Datasets:

ianiket23

/

podcast_llama_chat_format-1k

like 0

<s>[INST] Yeah, so the reason I ask about pronunciation, it's because yes, it is true that there are certain things were mispronounced kind of reveal that you don't care enough to pronounce correctly, you don't know enough to pronounce correctly and you dismiss the culture and the people, which I think for [/INST] your writing is </s><s>[INST] something that if it's okay, I'll go with Afghanistan just because I'm used to, I say Iraq Iran, but I say Afghanistan is as you're doing your writing, Afghanistan suffers from much misunderstanding from the rest of the world. But back to our discussion of this Pakistan Tajikistan, the whole region, that gives us context for the events of [/INST] 9 11. So yeah, if we go back to that day and the weeks, you know, that that followed, um my mind went to the community I knew in touch can um which was interesting. It was, I mean, they were so Islam was the focal point of our conversation in the US about 9 11, right? Everyone to know was relationship between the horrific violence and that religious tradition with its, you know, one million plus followers across the globe, right? That became the issue of course, for american security institutions, for local state and police institutions, right? I mean, it became the, I think it was the question that most americans have in their mind. So, again, I didn't imagine myself as someone who had all the answers of course. But given my background and coming at this from Russian history, coming at this from studying empire and trying to think about the region broadly. You know, I was very alarmed at the way the the conversation went. </s><s>[INST] Can I ask you a question, what was your feeling on that morning uh of 9:11? Who did this? Isn't that is that a natural feeling? It's coupled with fear of what's next, especially when you're in D. C. But also who is this? Is this an accident? Is this a deliberate terrorist attack? Because this uh domestic, what were your thoughts of the options and the internal ranking given your [/INST] expertise? I suppose I was taken by the narrative that this was international. I mean I I also lived in New York during one of the first bombings in 94 of the World Trade Center. So it was clear to me that a radical community had really fixed new york as part of the imagination of. And I immediately thought it was a it was a kind of blow to american power. And you know, I was drawn by the symbolism of it. If you think of it as an act, it was a kind of um an active speech if you will kind of a way of speaking to from a position of weakness speaking to you know, an imperial power. And I saw I saw it as a kind of symbolic, you know, speech act of that with horrific, you know, real world consequences for all those innocent victims for the firing of the police and just a, you know, the horror of the moment. Um, so I I did see it as as transcending the United States, but I did not see it as really having anything necessarily to do fundamentally about Afghanistan and the history of the region that I've been studying and the committee people that I knew who were not particularly religious, right? That the guys I hung out with actually wore me out because they want to go out every night. They want to party every night we're drinking. Yeah, we had discussions about alcohol. I mean, Uzbekistan is famous for its drinking. He's drinking. You know, it's something to look </s><s>[INST] forward to. So I didn't want to travel to that part of the, when, when was the last time you were in that part of the world? [/INST] Early two thousands. Well, in mid 2000, </s><s>[INST] way. So by the way, we're drinking vodka, what what's the problem with the weapon of choice [/INST] is Pakistan has incorporated vodka as as the the choice. Um, and it informs, you know, and it's, but the fascinating thing, you know, it's a student is what you're observing is a non muslim, you know, I'm a non Russian. This is all, you know, culturally new to me. And I'm, you know a student of all that right? As a grad student doing my work there. So you're like jane. Goodall of </s><s>[INST] vodka in Russia, just [/INST] observing. Yeah. And then then you you get you get the Ramadan, the grass vodka, you get, you know, I have I've had some long nights on the Kazakhstani frontier that I'm not proud of um you know, but you got to know the people </s><s>[INST] and some of them from [/INST] from but intellectually so that sort of thing. I mean the last thing there was it just as a I mean there's a whole um historian, right? But there are great contributions by, you know, anthropologists, photographers who have gone across the planet and try to understand how Muslims understand nutrition, a different context. So many aspects will say, you know, um this is part of our national culture to drink any as we please, right? And yet I'm a very devout muslim and so of course you can encounter other muslim communities who won't touch alcohol, right? But it's become kind of, I think it's very much um you know soviet culture left a deep impression in each of these places. And so there are ways of thinking, ways of performing, ways of enjoying oneself that are shared across so the former soviet space to this day, right? </s>

<s>[INST] as a developer. How would you recommend somebody listening to this? But also me uh, to get started with smart contracts and to get started with hybrid smart contracts. [/INST] Well. Well for hybrids more contracts, I'm going to have to do some kind of shameless promotion please? Where </s><s>[INST] let me twist your arm. [/INST] Thank you. I think you can go to our youtube. We we have a number of developer tutorials. Chain link Youtube. Yeah. Chain link, I think you can just start chain link on Youtube. You should, you should find it. Um beyond that we recently had a hackathon, we were we had a huge amount of very, very kind of advanced hybrid smart contracts getting built </s><s>[INST] to elaborate on that. You had a hackathon, is that something that people can follow along? Like a video or there's web page traces of what happened or is there a future actual hackathons that people could literally participate [/INST] it. There's plenty of more hackathons coming up. We want to enable as many developers and web three and web two to build hybrid smart contracts as a way to redefine our industry and kind of make all of these smart contracts come to life. Um there are definitely going to be more hackathons so people should go in and pre register register on a list to get involved in that. That's a great resource where we have a lot of speakers and a lot of educational tools, they happen over a course of weeks. Not they, so there's a long time for people to work on these things at the speed that they that they find comfortable </s><s>[INST] two questions. One is they're kinda hello World entry point for uh hybrid smart contracts and two on the hackathon side like what kind of stuff do you see people building at first just kind of getting their feet wet? Like in terms of the kind of applications that can be enabled. [/INST] I mean there's there's unbelievable things that that that we see people building I think how to get your feet wet. I think the Hello world is probably defy because it's pretty straightforward and there's a large amount of data sources that we already have putting data on chain on test net which is the test environment in which people would build. So I think defi is probably to a certain degree the most exciting for certain people and pretty pretty expansive in terms of the tutorials and the amount of contracts to see how people have already built it. Um I think beyond that we see people building amazing things at these hackathons in the previous hackathon we saw somebody build a smart contract that allows the rental someone to rent out their Tesla. Right? So it allows the Tesla p to give someone else access and rent out someone's Tesla on the basis of a smart contract kind of coordinating payment. Which was you know, which was kind of amazing the more recent Hackathon we saw something called the bridge which is a cross chain solution that lose historical networks to confirm data on different chains. So I think the things that people build will just become expansive and varied in ways that I can't I can't even imagine. Um But I I think this recent hackathon saw a huge huge list of different um different kind of winners in different categories and there's so many different categories. We even have a glove tech category and whole whole whole bunch of things if if people want to see what's possible they can go look at the winners. I think that's that's probably a good idea. Yeah that's that will be on the side of the hackathon. There's a blog related to that and we're going to have more of these. And what once again our our explicit goal is to take our industry into this world of hybrid smart contracts which just benefits everybody. It makes more on chain activity. It helps provide real world value to the average person from all of this infrastructure period. And at the end of the day I think that it just redefines what our industry is about through use cases right? Because if you only learn through our industry from the point of view of a single use case like the N. F. T. Use case or some other use case. That's what our industry is about and the more of these use cases that people can make available to the average person or to the Fintech world or to the insurance world or wherever the faster our industry will not just be about bit coins or tokens, it will be about changing global finance, changing global insurance, changing global trade and that's the change in the world that I and a lot of other people in this industry I think got got into this for </s><s>[INST] now. It's funny you mentioned about you've had a lot of kind words to say about Bitcoin and um ethereum as important technology that paved the way for the future and you somehow did not mention one of the most profound piece of technology which is dosh coin. What are your thoughts about this particular revolutionary technology and what are your thoughts about dosh coin going to the moon to mars and outside of the solar system? [/INST] I think those coin is is a very interesting kind of uh probably closer to a social experiment than anything else, </s><s>[INST] isn't everything. A social experiment. [/INST] Yeah, I I guess that's fair to to a degree. Um I think it's fascinating how how that's evolved. Um I think the people that made it made it with certain goals in mind and then it's kind of taken on a life of its own. I don't fully understand exactly why it's taken on a life of its own at this point. Um I once again I don't spend too much time thinking about, you know different tokens and and and how they're evolving. I'm much more focused on on the launching and </s>

<s>[INST] We talked a little bit about the difference between Judaism, Christianity and Islam. Because you may be talk about the difference between the Torah, the bible and the Koran. [/INST] So there's the hebrew bible is actually what's called a step cannon. That is, there are the five books of the Torah. Then there are books of history and the profits. Um, so books like Samuel Kings judges. Um, and then the prophets, Isaiah Jeremiah, Amos Ezekiel, so on and then there are what are called the writings, the writings are books like psalms proverbs job, the megalodon which are Esther daniel, all of those, all of those books um Ecclesiastes ah so in Hebrew is called the Tanaka, Torah, Navy MK two Vm, the Torah, the um prophets and the writings and that is the hebrew bible sometimes that's also called the tora, just to be confusing, but really the Torah generally refers to the five books. Then there is the new testament which the jews don't recognize as a sacred book. Um they recognize it as the book of another religion and I sometimes say to christians in order for them to really grasp this, jesus has as much religious significance to Judaism as Mohammed has to Christianity, that is jesus, although jewish became the founder of another religion. And for Judaism, that's not only inasmuch as christians and jews have had a lot of interactions, but religiously, jesus has no significance, said many beautiful things said some things I don't like so much like </s><s>[INST] what, like what [/INST] leave your father and mother and follow me. I don't like that as a religious model. Um now christians, christians will say that, I don't understand that, but they, but that's because christians like jews interpret their text different ways at different times. So um anyway, the Koran, which I know less well, I have read it, but I know it less well than I know the new testament and certainly less well, obviously that I know the hebrew bible um is a very, is in some ways, a parts of it are, I don't say this word, I say this because I can't find a better descriptive word, but but Muslims will not accept this. Okay, is it take off on the Torah in something that is, it's the same stories as the Torah, but they're different now, jews will say, and I being a jew will say this, that that's because Mohammed heard those stories from jews and also heard midrash, in which our rabbinic interpretations of those stories and he wrote those down, Muslims will say no, the jews got it wrong and Mohammed came along to correct the record and tell the real story, but </s><s>[INST] they're all telling the story of the same, [/INST] they hebrew, the hebrew bible part, the abrahamic part, they all tell the story of the same characters but tell them, they obviously christians accept the hebrew bible as sacred scripture. Um the Muslims retail, many of the stories in the bible, what is what is common to all of them, is that all of them are monotheistic faiths now in Christianity, that's more complicated because of the trinity, but as Christianity has developed over time, it clearly presents itself and thinks of itself and is a monotheistic faith as </s><s>[INST] well, what's the role of the word in each of these religions in the scriptures. So in terms of, so first of all oral, the role of oral traditions, the power of the exactness of the words in the scripture, Does it differ? Or is it really within the communities? The [/INST] different because in Christianity the words are not all the words of jesus, they are the words of jesus's disciples, none of the books of the new testament were written by people who met jesus in person. So they're different and therefore the and also we don't even know sometimes the original language of some of the things in the new testament in the bible and I understand in the Koran, but I'll speak for the hebrew bible. The idea is that that's LaShawn headquarters, that's sacred language and hebrew is in its, that's the language according to the tradition that God actually spoke to moses and therefore the exact words are infinitely interpret herbal and meaningful, </s><s>[INST] but the words were spoken by, written by moses and the same with Mohammed. But from memory or no, there are [/INST] different, there are different theories. I won't speak for Mohammed. You should ask, I don't want to get, I don't want to get that wrong. I don't want to get another religious tradition wrong in Judaism. The words are written by moses at God's dictation basically. That's the traditional view. There are other views that I'm happy to go into if you want to, but basically that's the traditional view. </s><s>[INST] What [/INST] makes it different? What makes Judaism and Christianity different is Christianity has an ideal life Judaism doesn't have an ideal life Judaism has an ideal book. So the holidays of Christianity are events in the life of God, God's birth, God's death and resurrection in Judaism, the holidays are all events in the life of the people, like the liberation from slavery or in the people's relationship to God like Yom kippur, which is a day of atonement. But there are no holidays in Judaism that are events in the life of God. Because in Judaism, God doesn't have a biography, God is eternal and God never came to earth. </s><s>[INST] And those events carry with them traditions and rules that you're to follow. Mentioned on one such event and scripture yet another time you walked through the fire, which is with exodus. Uh, that [/INST] was the first and </s><s>[INST] you never forget the [/INST] first, </s>

<s>[INST] won't get into architecture like you really, you really want to become physical reality. [/INST] Yes. And I've got close Rome wasn't built in a day. </s><s>[INST] Yeah, but Rome had to start somewhere, I gotta call you out on the advice, there really is a lot of people that look up to you and you've lived a really difficult life and you made it through all of it. What what what do you advise them to do, [/INST] do everything that you feel, even if you are told that it's the wrong thing. No, no, no, no, no, but not anything violent to </s><s>[INST] do what you feel, say what you feel like. Trust your heart, [/INST] Yeah. Trust your gut, trust your instincts. Because that instinct is who God made you to be not. You know what lines up with your like frat brothers or what lines up with what your dad wanted or what lines up with your classmates or you know, it's just God has something inside of you. And when you walk down the street, you're thinking about it and then you just see it in the window and you go down another street, you see the same thing or you're thinking about a number and that number pops up or you see it on a license plate and that's just you know, something is trying to say be the maximum, you know, be the maximum you and God won't give you anything that you can't handle. So for me, everything is a Yes, I think they say be like water. I know Bruce lee said that or matter of fact, just be because we are beings with engineering opportunities </s><s>[INST] beautifully put. Yeah. Uh, I have hope, I have faith that however, this turns out that you have the skill and the capacity to really add love to the world and I hope you do that. I really, really hope you do that. And we talked about the tension of that, the challenges and the opportunities of that. I [/INST] mean I see how we could be of use to each other. You actually have a particular thing for me as I eject from media because even also, you know, I'm really big and like, you know, burning the phoenix to all, you know, as an engineer that yourselves completely regenerate every seven years. I think I, I rushed the process a little bit so I run around looking like a burn victim sometimes, </s><s>[INST] but I gotta tell you anyone I, I'm close with, I work with, there has to be trust, there has to be love and I think you've been burned quite a bit in your life [/INST] sometimes. I did it myself, I put my hand on the stuff so how do we get to engineering? There's a deal to be done here, not saying you're making this money off of that and making that money off, but there's same twins. So there's dealings here, you got pain, I got pain but were beings with engineering opportunities </s><s>[INST] for a long time. I thought somebody should create a new social network and it looks like a great engineering could do that. You [/INST] got to at one time from two of your homeboys at one time. </s><s>[INST] Yeah. And that's a great way. I mean every, you know, it can be done from scratch or it can be done a new with an already established platform. Yeah, I'm very excited by that possibility parlors smaller, twitter is larger. I wonder whether you can do any kind of revolutionary engineering with a large company. If anyone can, I would say it's Ellen, [/INST] well, Ellen can look at what we do over here. That's why I like God does this a lot of times. Uh, he creates doppelgangers. There's a lot of examples where theory happen two places at one time. A really similar type of personality happens at one time. It's </s><s>[INST] weird. It's beautiful, hilarious actually. It's kind of humorous. [/INST] So we should, we should just share every piece of information together as like as I go bill parlor and as he builds up twitter and see how to make both those better. But I'll be like, hey, I'm not gonna let Snapchat bully me out of, you know, adding something to it. That's best. It should just be the best platform possible. That means that, you know, that means Tiktok has amazing features, twitter has amazing things about it. I know this girl that's like, I like instagram better than twitter is just she likes that twitter has porn but other than that instagram but I was like, well instagram is pouring also it's like soft, it's more subtle. It's not telling you it's not, it's not conservative by any means, you know, and I </s><s>[INST] mean that's the thing, you have to please a lot of people with these platforms and I think the goal of a platform should be to help individuals maximize their long term happiness and growth, like intellectually spiritually, psychologically, all of that. It's a tricky thing to figure out how to do that. Of course you could just have a platform just, just strictly for fun. I think that's where Tiktok leans, but um, there has, I think there's a balance to strike like twitter. There's a lot of intellectual philosophical stuff going on on twitter, but it's somehow currently makes it too easy to be divisive and hateful towards each other and cancel and all that kind of stuff. [/INST] I think we need to have these healthy conversations. That's what it is. Healthy conversation healthy dialogues. That's the biggest thing. Like when I first wore the red hat, the conversation is less healthy than it is today. The conversation about George Floyd. You know, it's like, did I send the tweet the right way. Did is Candace Owens documentary. Perfect. Is what Michael moore is that documentary is perfect century self isn't fully accurate. You know, it's 2-3 hours of a transmitter of information through uh, particularly usually one person's view and anything you want to research if you're interested in it, You gotta look at 10 versions of it. 20 versions of it, George Floyd, we've looked at one version of that now, we have a second. Well, by the time we get to the you know, I know this is like, it's it's not my last hoody but it's definitely not my first hoodie that I put on. You know, it's like, that's how we got to like even this particular size of zipper or the fact that, you </s>

<s>[INST] smooth pickup line by the way, if I've ever heard one that's good, you want to get out of here, [/INST] so start dating and she was the girl that screwed my brains out man and I felt head over hills, we got married six months later, six months, that's what it does and I had, I was, she didn't know it was a crook. She had no idea. Now. She knew I was very bright, you know, I would do a lot of theater stuff like that. I got a job at, I was in Hazzard, there was no jobs to be had. So I got a job in Lexington because we were going to be moving to the UK, got a job in Lexington at Lexmark testing, printer boards, um, circuit boards. So I would leave on a thursday night work 3 18 hour shifts at Lexmark, come back home on monday. Um, got married, faked a car accident to get that. Then the other, the rest of the money that I needed to get married. And the faking on that man. I had bought a A Chevy spectrum at a car auction gave like $500 for it. My aunt had previously defrauded usa insurance on a car accident and she was telling me all about it. She's like, look, go down to this chiropractor, make sure you get the insurance where they'll pay for a rental car, they'll pay lost wages. I was like, they pay lost wages. She's like, yeah, they pay lost wages. I was like, she's like, by the way you work for me and I was like, I work for you. So </s><s>[INST] you don't get to define the with the wage. And you can also define how long you were unable to work. [/INST] Exactly. Exactly. And the chiropractor will sign off on any damn thing. Alright, so my cousin Ronnie, he figures out that I'm going, he finds out I'm going to fake this car accident. So he comes to me, he's like, hey man, can I get in on that? I was like, yeah man, you get on that. So this kid, he's five days younger than I am, this kid. He goes to the dentist the day that we're faking, it has a tooth pulled, tells the dentist not to numb it, not to stitch it. Just pull it. So he shows </s><s>[INST] up, [/INST] he shows up the day that we're driving out to fake the accident. He's got blood all over his shirt. He's still bleeding out of the mouth and everything else. I'm like, are you okay? And he's like, yeah man, it's gonna be good. It's gonna be good. I'm like, ok. So my mom, by this point, I'm living with my grandparents. My mom is up in the head of a hollow. So we're like, well just do it up there. We'll go act like we're visiting my mom on the way back out, ran over a mountain. Okay? So we go visit and everything come back out that night, run over the side of the hill. Me and Ronnie walked back up. Of course it totals the car, walk back to my mom's acting like we've wrecked. She knows what time it is and everything else and follow the claims. So that gets the money to get married and me and my wife moved from hazard to Lexington and I'm the kid that my crime usually if I was a single guy wouldn't break the law and I would be all right, you know, but females involved Oh yeah, Oh yeah, I got to spend the money. You gotta show them gifts. Everything else was never enough to show love in some sort of healthy way. Always had to go overboard and typically it was buying or stealing some sort of expensive. </s><s>[INST] So that, that was, that was the thing that was the way you show love is by buying expensive gifts [/INST] or something overboard back then with with Susan initially it was don't worry about working. I got it. You just worry about going to school. She was a music major. I was like, you just worry about going to school, so don't worry about cooking and cleaning. I got it. I got it. So not only was I this this guy that was going overboard, but it's kind of a control freak too. Right? So now I got it. I got it. I got it. So here I am, you know, 60 hour week job, 18 hour class load, cooking, cleaning, something had to give, I quit the job. I couldn't do it, quit the job and start back in fraud and trying to hide that from her at the same time. So it was initially telemarketing fraud started, I was working at the first job I had was a telemarketer at a cemetery selling gravesites and then that ended, went over to work for the Shriners Circus, Shriners Hospital and there was a third party company that was doing all the telemarketing, made really good money doing that. That job ended and then they pivoted over to um working with Kiwanis clubs selling food baskets to the food banks and everything. So I stole the phone list and started at my own Kiwanis club and would do the telemarketing, go out twice a week and pick up checks. Well what happened was is I'm going out picking up Jax, go knock on the door, turns out one of the persons that I had called was a law enforcement officer, so he was like who are you? I'm like I'm with the Kiwanis club and he's like no you're not. </s><s>[INST] So [/INST] got arrested, spent three months in the county jail for theft by deception. Got out and we had to move from from Lexington back to Hazzard and lived with Susan's parents. They had gotten a desktop computer hp and I started surfing around online, found Ebay and didn't really know how to make money on Ebay about the same time, I'm committing low level frauds online, I don't really talk about that in the past the first time I've really talked about that but I would pay for it with bad checks. So </s>

<s>[INST] Do you often think about it as um as a simulation? So as the universe being kind of computation that has might have bugs and exploits? [/INST] Yes. Yeah, I think so. Physics </s><s>[INST] is essentially, [/INST] I think it's possible that physics has exploits and we should be trying to find them arranging some kind of a crazy quantum mechanical system that somehow gives you buffer overflow somehow gives you a rounding error in the floating point. Uh </s><s>[INST] Yeah, that's right. And like more and more sophisticated exploits. Those are jokes, but that could be actually [/INST] very close. We'll find some way to extract infinite energy. For example, when you train reinforcement learning agents um in physical simulations and you ask them to say run quickly on the flat ground, they'll end up doing all kinds of weird things. Um in part of that optimization, right? They'll get on their back legs and they will slide across the floor and it's because the optimization, um the enforcement learning optimization on that agent has figured out a way to extract infinite energy from the friction forces and um basically they're poor implementation and they found a way to generate infinite energy and just slide across the surface and it's not what you expected. It's just a it's sort of like a perverse solution. And so maybe we can find something like that. Maybe we can be that little dog in this physical simulation, </s><s>[INST] the cracks or escapes the intended consequences of the physics that the universe came up with. We'll figure out some kind of shortcut to some weirdness and then but see the problem with that weirdness is the first person to discover the weirdness, like sliding in the back legs, that's all we're gonna do. [/INST] Yeah, </s><s>[INST] it's very quickly because everybody does that thing. So like the paperclip maximize er is a ridiculous idea, but that very well could be what then we'll just we'll just all switch that because it's so fun. [/INST] Well no person will discover it. I think by the way I think it's going to have to be uh some kind of a super intelligent A. G. I. Of a third generation, like we're building the first generation A. G. I. You know, </s><s>[INST] third generation. Yeah, so the bootloader for an ai that ai will be a bootloader for another [/INST] guy </s><s>[INST] and then there's no way for us to introspect. Like what might even, I [/INST] think it's very likely that these things for example, like so you have these G. I. S. It's very likely, for example, they will be completely inert. I like these kinds of sci fi books sometimes where these things are just completely inert. They don't interact with anything and I find that kind of beautiful because they probably they probably figured out the meta meta game of the universe in some way, potentially they're they're doing something completely beyond our imagination. Um and they don't interact with simple chemical life forms, like why would you do that? So I find those kinds of ideas compelling. </s><s>[INST] What's their source of fun? What are they, what are they doing [/INST] solving in the universe? </s><s>[INST] But inert. So can you define what it means inert? So they escape the interaction, [/INST] physical realities as in um uh They will behave in some very like strange way to us because they're they're beyond their playing the meta game. And the meta game is probably say like arranging quantum mechanical systems in some very weird ways to extract infinite energy uh solve the digital expansion of pi to whatever amount they will build their own like little fusion reactors or something crazy. Like they're doing something beyond comprehension and not understandable to us and actually brilliant under the hood. </s><s>[INST] What if quantum mechanics itself is the system? And we're just thinking it's physics but we're really parasites on not parasite. We're not really hurting physics. We're just living on this organism and this organism and we're like trying to understand it. But really it is an organism. And with a deep deep intelligence maybe physics itself is uh the the organism that's doing the super interesting thing and we're just like one little thing. [/INST] Yeah </s><s>[INST] and sitting on top of it trying to get energy from it. [/INST] We're just kind of like these particles in the wave that I feel like it's mostly deterministic and takes universe from some kind of a big bang to some kind of a super intelligent replicator, some kind of a stable point in the universe given these laws of physics, you </s><s>[INST] don't think uh as Einstein said, God doesn't play dice, so you think it's mostly deterministic, there's no randomness and the thing [/INST] I think is deterministic, there's tons of, well, I want to be careful with randomness, </s><s>[INST] pseudo random. [/INST] Yeah, I don't like random. I think maybe the laws of physics are deterministic. Um Yeah, I think they're determined </s><s>[INST] just got really uncomfortable with this question. I do you have anxiety about whether the universe is random or not? What's there's [/INST] no randomness </s><s>[INST] you like? Good will hunting, It's not your fault andrei [/INST] it's </s><s>[INST] your fault, man. Um So you you don't like randomness uh [/INST] yeah, I think it's unsettling, I think it's a deterministic system. I think that things that look random, like say the collapse of the wave function, et cetera. I think they're actually deterministic, just entanglement and so on and some kind of a multiverse theory something something. </s><s>[INST] Okay, so why does it feel like we have a free will, like if if I raised his hand, I chose to do this now. Um what that doesn't feel like a deterministic thing, it feels like I'm making a choice, [/INST] it feels like it </s><s>[INST] okay, so it's all feelings, it's just feelings. So when RL agent is making a choice is that um it's not really making a choice, the choice is already there. [/INST] Yeah. You're interpreting the choice and you're creating a narrative for for having made it. </s>

<s>[INST] The thing about freedom is when you have freedom, you also have the responsibility for your actions and that could be a huge burden. Yeah, because if you succeed, it's you, but if you fail, it's you. And if you do horrible things, it's you, if you don't do something, for example, if you don't help people in North Korea, it's you. And that's a huge burden. And living with that burden is a kind of suffering. I mean, there's some aspect in which freedom is suffering [/INST] because </s><s>[INST] life is suffering and then the freedom is uh, you as an individual fully living through that. So you talk to your friends with Michael malice, he believes. And so I want to kind of ask you about government. Uh, he believes he's an anarchist and he believes kind of freedom fully implemented in in human societies, meaning that humans should, uh, all be free to choose how they, you know, transact with each other, how they live together, There shouldn't be a centralized force that tells you what to do. Do you think there's some role for government in um, in a healthy society? So if you look at North Korea, there is the most horrible implementation of government. But then if we look at what the United States strives to be at least in principle, there's uh, there's an ideal of a government that represents the people and helps the people. Like, is there, is there a place for that kind of ideal? Or is government always going to get us into trouble? [/INST] I am not. I mean, I spoke to Michael malice, I kept asking why why is anarchist, right? And he doesn't even believe military? None of it. And I was like, I was like, I don't think I want to be in the world you're describing when that's really scary. I want the law enforcement. I want like I don't in a way that so why equality makes no sense. Is that the fact that we knew and I were born, we were born in a very different capability of thinking, different intelligence, different, capable in our physics, Right? So, equality is nonsense. You can never achieve that. All right. So, to me, that's been it's very scary when the government equality on everybody. That is impossible. That </s><s>[INST] specifically equality of outcomes. Like given that we all started different places, enforce like measure in some kind of way where people stand and if they're an equal enforce equality. Yeah. And that's what leads to the kind of things that you mentioned with the class system in North Korea. [/INST] Yeah. So, I think that's why government can be bad. They can be very dumb. And another thing is that they cannot know what you want. A lot of times people don't even know what they want and individual like how the heck do you or some government gonna know what is best for you? Nobody knows. We just all do our best. I do think there's some governments against Switzerland, you know, have more give power to the different state chemical. I think I'm more, you know, like giving power to the state and the individual decide where they want to go ingredients taste like I mean why did you choose texas right? There's no income tax, right? Like there's a lot of things people find texas like you know charming and they come here so in a way that I don't want to be the one strong government makes every single thing the same way in a way I want to kind of experiment to everything. We can have anarchy state, there's no police, nothing going on. You can be whatever one you want and you can go on stage really is like abortion is bad blah blah. This is bad. All the conservative values and let the ideas compete and let them how they are being pregnant in real real life. But I think it's very scary when the U. S. Government is getting bigger and bigger and then they try to make every state under one big government. And that's like when I get really alarmed, </s><s>[INST] are there things that you see in the United States in the current culture that kind of has echoes of the same things you saw in North Korea. That that worry you that much. [/INST] Absolutely. It's it's uh it's in America now the meritocracy doesn't matter right? It's evil. The white man's idea of like talking about if you're competent enough, there's like oh if you're coming from which right family you are going to be competent. So other people don't have a chance. But look at asians who came from, nothing is competent and go like Harvard Law school and medical school. So it doesn't almost, it's like there's no incentive for you to work hard anymore in the system right now that is north Korea, there's no incentive because you're born with your class already. So no matter what you do you can never know the whole everything about North korean system is that there's nothing holding marry up. So if you're coming from other cultures that like make a market, joined the royal family and she became a lawyer, you go up by North Korea. If someone from high class gonna marry somebody down, you only go down with them. That's how they prevent class mix </s>

<s>[INST] Yeah. No, he's not. I mean the same way you are, he's annoying in the same way, which is like he drops truth bombs. It's like, yeah. Yeah, that's [/INST] so true. Yeah. We're probably comparably, you know, doing that, you know, there. </s><s>[INST] But he's so he his profession requires that. So he's not just like a motivational speaker, whatever. He uh, he's a computer science, theoretical computer scientist and he needs the long hours in the day of doing like serious math. So it's mostly math proofs. And for that you have to sit and think really deeply, it's like really hard work compared to like uh what most people do. Like even what I mean, what I do like programming is way easier than rigorous math proofs because you have to basically you have this machine and you have to your brain to turn out logic In a focused way while visualizing a bunch of things and holding that in your brain and holding that for 10 minutes, 20 minutes, hopefully several hours and you're not just like doing homework. You're doing totally novel stuff. So like stuff that nobody's ever done before. So you keep running up against the wall of like fun this is a done and on, No, wait, is this a dead end? And like that whole frustration, that serious mental work. That's like incredibly difficult mental work. So he knows what he's talking [/INST] about. It's amazing. But like you said, he's like, this seems like the standard for the quality of work that he needs is so high. So almost anything less than this level of Systematize ation an organization would preclude it. </s><s>[INST] So he can't afford the kind of bullshit that I don't know about you. But certainly I do, which is like last deadline kind of stuff because you can't do that kind of work, uh, last minute on that kind of stuff. So my, my question for him in general is like, and for you, and I was like, well, here's these negative patterns that we do of like doing shit last minute and so on. Is this just who we are now? Or are there [/INST] some, I'm really big into a free will. You know, I was thinking that it's mostly predestination that at least in this regard, </s><s>[INST] it's the same with like communism, like as long as it fits my, uh, whatever is the lazy thing to do, I'll just not [/INST] believe it. I'm not a congressman opportunist, uh, that </s><s>[INST] I'm an opportunistic communist and capitalist. I just do whatever, whatever. It's cool at the time. Exactly. Uh, let me ask you to examine some fundamental principles of a particular thing that joe Rogan brought up to me several times online and offline, which is that he thinks that the tie that I wear is something that makes me vulnerable to attack. That you should be. The reason he doesn't wear a tie is because he can get choked very easily with a tie. It's a big concern. Okay. My contention and by the way, he wore a suit last time to, uh, he didn't wear it on the podcast. He wanted for dinner later. [/INST] Yeah. I wore a suit the other day and I had no socks on. I didn't realize. Yeah, you're supposed to wear socks. Yeah, that's, that's my understanding </s><s>[INST] what you wear a suit, [/INST] you go to court. I don't know. And I don't know. I don't know. I just wanted to play. I wanted to pretend I was an adult for a day. </s><s>[INST] Okay, cool. So, uh, so my contention is like the jacket, everything is more dangerous than a tie. [/INST] That's kind of where I was going with. That. That's kind of where, yeah, this was my first thought too. Like if once the tie becomes an issue, like, </s><s>[INST] like everything else is already [/INST] and it's already an issue </s><s>[INST] because the tie to me now without, like messing with it now is to me has some of the similar problems that a belt does. So like for example, I don't know about you. Maybe you can correct me, but I'm not sure you can use the belt as tied, Uh, you know, I know there's some kind of guards, you can probably utilize the belt with, but the belt, sorry, when it's tied around the waist [/INST] belt belt or a G </s><s>[INST] bo g belt, Gabo importantly belt, it's not that great of a thing to use in most cases, I would say, because it slides, it doesn't, you can probably invent a few interesting ways to use it as leverage is control and so on. But there's just so many more things around belt better. And so for me, the time, what people don't realize [/INST] are we trying to sell a DVD here and have some some widgets and bells and whistles, because in that case the belt is really important part of what we do, and I would really encourage you guys to look into it. Uh, if we're trying to actually like, learn something and say you, like you said, we're surrounded by better </s><s>[INST] options. Well, that's the thing. I mean, it's not obvious to me that the belt, maybe there's actually undiscovered things about using the belt. You know, I think people have used, like, like putting a foot inside the belt somehow inside to give lt [/INST] some this is a no punches. G grappling situation. Yes, Okay, I guess so, started fairly contrived, </s><s>[INST] right? But with punches to like, is there, okay, let's let's talk about the street fights with a belt that's like a jeans belt, like a belt clothing belt. [/INST] Okay, so I get to take it off and whipped him in the face of the buckle. How serious is this street fighter we're talking, but they're not serious? Or are we talking? </s><s>[INST] Like, like death? Like one of you has to die? Oh yeah. [/INST] Whoa. Okay. You ever, like, </s>

<s>[INST] No, it's uh I mean it has a sense like the Stranger by camus has a sense of like this is how life is and it's like has more about old age and that you're not quite the man you used to be feeling of like this is how time passes and then the passing of time and how you get old, you get older and this is one last fish. It's less about this is the fish, It's more like this is one last fish, like and asking who was I, who was I As a man, as a human being in this world. And this one fish helps you ask that question fully. [/INST] Wonderful. It's one fish which is just sort of all the other fish to write. And and that is a big difference because for for ahab, no other fish will do that movie Dick. It's got to be the biggest, the most powerful, the most tormenting. It's got to be the one that you've got history with that has filed you. And it's uh it's a raucous ride movie, Dick. What about David </s><s>[INST] Foster Wallace. So why is he important to you in the search of meaning? Uh in a secular age? [/INST] Good. So, so I'll just, just to finish the movie Dick thing, I think what's interesting about Melville is that he thinks our salvation comes, not if we get in the right relation to monotheism or Christianity, but if we get in the right relation to polytheism to the idea that there's not a unity to our existence, but there are lots of little meanings and they don't cohere sometimes, you know, uh like in like in Homer, sometimes you're in Love Helen's in love with paris and they do crazy things, they go off and run away and the Trojan war begins and sometimes you're in a Battle Fury that love is Aphrodite's realm and the Battle Fury, that's Aries realm and that's a totally different world. And they're not even I mean they're related, there is a kind of family resemblance but not much. Mostly you're just in different sort of local, meaningful worlds. And Melville seems to think that that's that's a thing that we could aim to bring back. He says we have to lure back the mary made a gods of old and and lovingly and thrown them in the now egotistical sky. The now on haunted hill. That's what we live in this world, where hills aren't aren't haunted with significance anymore. And the sky is just a bunch of stuff that we're studying with physics and astrophysics and stuff, but they used to be all inspiring and we have to figure out how to get in that relation to them, but not by trying to give a unity to our existence through developing habits and practices that get written on our body. And so his is about the end of Judeo Christianity and the sort of roman appropriation of it in Wallace. What one of the things I think is so interesting about him is that I think he has a great observer of the contemporary world and he's a very funny writer. It is really funny, but he's a great observer, the of the contemporary world, what he thought was at the core of the contemporary world. Was this constant temptation to diversion through entertainment. That's a different story than Heidegger story about efficiency and optimization. But it's the other side of it? Like what is this temptation temptation sort of diverting us from the ability to be more efficient? So, you know, you're attempted to go, you know, watch some stupid film or television show or something that's dumb and not really very interesting. But you read that temptation is a temptation precisely in virtue of its taking you away from your optimizing your your existence. And so I think there are two sides of the same coin. I think he's brilliant at describing it. I think he thought it was a desperate position to be in that. It was it was something that we needed to confront and find a way out of And his characters are trying to do that. And I think there's two different David Foster Wallace is one. I mean, David Foster Wallace committed suicide and when I, and it's very sad and he clearly did have, you know, sort of there was a physiological basis to his condition. He knew it. He was treating it from decades with medication. He had electroshock therapy a number of times. It's just very, very sad story when I decided that we were going to write about David Foster Wallace. The first thing I was worried about is what can you, can you like obviously a motivating factor may be the motivating factor in his committing suicide? Was his physiological condition? Um, but there was there's there's this, there was a question, could you think, I mean, he's obsessed with the condition with what we need to do to achieve our salvation, to live well, to make our lives worth living. And he clearly in the end felt like he couldn't do that. So in addition to the physiological thing, which probably most of it, the question for me was could you find in his writing what his, what he was identifying as the thing we needed to be doing that he nevertheless felt we couldn't be doing. And and he talks as if that's that's the difficulty for him. Uh, so, so that that's one side of him and I did want to find that. I think there's another side of him that's very different. But you were gonna </s><s>[INST] ask please, what's the other side? [/INST] I mean, what I write about in the, in the chapter mostly, um is what I think he's got as are as as our saving possibility, he thinks are saving possibility. He says this in a graduation speech that he gave to Kenyan, is that um we have the freedom to interpret situations however we like. So what's the problem case for him? He says, look, you know, the problem case, we have, we have it all the time. You get pissed off into the world. You know, some some big suv cuts you off on the highway and you pissed off and you might express your anger with one finger or another directed at that person and he says, but actually, you know, you're being pissed off as the result of your having made an assumption. And the assumption is that that action was directed at you. Like the assumption is that you're the center of the universe and you shouldn't assume that. And the way to talk yourself out of it, he says, is to recognize the possibility. Maybe that wasn't an action directed at you. Like maybe that guy is racing to the hospital, you know, to take care of his dying spouse who's been there suffering, you know, from cancer or maybe he's you know, on the way to pick up a sick child or maybe he's and it's not an action director. That was your assumption, not something that was inherent in the situation. And I think there's something interesting about that. I think there's something right about that at the same time, I don't think he speaks as if we can just spin out these stories and whether they're true or not, doesn't matter what matters is that they free us from this assumption. And I think they only free us from this assumption if they're true. Like sometimes the guy really did directed at you and that's part of the situation. And like you can't pretend that it's not part of the situation. You have to find the right way of dealing with that situation. So you have to listen to what's actually happening and then you have to figure out how to make it right. And I think he's he thinks that we have too much freedom. He thinks that you don't have to listen to the situation, you could just tell whatever story you like about it and I think that's actually too tough. I don't think we have that kind of freedom. And he and he writes these sort of incredibly moving letters when he's trying to write The pale King, which is the end of which is the unfinished novel that really sort of drove him to distraction. At the center of the novel is this character who was one of the characters at the center of the novel is a guy who's doing the most boring thing you could possibly imagine he is an I. R. S. Tax examiner, he's going over other people's tax returns trying to figure out whether they follow the rules or not. And like just the idea of doing that for eight hours a day is just terrifying. And and he puts this guy in an enormous warehouse that extends for miles where a person after person after person is in rows of desks, sort of nameless each of them doing this task. So he's in nowhere doing nothing. And it's got to be intensely boring. And now the main character is trying to trying to teach himself to do that. And the question is how do you put up with the boredom? How do you put up with this onslaught of meaninglessness and the main character is able to confront that condition with such bliss that he literally levitates from happiness while he's going over other people's tax returns. And I that's that's my metaphor for what I think Wallace must have imagined. We have to try to aspire to, and I think that's unlivable. I think that's not I think that's not an ambition that we could achieve. I think there's something else we could achieve. And the other thing that we can achieve that, I think is is is something that he also is onto but doesn't write about as often is something more like achieving peak moments of significance in a situation when something great happens. And he writes about this in an article about Roger Federer, he loved tennis, Are you a tennis lover? </s>

<s>[INST] this there's this going back and forth and now there's a feeling like you're censoring a little bit too much. And so I would lean, I would try to be ahead of that feeling. I would now lean towards freedom of speech and say, you know, we're not the ones that are going to define misinformation. Uh, let it be a public debate. Let the idea stand. And I actually place, you know this idea of misinformation, I place the responsibility on the poor communication skills of scientists. They should be in the battlefield of ideas and everybody who is um spreading information against the vaccine, they should not be censored. They should be talked with and you should show the data you should have open discussion as opposed to rolling your eyes and saying I'm the expert, I know what I'm talking about. No you need to convince people it's a battle of ideas. So that's the whole point of freedom of speech is the way to defeat bad ideas is with with good ideas with speech. Um so like the responsibility here falls on the poor uh communication skills of scientists. Thanks to social media. Scientists are not communicators. They have the power to communicate. Some of the best stuff I've seen about covid it from doctors is on social media. It's a way to learn to respond really quickly to go faster than the peer review process. And so they just need to get way better at that communication and also by better. I don't mean just uh convincing. I also mean speak with humility. Don't talk down to people all those kinds of things. And as a platform I would say I would step back a little [/INST] bit. </s><s>[INST] Not all the way of course because there's a lot of stuff that can cause real harm as we've talked about. But you lean more towards freedom of speech because then people from a brand perspective wouldn't be blaming you for the other ills of society which there are many the institutions have flaws, the political divide. Obviously politicians have flaws that's news, the media has has flaws that they're all trying to work with. And because of the central place of facebook in the world, all of those flaws somehow kind of propagated facebook and you're sitting there in the in as plato the philosopher have to answer to some of the most difficult questions asking being asked of human civilization. So I don't know, maybe this is an american answer though, to lean towards freedom of speech. I don't know if that applies globally. So yeah, I don't I don't know but transparency and saying, I think as a as a technologist, one of the things I sense about facebook and matter when people talk about this company is they don't necessarily understand fully how difficult the problem is. You talked about aI has to catch a bunch of harmful stuff really quickly. Just the sea of data you have to deal with. It's a really difficult problem. So like any of the critics, if you just hand them the helm [/INST] for </s><s>[INST] a week, let's see how well you can do like that to me that that's definitely something that would wake people up to how difficult this problem is. If there is more transparency is saying how difficult this problem is. Let me ask you about on the eye front just because you mentioned language and my in eloquence translation is something I wanted to ask you about. And first just to give a shout out to the supercomputer, you've recently announced the ai research Supercluster RSC obviously I'm somebody who loves the Gpu s. It currently has 6000 Cpus and NVIDIA G G X a one hundred's uh is the systems that have in total 6000 Cpus and uh it will eventually maybe this year, maybe soon we'll have 16,000 GPU s so it can do a bunch of different kinds [/INST] of </s><s>[INST] machine learning applications. There's a cool thing on the distributed storage aspect and all that kind of stuff. So one of the applications that I think is super exciting is translation, real time translation I mentioned to you that you know having a conversation I speak Russian fluently, speak english somewhat fluently and I'm you know having a conversation with Vladimir Putin say as a use case me as a user coming to you in the use case we both speak each other's language. I speak Russian, he speaks english. How can we have that communication go well with the help of a I I think it's such a beautiful and powerful application of ai to connect the world that bridged the gap not necessary between me and Putin, but people that don't have that shared language um can you just speak about your vision with translation because I think that's a really exciting application [/INST] if you're trying to help people connect all around the world, you know, a lot of content is produced in one language and people and all these other places are interested in it. So being able to translate that um just unlocks a lot of value on a day to day basis. So the kind of ai around translation is interesting because it's gone through a bunch of um a bunch of iterations, but the basic state of the art is that you don't want to go through, you know, different kind of um intermediate symbolic um representations of of of language or something like that. It's you basically want to be able to map the concepts and and basically go directly from one language to another and you just can train um bigger and bigger models in order to be able to do that. And that's where the the the research supercluster comes in is basically a lot of the trend in in machine learning is just you're you're building bigger and bigger models and you just need a lot of computation to train them. So it's not that like the translation would run on the supercomputer, the training of the model, um which which could have, you know, billions or trillions of examples of just basically that um your your training models on this supercluster in, you know, days or weeks, that might take a much longer period of time on a smaller cluster. So it just wouldn't be practical for most teams to do. But the translation work. Um we were basically getting from, you'll be able to go between about 100 languages seamlessly today. Um to being able to go to about 300 languages um in the near term and so </s>

<s>[INST] yeah, to me, so maybe I'll throw a wrench into your thing. Uh to me it's super interesting from an engineering perspective. So if you look at virtual reality systems, the actual question is how much computation and how difficult is it to construct the world that like, there are several levels here. One is you won't know the different our human perception systems and maybe even the tools of physics won't know the difference between the simulated world in the real world. Um that's sort of more of a physics question. The most interesting question to me has more to do with why food taste delicious, which is created, how difficult and how much computation is required to construct a simulation where you kind of know it's a simulation at first, but you want to stay there anyway. And over time you don't even remember. [/INST] Yeah. Well anyway, I agree. These are kind of fascinating questions and they may be very, very relevant to our future as a species. But yeah, they're just very far from anything. I </s><s>[INST] but so from a physics perspective, it's not useful to you to think, taking a computational perspective to our universe, thinking of as an information processing system and then they give it as doing computation and then you think about the resources required to do that kind of computation and all that kind of stuff. You can just look at the basic physics and who cares what the computer is running on this? Yeah, it's just, I mean the kinds of it [/INST] mean I'm willing to agree that you can get into interesting kinds of questions going down that road, but they're just so different from anything from what I found interesting. And I just again, I just have to kind of go back to life is too short and I'm very glad other people are thinking about this, but I just don't see any any, anything I can do with it. </s><s>[INST] What about space itself. So I have to ask you about aliens again something since you emphasize evidence um do you think there is? How many do you think there are and how many intelligent alien civilizations are out there? I [/INST] have no idea what I've certainly as far as I know unless the government is covering it up or something we haven't heard from. We don't have any evidence for such things yet but there's there seems to be no there's no particular obstruction why there shouldn't be. So </s><s>[INST] I mean do you you work on some fundamental questions about the physics of reality when you look up to the stars? Do you think about whether somebody is looking back at us? [/INST] Yeah. Actually I originally got interested in physics. I actually started out as a kid interested astronomy exactly that telescope and whatever that and certainly read a lot of science fiction and I thought about that I find over the years I found myself kind of less anyway less and less interested in that just because I don't I don't really know what to do with them. I also kind of at some point could have stopped reading science fiction that much kind of filling out that there's just too that the actual science I was kind of learning about was perfectly kind of weird and fascinating and unusual enough but better than any of the stuff that in Isaac Asimov. So why should I? Yeah </s><s>[INST] and you can mess with the science much more than the distant science fiction. Uh the one that exist in our imagination or the one that exists out there among the stars. Well you mentioned science fiction, you've written quite a few book reviews. I got to ask you about. Some books perhaps if you don't mind. Um is there one or two books that you would recommend to others? And maybe if you can what ideas you drew from them either? Negative recommendations. Impossible. We'll do not read this book [/INST] for sure. Well I must say. I mean unfortunately yeah you can go to my website and there you can click on book reviews and you can see I've written read a lot of a lot of I mean as you can tell from my views about string theory, I'm not a fan of a lot of the kind of popular books about isn't string theory. Great and that yes, I'm not a fan of a lot of things of that kind </s><s>[INST] of. Can I see a good question on this, a small tangent? Are you a fan? Can you explore the pros and cons of forget string theory sort of science communication sort of cosmos style communication of concepts to people that are outside of physics, outside of mathematics, outside of even the sciences and helping people to sort of dream and fill them with all bought the full range of mysteries in our universe. [/INST] That's a complicated issue I think, you know, I certainly go back and go back to like what inspired me and maybe to connect to connect a little bit to this question about books. I mean certainly one of the books that some books that I remember reading when I was a kid were about the early history of quantum mechanics. Like Heisenberg's books that he wrote about, you know, kind of looking back at telling the history of what happened when he developed mechanical. It's just kind of a totally fascinating, romantic, great story and those were very inspirational to me. And I would think maybe other people might also also find them that. But </s><s>[INST] the and that's that's almost like the human story of the development of the ideas. [/INST] Yeah, the human story. But yeah, just also how, you know, they are these very, very weird ideas that didn't make sense that how they were struggling with them and how, you know, they actually Anyway, it's I think it's the period of physics kind of beginning 1905 Plank and Einstein and ending up with the war when these things are get used to, you know, make passively destructive weapons. It's just the truly </s>

<s>[INST] So the elder scrolls has or at least Skyrim has some humor, has [/INST] a little bit </s><s>[INST] but leans into a little more, [/INST] a little bit more, a little bit more. Yeah. Yeah, it does, it's like ironic humor, it's the duck and cover it. So get under your desk if the bomb comes and everything will be fine, it's that type of humor. </s><s>[INST] So the funny thing is, I do think Fallout three is one of the greatest games ever. Uh You said that quote when we started Fallout three in 2004, we obviously had big ideas of what we could do with it. And I talked to a lot of people from X developers to press folks to fans what made it special. What are the key things you'd want out in in a new one? The opinions and I'll put this mildly varied a lot, but they would all end the same like a stern father pausing for effect but do not screw it up. How do you not screw up a game? You have not screwed up many games yet. [/INST] I mean back to the fallout one. Yeah, that was, look that I remember that we were met with a lot of skepticism in terms of, oh, what are they going to do with this? It was a beloved kind of isometric, turn based role playing game, you know, awesome for when it came out. Um And actually it was announced we had finished more win but not announced Oblivion, but because we had acquired the rights, we had to announce it because I think Interplay was a public company. I don't remember. Um I remember we had to announce it and we're thinking there, well you're gonna we're gonna piss off all the elder scrolls fans because we're announcing a Fallout game, we're probably gonna piss off the hardcore fallout fans because we didn't make the original and clearly will probably make a different kind of game. So I do remember, you know, there was a lot of concern with with all of our fans um and fans of Fallout at the time, and so I think it was pretty rewarding for us that that game found the audience and success that it that it did um is one of my favorite projects that I've ever ever worked on, and because it was so fresh for us and we we had a very clear like even before we had the rights like this is the game we're gonna make, like we're this is the kind of thing we're gonna do. And we had done more and then we were working on Oblivion and it was kind of a breath of fresh air to do it. And what's kind of remarkable is Fallout three comes out just, you know, 2.5 years after Oblivion, and we did all this DLC for Oblivion. So we were really, really kind of prolific in how our development, how it was going. So, um I just remember enjoying making that game so much because it was everything we were doing was new, </s><s>[INST] which, which after the world creation, was there some innovation? Like technically that was happening [/INST] the world creation, like it was, you know, obviously a different look, even though some of us, very few of us had worked in the terminator things, um the vat system, the skill system, and we love the original game so much. So you felt this responsibility to bring it back in a big way and reintroduce it in a way that, you know, as much as we could scratch the same itch when you, when you played the original game that had the same tone. Are </s><s>[INST] there some favorite things to you about that world? [/INST] I love again, I usually start with the beginning, I love the beginning, I love the character generation. If you go, if you played it a lot where you're developing it, it starts to feel really long, but the first time you play it or second, I just think it's awesome and this idea, it's a hard thing to say, okay, we want, we want you to feel like your character on the screen, even when you play like a Sky room, you don't know what you were doing before that, but Fallout three, you you were born in the vault and you raised in the vault and you lived in the vault, but you experience a part of that, so it's a very different when you step out, I don't think it really, and the visuals are the visuals, but the emotional moment of stepping out of the vault, you feel like you lived your whole life in the vault </s><s>[INST] and you feel like you have a sense of your past, [/INST] right? And I need to find my father. We </s><s>[INST] should, we should, isn't it possible to have that sense with, like, elder scrolls, like a life story, like, like childhood trauma and stuff. You [/INST] have to like, look, you do some of that stuff, but they go through menus, you know, pick your background, we're doing that in star field, Hey, pick your background. What were you doing before this moment? </s><s>[INST] Can you pick your traumas and stuff, you [/INST] go for that </s><s>[INST] and then also, but [/INST] a lot of it, you know, it's in your head, you're gonna, you're gonna do that, you're gonna pick this background and do these things and you're like, this is who I was and the intention with elder scrolls kind of make it up as much of a blank slate, you know, a little bit more of a blank slate game to who you are, which has a lot of positives and and fallout for us has been more of a, this is this, this was your life before, here's who you were go be who you want to be, but this is the background, it's a little more strict </s>

<s>[INST] or a great general intelligence, all those kinds of things. A huge amount of progress has been made and there it's fascinating to watch. So I'm on both minds as a person who's building them. I'm realizing how sort of quote unquote dumb they are, but also looking at human history and how poor we are predicting the progress of innovation and technology. It's obvious that we have to be humbled by our ability to predict, coupled with the fact that we keep uh to use terminology carefully here, we keep discriminating against the intelligence of artificial systems, the smarter they get, the more ways we find to dismiss their intelligence. Uh so this this has just been going on throughout where I it's almost as if we're threatened in the most primitive human way, uh animalistic way were threatened by the power of other creatures and we want to lessen dismiss them. So Consciousness is a really important one. But the one I think about a lot in terms of consciousness, the very engineering question is whether the display of consciousness is the same as the possession of consciousness. So if a robot tells you, they are conscious, if a robot looks like they're suffering when you torture them, if a robot is afraid of death and says they're afraid of death and are legitimately afraid, like for in terms of just uh everything we as humans used to determine the ability of somebody to be their own entity there. The one that loves one that fears, one that hopes one that can suffer if if a robot like in the dumbest of ways is able to display that we it changed, it starts changing things very quickly. Uh, I'm not sure what it is, but it does seem that there is a huge component to consciousness. That is a social creation. Like we together create our consciousness like we believe our common humanity together alone, We wouldn't be aware of our humanity and the law as it protects our freedoms. Seems to be a construct of the social construct. And when you add other creatures into it, it's not obvious to me that like you have to build, there will be a moment when you say this thing is not conscious. I think there's going to be a lot of fake it until you make it. And there will be a very gray area between fake and make that is going to force us to contend with with what it means to be an entity that deserves rights were all men are created equal, the men part might have to expand in ways that we are not yet anticipating. That's very interesting. I mean, my favorite, the fundamental thing I love about artificial intelligence does it gets smarter and smarter. It challenges to think of what is right, the questions of justice, questions of freedom. It basically challenges us two to understand our own mind to understand what like almost from an engineering first principles perspective to understand what it is that makes us human. That is at the core of all the rights that we talk about, all the documents. We right. So even if we don't give rights to artificial intelligence systems, we may be able to construct more fair legal systems to protect us humans. [/INST] Well, I mean, interesting ontological question between the performance of consciousness and and and actual consciousness to the extent that it's uh, that actual consciousnesses anything beyond some contingent reality. But you posed a number of interesting philosophical questions. And then there's also it strikes me that uh, that uh philosophers of religion would pose another set of questions as well when you deal with issues of uh, of structure versus soul. Body versus soul. And, and uh, it would be a, it will be a complicated mix and I suspect I'll be uh dust by the time those questions get, get worked out. </s><s>[INST] And uh, so yeah, the soul, the soul is a fun one. There's no soul, I'm not sure maybe you can correct me, but there's very few discussions of soul in our legal system. Right, [/INST] right, correct. So, uh, but there is a discussion about what constitutes a human being. And I mean, you gestured at the notion of the potential of the law widening the domain of so of human being. So, in in in in that sense, right. Uh, you know, people are very angry because they can't uh, get sort of pain and suffering damages if someone negligently kills a pet because a pet is not a human being. And people say, well, I love my pet, but the law sees uh, a pet as chattel as property like this, this water bottle. Uh, so the current legal definitions, um, trade on a definition of humanity that may not be worked out in any sophisticated way, but certainly, um, there's a there's a share broad and shared understanding of what, what it, what it means. Uh, so it probably doesn't, uh, explicitly containing the definition of something like soul. Uh, but it's it's more robust than, you know, a carbon based organism uh that there's something a little more distinct about what the law thinks a human being is. </s><s>[INST] So if we can dive into uh we've already been doing it, but if we can dive into more difficult territory. So 2020 had the tragic case of George Floyd. When you reflect on the protests, on the racial tensions over the death of George Floyd, how do you make sense of it all? What do you take away from these events? [/INST] The George Floyd moment occurred, occurred at at and historical um moment where people were uh in um quarantine for covid. Um and people uh have these cell phones to a degree greater than we've ever had them before. And this was a sort of the straw that broke the camel's back after a number of these sorts of cellphone videos surfaced. Mhm. People were fed up. Uh they there was unimpeachable uh evidence of um a form of mistreatment, whether it constitutes murder, manslaughter. There, the trial is going on now, and jurors will figure that out. But but there was widespread appreciation that a fellow human being was was mistreated that we were just talking about humanity, that there was uh not a sufficient recognition of this person's humanity, the common humanity </s>

<s>[INST] Well, let me ask you about human nature here on on both sides. So first, what have you learned about human nature from studying genocide? Why do humans commit genocide? What lessons? First of all, why is a difficult question. [/INST] But </s><s>[INST] what insights do you have into humans? That genocide is something that happens in the world. [/INST] That's a really big and difficult questions, right? And it's, um it has to be parsed, I think, into different kinds of questions, you know? Why does genocide happen? You know which the answer There is frequently political meaning. You know why Hitler ended up killing the Jews? Well, it had a lot to do with the political history Of Germany and wartime history of Germany. Right, um, in the 30s and you know, it's traceable to them, you know, like you mentioned it yourself. You can't imagine Hitler and In the mid 20s, turning into anything of the kind of dictator. He ended up being in the kind of murderer mass murderer he ended up being. So so. And the same thing goes, by the way, for Stalin and Soviet Union and Pol Pot. I mean, these are all essentially political movements where the polity state seized, you know, by, uh, ideological or, uh, you know, party single party movement, and then is moved in directions where where mass killing takes place and the other question separate that question out. The other question is, why do ordinary people participate? Because the fact of the matter is just ordering genocide is not enough. Just saying, you know, go get them is not enough. There have to be people who will cooperate and who will do their jobs. You know, both at the kind of meso level, the middle level of a bureaucracy, but also at the everyday level, people who have to pull the triggers and that kind of thing and, you know, force people into the gas chamber and grab people. You know, in Kiev in September 1941 and Bob and ER and pushed them, you know, towards the ravine, where the machine gunners are going to shoot them down, you know, and those are all different questions. The question of, um, you know, the especially the lower level people who actually do the killing is a question which I think we've been talking about, which is that within all of us, no. Is the capability of being murderers, mass murderers, I mean, to participate in mass murderers. I won't call them laws of social psychology, but the character of social psychology, you know, we will do it in most cases. I mean, one of the shocking things that I learned just a few years ago studying the Holocaust is that you could pull out. In other words, if if they order a police battalion to go shoot Jews, you didn't have to do it. You could pull out. They weren't gonna They never killed anybody. They never they never executed anybody. They never even punished people for saying No, I don't I'm not gonna do that. So people are doing it voluntarily. They may not want to do it. You know they give them booze to try to, you know, numb the pain of murder because they know there's there is pain. People experience pain when they murder people, but they don't pull out. And so it's the character of who we are in the society in groups and we're very, very influenced were highly influenced by the groups in which we operate. And you know who we talked to and and who our friends are within that group and who is the head of the group. And I mean, you see this evening I mean, you see it in any group, you know, whether it's in the academy, right at that Stanford or whether it's, you know, in a labor union or whether it's in a church group in in Tennessee or wherever. You know, people pay attention to each other, and they and they are unwilling frequently to say no, this is wrong. Even though all of you think it's right, it's wrong. I mean, you just don't do that usually, especially in societies that are authoritarian or totalitarian, right, because it's it's harder because there's a backup to it, right? There's the NK VD there. There's the Gestapo there. There are other people there, So you just you know, they may not be forcing you to do it, but but your social beings, plus this danger in the distance, you know you do it. </s><s>[INST] But then if you go up the hierarchy at the very top, there's a dictator presumably, you know, you go to like middle management and bureaucracy. Mhm. The higher you get up there, the more power you have to change the direction of the Titanic. [/INST] Right? </s><s>[INST] But nobody [/INST] seems to do it or what happens, and it does happen. It happens in the German army. I mean, it happens in the case of the Armenian genocide, where we know their governors. Who said No, I'm not. I'm not going to kill Armenians. What kind of business is this? They just removed. They removed. Then you find a replacement very easily. So you know, you do see people who stand up and again. It's not really predictable. Who will be, I would maintain. I mean, I haven't done the study of the of the Armenian governors who said No. I mean the Turkish governors who said no to the Armenian genocide, but you know um, there are people who do step aside every once in a while in the middle level and again, they're German generals who say, Wait a minute, What is this business in Poland when they start to to kill Jews or in Bella, Russia? And, you know, they're just pushed aside. You know, if they don't do their job, they pushed aside or they end up doing it and they usually do end up doing it. </s>

<s>[INST] how does the human interact with it [/INST] by tossing it? So it's an interactive musical instrument. It actually requires another partner. So the idea was that it's something like a dance um or just like something like a choreography in space. </s><s>[INST] Got it. And then speaking of which you also talked about sports and like ball sports, like playing soccer. So what you mentioned that so you you also can move with full speed and then if you push off the wall lightly you fly across, zoom, zoom across. So how does the physics of that work for? Can you still play soccer? For example, in space? [/INST] You can but one of the most intuitive things that we all learn as babies right is whenever you throw something, if I was going to toss something to you, I toss it up because I know that it has to compensate for the fact that that florian arc is going to draw it down, the you know, equations of motion are going to drop down. I would in space. I would just shoot something directly towards you. So like straight line of sight. And so that would be very different for any type of ball sports is to retrain your human mind to have that as your intuitive arc of motion or lack of arc </s><s>[INST] from your experience, from understanding how astronauts get adjusted to the stuff, How long does it take to adjust to the physics of this world, this other world? [/INST] So even after one or two parabolic flights, you can gain a certain facility with moving in that environment. I think most astronauts would say maybe several days on station or a week on station and their brain flips. It's amazing the plasticity of the human brain and how quickly they are able to adapt and so pretty quickly they become creatures of this new environment. </s><s>[INST] Okay, so that's cool. It's it's creating a little bit of an experience. What about if you go for more than 100 days for one year, for two years for three years, what challenges start to emerge in that case? [/INST] So scott kelly wrote this amazing book after he spent a year in space and he's a twin, it's absolutely fantastic that Nasa got to do a twin studies. Perfect. Um so he wrote a lot about his experience on the health side of what changed things like bone density, muscle atrophy eyesight changing because the shape of your eyeball changes, which changes your lens, which changes how you see if we're then thinking about the challenges between a year and three years, especially if we're doing that three year trip to mars for your friend who asked earlier then you have to think about nutrition and so how are you keeping all of these different needs for your body alive? How are you protecting astronauts against radiation either having some type of a shell on the spacecraft, which is expensive because it's heavy, you know, if it's something like lead a really effective radiation shell, it's going to be a lot of mass, or is there a pill that could be taken to try to make you um less uh in danger of some of the radiative radiation effects? A lot of this has not yet been answered. But radiation is really significant challenge for that three year journey. </s><s>[INST] And what are the negative effects of radiation on the human body out in space? [/INST] A higher likelihood to develop cancer at a younger age. Um, So you'd probably be able to get there and get back, but you'd find yourself um in the same way, if you were exposed to significant radiation on earth, you'd find significant bad health effects as you age. </s><s>[INST] What do you think about like decades? Do you think about decades or is this like an entire, [/INST] I think about centuries. </s><s>[INST] For [/INST] Myspace marks. But yeah, for decades, I think as soon as we get past the three year mark. Well, absolutely want somewhere between three years in a decade. We'll want artificial gravity and we know how to do that. Actually. The engineering questions still need to be tweaked for how we really implemented. But the science is there to know how we would spin habitats in orbit generate that force. So even if the entire habitats not spinning you at least have a treadmill part of the space station that is spinning and you can spend some fraction of your day in a near to one G. Environment and keep your body healthy </s><s>[INST] literally from just spinning [/INST] from spinning. Yes centripetal force. So you generate this force. If you ever been in those um carnival rides the gravity Iran's that spin you up around the side. That's the concept. And this is actually one of the reasons why we are spinning out a new company from my M. I. </s><s>[INST] T. Lab spinning [/INST] out accidental but well well noted space planets as </s><s>[INST] possible. [/INST] Um But yeah we're spinning out a new company to look at next generation space architecture and how do we actually scale humanity's access to space? And one of the areas that we want to look at is artificial gravity. </s><s>[INST] Is there a name yet, [/INST] yep there's a name, we are brand new, we are just exiting stealth mode. So your podcast listeners will literally be among some of the first to hear about it. It's called Aurilia Institute or alia is an old english word for Chrysalis and the idea with this is that we humanity collectively are at this next stage of our metamorphosis like a Chrysalis into a space faring species and so we felt that this was a good time unnecessary time to think about next generation space architecture but also Starfleet Academy, if you know that reference from star trek. </s>

<s>[INST] But I think that's part of the way life works on earth, maybe human civilization works is it seems like we want ourselves to be quite similar and then within that, you know what everybody's about the same, relatively AQ intelligence, problem solving capabilities, even physical characteristics. But then we'll find some aspect of that that's different and that that seems to be like, I mean it's it's really dark to say, but it seems to be the, not even a bug, but like a feature of the early development of human civilization. You pick the other, your tribe versus the other tribe and you wore. It's a kind of evolution evolution in the space of of memes, a space of ideas I think and you wore with each other. So we're very good at finding the other even when the characteristics are really the same. And I don't know what that I mean, I'm sure so many of these things echo in the biological world. [/INST] Yeah. There's a fun experiment that I did. My son actually came up with this. We we did um a biology unit together. We used to home school and so we did this a couple of years ago, we did this thing where I imagine you got the slime mold and it grows on a on a on a Petri dish of a guard and it sort of spreads out and and it's it's it's it's a single cell, you know, produce, but it's like this giant thing. And so you put down a piece of oat and it wants to go get the oat and that sort of grows towards the oh, so what you do is you take a razor blade and you just you just separate the piece of the whole culture that's growing towards the oh you just kind of separated. And so now think about think about the interesting decision making calculus for that little piece. I can I can go get the oat and therefore I won't have to share those nutrients with this giant mass over there. So the so the nutrients per unit volume is going to be amazing. So I should go eat the oat. But if I first rejoin because once you cut it has the ability to join back up. If I first rejoin then that whole calculus becomes impossible because there is no more me anymore. There's just we and then and then we will go eat this thing. Right? So so that's interesting you know this this you can imagine a kind of game theory where the number of agents isn't fixed and that it's not just cooperate or defect but it's actually merge and and whatever. Right? </s><s>[INST] So that kind of that that competition, how does it do that decision making? [/INST] Yeah. So so so that. Right. So so it's it's really interesting and so and so empirically what we found is that it it tends to merge first, it tends to merge first and then the whole thing goes. But but it's really interesting that that that that that calculates what do we even have. I mean I'm not an expert and they cannot game theory and all that but maybe there's a Calgary made some sort of hyperbolic discounting or something. But but maybe you know this idea that the the actions you take not only change your payoff but they change who or what you are and that you may not you you could take an action after which you don't exist anymore or you are radically changed or you are merged with somebody else. Like that's you know as far as I know that's a whole you know we're still missing a formalism for even knowing how to how to model any of that </s><s>[INST] D. C. Evolution by the way is a process that applies here on earth. Or is it somewhere did evolution come from? Yeah. So this thing um that from the very origin of life that took us to today. What the heck is that? [/INST] I think evolution is inevitable in the sense that if you combine and and basically I think one of the most useful things that was done in early computing I guess in the 60s it started was was evolutionary computation and just showing how how simple it is that if you have if you have imperfect heredity and competition together those two things or three things. Right? So heredity imperfect heredity and competition or selection those three things and that's it now now now you're you're off to the races right? And so that can be it's not just on earth because it can be done in the computer can be done in chemical systems that can be done in you know, lee Smolin says it's it works in on on cosmic scales. So I think that uh that kind of thing is incredibly um pervasive and and and and general it's a general feature of life. It's it's interesting to think about, you know, the standard uh standard thought about this is that it's it's blind right, meaning that the intelligence of the process is zero is stumbling around. And I think that back in the day when the options with the options were it's dumb like machines or it's smart like humans and of course the scientists went in this direction because nobody wanted creationism and they said okay, it's gotta be like completely blind. I'm not actually sure right? Because because I I think that um I think that everything is a continuum and I I think that it doesn't have to be smart with foresight like us, but it doesn't have to be completely blind either. I think there may be aspects of it and in particular this kind of multi scale competency might give it a little bit of look ahead maybe or a little bit of problem solving sort of baked in, but but but that's gonna be completely different in different in different systems. I do think I do think it's general, I don't think it's just on Earth. I think it's a very fundamental thing, it </s>

<s>[INST] that's going to come out and the problem, like statistically speaking, it's going to come out as a strong relationship and a person in the grocery store is going to wash out. It's not an important physical relationship. Okay, I mean this is brilliant. Uh what uh how difficult is it to make work? So you said one, there's a mathematical component that was just kind of talked about and then there's the user experience component. So how difficult is it to go? Just like you built the video game Alien attack from 0-2 completion? What's involved? How difficult is [/INST] it? So I'm going to answer that question in terms of building the product but then I'm also going to acknowledge that just having an app doesn't make it useful because that's actually may be the easy part if you know what I mean, There's like all of this stuff about rollout adoption and awareness, but let's focus on the app part first. So that's again, why is that? The team is incredible. So we have a bunch, a bunch of people who um let's just say that the technology that we use to make it is not the standard way you make an app. If you think about a standard IOS app or android app, those are user interface that contacts the web server and send some information back and forth. We're doing some stuff that has to hook into the operating system of saying, let's go use Bluetooth for something it wasn't really meant for. Right? So there's that part and by the way, </s><s>[INST] what is the app called? [/INST] It's called No vid Covid within that. </s><s>[INST] Very nice. So you have to hook into Bluetooth, you're saying you have to do that um beyond the permissions that are like at the very surface level uh provided on the phone. [/INST] Well I don't want to call them permissions. I just want to say that's not what you usually do with Bluetooth usually with bluetooth, you say, do I have headphones nearby? Okay. I'm done. You don't go and say do I have headphones nearby or do I have another phone nearby, which is doing something and I keep asking that same, asking the question, right. So this is actually not easy. And I mean there were some parts of it which actually a lot of people had tried unsuccessfully. Um actually it's, it's known that for example, the UK was trying to do something uh similar. And the problem they ran into was when you program things on IOS, uh, IOS is very good at making it hard to do things in the background. And so there was quite a lot of effort required to go and make this thing work. </s><s>[INST] So the whole point, this thing would run in the background and I was, I mean most android probably as well. Right. But yeah, Iowa certainly makes it difficult for something to run the background, especially when it's eating up your battery. Right? [/INST] Uh Well, we wanted to make sure we didn't eat up the battery. So so that that one we can, we actually are very proud of the fact that RS uses very little battery. Uh actually, even if compared to Apple's own system. </s><s>[INST] So beautiful. So what else is required to make this thing work? [/INST] Right. So the key was that you had to do significant amount of work on the actual mobile app development, which fortunately the team that we brought was this kind of general thinkers where we would dig in deep into the operating system documentation and the api libraries. So we got that working. But there's another angle which is, you also need the service to be able to compute fast enough, which is tying back to this old school computer programming competitions and math olympics, in fact, our team that was working on the algorithm and back inside uh included several people who had been in these competitions from before, which I happen to know because I do coach the team for the math. And so we were able to bring people in to build servers, server infrastructure in C plus plus actually so that we could support significant numbers of people without needing tons of servers. </s><s>[INST] Is there some distributed algorithms working here or you basically have to keep in the same place? The entire graph as it builds? Because especially the more and more people use it, the bigger the bigger the graph gets. I mean, this is very difficult uh scaling problem. Right. [/INST] So that's actually buy this computer algorithm competition stuff was handy. It's because there are only about 7-8 gig of people in the world. Yeah, that's not that many. So if you can make your algorithms linear time or almost linear time, a computer operates and gigahertz, I only need to do one run 11 recalculation every hour in terms of telling people how far away these dangers are. So I suddenly have 3600 seconds and my CPU cores are running in gigahertz. And at most there giggle people. </s><s>[INST] Well, you're skipping over the fact that there's unscrew aired potential connections between people. So how do you get around the fact that uh you know that we, you know, the potential set of relationship any one of us could have eight billion. So it's a billion times uh squared. That's does potential amount of data you have to be storing and computing over and constantly updating. [/INST] So the way we dealt with that is we actually expect that the typical network is very sparse. The fact that the technical term sparse would mean that average degree or the average number of connections that a person has, it's going to be at most like 100 strong connections that you care about. If you if you think of it almost in terms of the heavy hitters actually in most people's lives, 100. If we just kept track of their top 100 interactions, that's probably most of the signal. Mhm </s>

<s>[INST] Well that's a very harsh your your I think that's a harsh view of humanity. There's a lot of bad people whether incompetent or just malevolent in this world. Yes, but it feels like the more malevolent. So the more damage you do to the world, the more resistance you have in your own human, like, [/INST] but Hollande explained with malevolence or stupidity, what can be explained by just people acting on their incentives? So what happens in stanford is not that somebody is evil, It's just that they do what they're being paid for? No, it's </s><s>[INST] not evil. That's I I tend to. So no, I said I see that as malevolence. I see uh as I even like being a good german as I told you, offline is some it's not it's not absolute malevolence, but it's a small amount, it's cowardice. I mean when you see there's something wrong with the world, um it's either incompetence, you're not able to see it or it's cowardice. The you're not able to stand up, not not necessarily in a big way, but in a small way. So I do think that is a bit of malevolence. I'm not sure the example you're [/INST] describing is the question is what is it that you are aiming for? And if you don't believe in the future, if you, for instance, think that the dollar is going to crash by what you try to save dollars. If you don't think that humanity will be around in 100 years from now because global warming will wipe out civilization, Why would you need to act as if it were all right. So the question is, is there an overarching aesthetics that is projecting you and the world into the future, which I think is the basic idea of religion that you understand the interactions that we have with each other as some kind of civilization level agent that is projecting itself into the future. If you if you don't have that shared purpose, Right, what is there to be ethical for? So, I think when we talk about ethics and a I we need to go beyond the insane bias discussions and so on where people are just measuring the distance between a statistic to their preferred um, world model. But </s><s>[INST] the optimism where I was a little confused by the previous things just to clarify, uh, it's there is a kind of underlying morality too, having an optimism that human civilization will persist for longer than 100 years like that. Like I think a lot of people believe that it's a good thing for us to keep living [/INST] Of course, and thriving reality itself is not an end to itself. It's instrumental to people living in 100 years from now, Right? Or 500 years from now. Right. So, it's only justifiable if you actually think that it will lead to people or increase the probability of people being all right. And in that time frame. And a lot of people don't actually believe that at least not actively </s><s>[INST] but I believe what Exactly. So, [/INST] uh most people don't believe that they can afford to act on such a model, basically what happens in the US as I think that the health care system is for a lot of people no longer sustainable. Which means that if they need the help of the health care system, they are often not able to afford it. And when they cannot help it, they are often going bankrupt. It's I think the leading course cause of personal bankruptcy in the US is the health care system and that would not be necessary. It's not because people are consuming more and more medical services and are achieving a much much longer life as a result. That's not actually the story that is happening because you can compare to other countries and life expectancy in the U. S. Is currently not increasing and it's not as high as in all the other industrialized countries. So some industrialized countries are doing better is much cheaper. Health care system. And uh what you can see is, for instance, administrative bloat. The health care system has maybe to some degree deliberately set up is job placement program to allow people to continue living in middle class existence despite not having a useful uh use case in productivity. So they are being paid to push paper around and the number of administrators in the health care system has been increasing much faster than the number of practitioners. And this is something that you have to pay for right? And also the revenues that are being generated in the health care system are relatively large and somebody has to pay for them. And the result, why they are so large is because market mechanisms are not working? The FDA is largely not protecting people from malpractice of health care providers. The FDA is protecting healthcare providers from competition. So this is a thing that it has to do with values and this is not because people are malicious on all levels. It's because they are not incentivized to act on a greater whole on this idea that you treat somebody who comes to you as a patient like you would treat a family member. Yeah, but yeah, but </s><s>[INST] we're trying I mean, you're highlighting a lot of the flaws of the different institutions and systems were operating under. But I think there's a continued throughout history mechanism design uh of trying to design incentives in such a way that these systems behave better and better and better. I mean, it's a very difficult thing to operate a society of hundreds of millions of people effectively with. [/INST] Do we live in a society that is ever correcting uh observed that our models of what we are doing our predictive of the future and then they are not improved them. Our laws of adjudicated with classes that you put into every law, what is meant to be achieved by that law and the law will be automatically repealed if it's not achieving that right. If you are optimizing your own loss. If you're writing your own source code, you probably make an estimate of what is the thing that's currently wrong in my life, What is it that I should change about my own policies? What is the expected outcome? And if that outcome doesn't manifest, uh, I will change the policy back right or will change it to something different. Are we doing this on a societal level? </s>

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

<s>[INST] and by dangerous, you mean it challenges the people with power, who don't, who want to maintain that power in times of stagnation, when there's not much growth, innovation, creativity, all that kind of stuff. [/INST] Right? And we know that if nothing new is created, people uh have promises that they've made about what will be paid to whom, what debt structure is. The only possibility if stagnation lasts for long enough is really some kind of great conflict, great war because people have to take from others to make good on their own promises. So we know that by denying any sort of grand ideation, we are accepting that there will be some kind of great catastrophe. And so we have to understand that philosophy is the most important uh when we've seen too much stagnation for too long. It is also very dangerous. And it's dangerous for the people who are doing it. And it's dangerous for the people who believe it. But it's kind of our only way out ever. </s><s>[INST] And again by philosophy, you mean the bigger is not academic philosophy or this kind of uh games played in the in the space of just like moral philosophy and all those metaphysics, all that kind of stuff. You mean just thinking deeply about this world thinking from first Principles. I think your twitter line involves something about [/INST] trying to piece everything together in First Principles. </s><s>[INST] So that's that's fundamentally what being philosophical about this world is and that's where the people who are thinking deeply about this world are the ones who are feeding, who are the catalysts of this growth in society and so on. [/INST] Yeah, I I mean I also think that the real implication of moral philosophy uh can be something that most would consider like a real political uh implications. So I think all philosophy really ties together because there has to be some sort of grand structure to all thought and how it relates. </s><s>[INST] Do you think this growth and innovation and improvement can lest forever? We've seen some incredible, you know, the thing that humans have been able to accomplish over the past several 100 years. It's just I mean, all inspiring and every moment in that, in that history it almost seemed like no more could be done like we've we've solved all the problems that are to be solved. I mean there's just historically there's all these kind of ridiculous like Bill Gates style quotes or like it's obvious that we've this new cool thing is not going to take off and yet it does. And so there's there's a feeling of the same kind of pattern that we're seeing moore's law, There is constant growth in different technologies in the modern day era in any kind of automation for the past 100 years, do you think it's possible that will keep growing this way if we give power to the philosophers of our society? [/INST] I think the only way that we can keep growing this way is if we give power to real thinkers, um and there's no guarantee that that will work, but we sort of don't have any other choice and I think you're entirely right that this period of both understanding the universe uh at a rate which has never been seen before and invention and creativity, that these past 100 years have been sort of uncharacteristic uh for the level of growth that we've seen in all of history, we've never seen anything like this and I think a lot of our uh a lot of our promises rest on this sort of thing, continuing, I think that's very that's very dangerous, but the one thing that can get us out of this is philosophy and being ready to radically restructure all of our notions about what should be what is, I think that's very important. </s><s>[INST] So you think deeply about this world, you are clearly this embodiment of a think of a philosopher, Your dad is also one such guy, ERic Weinstein, do you just, do you have big disagreements with him on this topic in particular? I think now people should know, he also happens to be in the room, but the mics can pick him up so he can heckle, it doesn't even matter. Uh but do you have disagreements with him on this point? Let me um try to summarize his argument that we were actually based a lot of our american society on the belief that things will keep growing. And yet it seems that however you break it apart maybe from an economics perspective that they're not growing currently and so that's where a lot of our troubles are at. Do you have the same sense that thinks there's a stagnation period that we're living through over the past couple of decades? [/INST] I think stagnation modern stagnation is completely undeniable, particularly scientifically. And I think there have been a few fields where tremendous progress has been made very recently. I think my dad might feel that uh there is sort of an inevitability to the ending of this period and I'm not so certain so certain that the fall of this great time is completely inevitable because I don't know what thoughts were capable of producing what we're able to reconsider. I think we really have to be open to the possibility that uh all of our standard frameworks where you know, like he will talk about embedded growth obligations, if we continue within the same framework, then we're very susceptible to the dangers of whatever these embedded growth obligations are. I think if we break the frameworks we have no reason to believe that the problems we're experiencing with our current frameworks will will follow us. And I think that's the importance of radical thought is we don't know what the solution is, but if there is a solution, it will be born from some very fundamental thinking. And so I've had great hope. </s>

<s>[INST] My dad was like, yeah, say goodbye to him, you know. [/INST] I guess he does, gangster. I got it. Tough guy. He did some gangster shit that day. But on my end, I was being isolated, basically, as COVID is, everybody's slowing down. No more classes, no more excuses to go out there and drink and no more socializing. So social drinking turned into alone drinking more and more and more. I bought a bottle of gin because I was down in Mexico taking care of my dad, and they closed down beer production in Mexico. So beer went away, and beer was a way I kind of managed it. It's not hard alcohol, it's just beer. But that went away, so it was just hard alcohol. That was what's available down there. One night alone at the house, my dad's house, I drank a bottle of gin, a whole bottle of wine, and I almost died. And after that, some people started noticing that I was isolating more and more, and it was kind of eating away at me. I was in a relationship at that point when I started seeing everything just kind of fall apart around me. And I drank half of a glass of wine, and it made me sick internally in my mind. And my kid said to me, and I don't know, nobody coached her, nobody said anything to her. She's a pretty intuitive kid. She said, I don't drink anymore, dad. I thought of nowhere in the middle of the night. And I stopped. I stopped that night. I remember waking up at three in the morning and taking a cooler that I had and just dumping all the beers in it and chucking them in the garbage, and with a knife poking each of them to not be tempted to go pack for them. And then the second day, I went around and started finding the hides that I had because I had some hides. And then I went somewhere and locked myself in for two weeks. I had the withdrawals, the clearest nightmares that I'd ever had in my life for two, three weeks. I went somewhere. I don't want to keep them private, but I went somewhere where they offered a place for me. And when I asked them about it, it's a community. I gave them some money for their school as a donation. I gave them like a few thousand dollars. I said, yeah, never come. You can go through this process here. Cool as fuck people. The first thing they did when I got there is they stood me up in front of everybody to thank me for the donation and then told everybody that I was an alcoholic. And if anybody saw me drinking, I was to be kicked out of there immediately. And I felt horrible. So that was where I started. Is that temptation still there? There was a moment when it was. And some therapy circle. There's a rodeo clown friend of mine who his body's, his spine is basically fused together, you know, type of guy. We've been friends and enemies and friends again, you know, in during the heart therapy circle sessions. Oh, so like there's an intimacy there. Yeah. He didn't know anything about me. One time when we were telling our story, he stood up and told his story and then he heard mine and then he was pissed off at me and didn't want to talk to me for a while. And then later he told me that it was because he saw what I did with my experience and how much of a difference that he's perceived that I was making with it. And he felt jealous that he can do the same with his experience because he was just a broken ex rodeo clown. He told me when I was going through the process, like, Hey, you're an internet celebrity person. You know, you're, you're known. Are you worried about people finding out that you're, that you're recovering drunk? And I said, yeah, it's fucking scary as shit. If people find out that I am going through this process, it's scary that, you know, the critique, you know, I already get a lot of shit for being a ex police officer in Mexico and all that, uh, all the negativity that comes from that. And he said, don't be, you know, that you can't pickpocket a naked man. So just get naked. And what does that mean? Write about it. Post it online. You never know somebody, somebody out there might get inspired to do their own kind of process. So I started posting cowardly in a way because I wanted to make other people keep me on the path, you know, but in other ways, you know, uh, desperation. You know, I w I don't want to drink anymore. I don't want to go back to that. I'm not a bath, which I know leads directly to a bad death. I'm not afraid of death. I just want a good one. I don't want a bad one. I think that was going to lead me to a bad death. As our writing about in sharing it online, you know, through my, uh, fever dreams post. And just being humorous about it online and Getting a lot of hate on one side, having a few people and companies that I work with kind of step back and seeing this guy has some issues to having other people kind of make fun of </s><s>[INST] or make light of that weakness portrayed. Also getting hate, getting criticism, because here you are, a counter narcotics police officer, there's no, that's a drinking problem. [/INST] So is that like supposed to be what like flaws revealed? Weakness or a perception of alpha in the U.S. I guess that some people have, you know. You were supposed to be strong and here you are. I mean, I'm not Jocko Willnick, I'm not David Goggins, you know, I'll wake up at 10 in the morning sometimes and I'll have cornflakes with my eight year old, you know. I like days off. I used to wake up at 3 30 in the morning every day to review what happened during the night and then go off for a jog and then the gym and just be ready to be able to murder somebody with my hands if I had to. But that is, I couldn't maintain that during the whole process of getting out of it. Now leaving alcohol, I remember just being honest with it and just seeing the two sides of it, you know. Joe told me, never read the comments section, right? Which is a beautiful, it's a beautiful piece of advice. But they get you sometimes. When you talk about some of these things openly and some of the comments were positive and I've been seeing people comment, sending me messages and meeting people on the road that are five months in, 10 months. Some people that have been on that wagon for way longer than I have. And there's, it's what's cool when you meet people that are superhuman or perform and take an extreme ownership of things and are just amazing people that are thriving out there, inspirational. I see some of these people and I'm like, holy shit, I need to figure out how to get to some semblance of that. But I'm not that, you know. I've been through the wringer. I've fucked up a shit ton of times. My nose is an example of that, a few missing teeth. But in a way, I think all of that is part of the process that not a lot of people wanna talk about, you know. Independently of the experience I got down there and some of the things that I show and talk about and some of the advocacy I do related to women like her that are, you know, trying to look for a better life and trying to find their missing kids, training people to not get into those situations. But also showcasing the fact that people that go through some of these processes have a journey to go through, you know. I just came into your studio with a duffel bag. Straight from the airport and I'm gonna leave early tomorrow morning to somewhere else. I've been on the road for almost, I think, five years nonstop. I go back to a specific place every week to see my kid for two, three days. And then I'm back out, you know, some people are like, are you running? Like, are you worried, is this afraid about them? No. But I am, you know, on this weird path, I guess, trying to look for something that I think I've been missing. As far as my afterlife of a sort, you know, coming out of that gap. </s>

<s>[INST] So, some fortune, Some misfortune affects the progress of science, especially with ideas. As uh to me at least if I put myself back in those days as radical as general relativity is first. Can you describe if it's okay briefly what general relativity is? And yeah, could you just take a moment of Yeah. Put yourself in those shoes in the back and academic researchers, scientists at that time. And what is this theory? What is it trying to describe [/INST] about our world? It's trying to answer the thing that left Isaac Newton puzzled. Isaac Newton says, gravity magically goes from one place to another. He doesn't believe it. By the way, he knows that's not right. But the mathematics is so good that you have to say, well, I'll throw my qualms away because I'll use it. That's all We used to get a man from the earth to the moon. Was that mathematics? So I'm one of those scientists. I've seen this. And if I thought deeply about it, maybe I know that Newton himself wasn't comfortable. And so the first thing I would hope that I would feel is gee there's this young kid out there who has an idea to fill in this hole that was lee left with us by the Sir Isaac Newton. That would I hoped would be my reaction. I have a suspicion. I'm I'm kind of a mathematical creature. Uh I was four years old when I first decided that science was what I wanted to do with my life. And so if my personality back then was like, it is now, uh I think it's probably likely I would want to want to have studied his mathematics. What was a piece of mathematics that he was using to make this prediction? Because he didn't actually create that mathematics, that mathematics was created a roughly 50 years before he lived. He is the person who harnessed it in order to make a prediction. In fact, he had to be taught this mathematics by a friend. Mhm So this is in our book. So putting myself in that time, I would want to like that, I think I would feel excitement, I would want to know what the mathematics is and then I would want to do the calculations myself. Because one thing that physics is all about is that you don't have to take anybody's word for anything, you can do it yourself. </s><s>[INST] It does seem that mathematics is a little bit more tolerant of radical ideas, or mathematicians are people who find beauty in mathematics. Why all the white questions have no good answer. Let me ask, why do you think Einstein never got the Nobel prize for general relativity? He got it for the photo [/INST] electric effect. That is correct. Well, first of all, that's something that is misunderstood about the Nobel prize in physics. The Nobel prize in physics is never given for purely giving for purely proposing an idea, it is always given for proposing an idea that has observational support. So he could not get the Nobel prize for either special relativity nor Jenna relativity because the provision that Alfred Nobel left for the award prevent that, but </s><s>[INST] after it's been validated, can you not get it then or No? [/INST] Yes, but remember the validation doesn't really come into the 1920s, </s><s>[INST] but that's why they invented the second Nobel prize. I mean, uh merry chri you can get in second Nobel prize for one of the greatest so [/INST] theories in physics. So let me, let's be clear on this. The theory of general relativity had its critics Even up until the 50s. So if you had if we had if the committee had wanted to give the prize for general relativity, There were vociferous critics of general relativity up until the 50's Einstein died in 1955. </s><s>[INST] What lessons do you draw from from the story you tell in the book, from general activity from the radical nature of the theory to looking at the future strength theory? [/INST] Well, I think that the string theorists are probably going to retrace his path, but it's going to be far longer and more tortuous in my opinion, String theory is such a broad and deep development that in my opinion when it becomes acceptable, it's going to be because of a confluence of observation is not gonna be a single observation and I have to tell you that. So, I gave a seminar here yesterday, my team and it's, it's on an idea I have about how string theory can leave signatures in the cosmic microwave background, which is an astrophysical structure. And so if those kinds of observations are borne out, uh if perhaps uh other things related to the idea of supersymmetry going out, those are gonna be the first powerful observation lee based pieces of evidence that will begin to do What the Eddington Expedition did in 1919. But who, that may take several decades, </s><s>[INST] do you think there will be Nobel prize is given for string theory? Because because [/INST] I think because it'll be it'll be I think it will exceed normal human lifetimes. But there are other prizes that are given. I mean there is something called the breakthrough prize. Um there's a Russian immigrate, Russian american immigrant named Yuri Milner, I believe his name started this wonderful prize called the breakthrough prize. It's three times as much money as the Nobel prize and he gets award every year. And so something like one of those prizes is likely to be garnered at some point far earlier than a Nobel award, </s><s>[INST] jumping around a few topics while you were at caltech, you've gotten to interact, I believe with Richard Feynman, I have to ask. Yes, Richard fine [/INST] indeed. </s><s>[INST] Do you have any stories that then on your memory of that? I [/INST] have a fair number of stories, but I'm not prepared to tell them. They're not all politically correct me say. </s>

<s>[INST] I love it. Uh is there uh let's put on your wise visionary hat and ask when you look too young folks, is there advice? You can give the young people today, whether in high school or college about career, [/INST] about </s><s>[INST] life? You've lived quite a non linear and fascinating life yourself. Is there advice you can give either on career or more generally in life? [/INST] Well, I I would say what, what people often here is that um you know, we're not actually here for that long a period of time. Um, and so to the, and the world is on fire and whether humanity survives is not clear. And whether, how many species are we gonna kill before we figure out not to do that anymore. So I would advise you to really try to um develop a combination of what do you need in terms of income for your own survival. But what does the world need in terms of um, help to make the world better? And you know, Howard thurman, who he talked about, who ran the good friday experiment. The Minister there, he said he's got a famous quote attributed to him, he says, um and this is exactly it to young people. He said, um you know, there's nothing particular that you should do but find what makes you come alive because what the world needs is people that have come alive and are passionate. Um, so I would say that beware of this uh trap that you need vast resources that you need. All this stuff. You know, uh you know, I keep thinking of the super wealthy people in first class on the titanic, you know, as the titanic is sinking. You know, their their money is not going to help them, that the earth is like titanic, you know, we're sinking, we're destroying the planet, destroying the environment. So it's um you need a certain amount of money to be comfortable uh to not be at that edge of survival because once you're at that edge of survival, it's hard to think about anything else. But I'd say to young people, um mhm. To the extent that you're able to do this, and again, student debt and all this kind of stuff is a big problem there too, but really just try to um find this combination of what the world needs and what you need. The the other thing to say to young people is um Life is a lot shorter than you think that. Um and a 20-year plan is not really that long. So if it takes you 20 years to get in a position to do what you want to do um go for it, you know, have long term plans. The other part that was so important for me to um Keep doing what I've been doing basically. Now, it's 49 years that I've sort of been devoting my life on psychedelics since I was 18 um when I started, I didn't think I would ever work, I just thought this is the only idea I have in this crazy world, you know, this is what I want to work on, luckily I had support from my family that took care of my survival needs. So I could do that. But I realized that if my happiness was dependent upon accomplishments, that I might never be happy that I was able to reframe happiness in terms of effort, you know, so if I'm trying hard to get stuff um to be better, whether it's better or not, I can be happy at the end of each day. I tried and so I think you try to separate out the goals that you have and your happiness to whether you're trying hard. Um The other thing I would say is that um everybody has this humanity within them, so be very careful about dividing the world into us and them. Um you know, and try to, so so one of the things that I've done um that has um taking a long time because you know, I feel like um you know, drugs are illegal, I always felt like, you know, the police were the predator and I'm the prey. Yes, you know, but now we're working with the police and the police have tremendous trauma from the work that they do. We have one police officer who is now going, he's a full time police officer, he's also a psychotherapist and he's going through our training program to learn how to give M. D. M. A therapy to other police officers and I met his police chief a couple times, He got permission from his police chief to go to the second part of our training program, which is where we give M. D. M. A. Two therapists who volunteered as a patient. So we have just a couple weeks ago dosed the police with M. D. M. A. And so I think this idea of those people that are on the other side try to see through that to their humanity to what their pains and suffering, what their struggles are. To the extent that you can and that I think and build long term relationships. You never know what's gonna Um come around 20 years from now. So you you help some people try to keep these relationships going 20 years from now something could could come and and also um be persistent, you know. Yeah, I think that's that's been the key to success. I mean once the FDA or D. A figured out we're not going anywhere, they're going to have to deal with us. Then we started getting some progress mix </s><s>[INST] of patients and stubbornness, gets things done. Is there something you've figured out [/INST] through your journey </s>

<s>[INST] to others. I [/INST] think those are fairly general. </s><s>[INST] How do you pick the thing, [/INST] you just have like a deep interest in something uh or like try to like find the art max over, Like the things that you're interested in </s><s>[INST] art max at that moment and stick with it, how do you not get distracted and switch to another thing [/INST] you can, if you like um </s><s>[INST] if you do an arg max repeatedly every week, [/INST] doesn't converge, </s><s>[INST] doesn't you [/INST] can like low pass filter yourself in terms of like what has consistently been true for you? Um But yeah, I definitely see how it can be hard, but I would say like you're going to work the hardest on the thing that you care about the most so low pass filter yourself and really introspect in your past, what are the things that give you energy and what are the things that take energy away from you? Concrete examples and usually from those concrete examples, sometimes parents can emerge, I like I like it when things look like this one of these positions, so </s><s>[INST] that's not necessarily the field, but the kind of stuff you're doing in a particular field. So for you, it seems like you were energized by implementing stuff, building actual things. [/INST] Yeah. Being low level learning, and then also uh communicating so that others can go through the same realizations and shortening that gap um because I usually have to do way too much work to understand the thing and then I'm like, okay, this is actually like okay, I think I get it and like why was it so much </s><s>[INST] work, [/INST] it should have been much less work and that gives me a lot of frustration and that's why I sometimes go teach. </s><s>[INST] So aside from the teaching you're doing now, putting out videos aside from a potential uh Godfather part two, uh would the A. G. I. At Tesla and beyond. What does the future of apathy hold? Have you figured that out yet or? No? I mean uh as you see through the fog of war, that is all of our future. Um do you, do you start seeing silhouettes of what that possible future could look like? [/INST] The consistent thing I've been always interested in for me at least is is A. I. And um that's probably what I'm spending my rest of my life on because I just care about it a lot and I actually care about like many other problems as well, like say aging, which I basically view as disease and I care about that as well. But I don't think it's a good idea to go after it specifically. I don't actually think that humans will be able to come up with the answer. I think the correct thing to do is to ignore those problems and you solve AI and then use that to solve everything else. And I think there's a chance that this will work. I think it's a very high chance and uh that's kind of like the the way I'm betting at </s><s>[INST] least. So when you think about ai are you interested in all kinds of applications, all kinds of domains and any domain you focus on will allow you to get insights to. The big problem with a guy [/INST] for me is the ultimate mental problem. I don't want to work on any one specific problem. There's too many problems. So how can you work on all problems simultaneously? You solve the meta problem, which to me is just intelligence and how do you automated </s><s>[INST] is their cool small projects like archive sanity and and so on that you're thinking about the the world, the ml world can anticipate. [/INST] There's someone always like some fun side projects. Archive sanity is one basically like there's way too many archive papers. How can I organize it and recommend papers and so on. I transcribed all of your podcasts. </s><s>[INST] What did you learn from that experience? Uh from transcribing the process of like you like consuming audio books and podcasts and so on. And here's a process that achieves um closer to human level performance and annotation. [/INST] Yeah, well I definitely was like surprised that transcription with opening eyes, Whisper was working so well compared to what I'm familiar with from Siri and like a few other systems, I guess it works so well. And uh that's what gave me some energy to like try it out. And I thought it could be fun to random podcasts. It's kind of not obvious to me why whisper is so much better compared to anything else because I feel like there should be a lot of incentive for a lot of companies to produce transcription systems and that they've done so over a long time. Whisper is not a super exotic model. It's a transformer, It takes mel spectrograms and you know, just outputs tokens of texts, not crazy uh model and everything has been around for a long time. I'm not 100% sure why. </s><s>[INST] It's not obvious to me either. It makes me feel like I'm missing something. [/INST] Something. Yeah, </s>

<s>[INST] And you're very nice about Muslims in the soviet union. Uh there's an article that there was a pay walls that couldn't read it and I really want to read. It is shared with you in Moscow and the mosque or something like that. Um by the way, just another tangent and the tangent. Uh so I bought all your books. I [/INST] love them very much. </s><s>[INST] One of the reasons I bought them and read many parts is because they're easy to buy. Unlike articles, every single website has a page. So it's it's very, very frustrating to read brilliant scholars. So she's yourself. Um I wish there was one fee I could pay everywhere. I don't care what that fee is because it allows me to read [/INST] some of your brilliant writing. You know, I think moving toward more kind of open source for many stuff I think is what a lot of generals are thinking about now. And I think it's definitely for the kind of democratization of knowledge and scholarship. That's definitely an important thing that we should all think about. And I think um you know, we need to exert pressure on these publishers to do that. So I appreciate this is what I'm doing here. Yeah, I appreciate it. So, </s><s>[INST] uh your thought was Afghanistan is not it's not going to be the center the source [/INST] exactly where it's not the center of this and invaded that country isn't gonna fix is going to fix the, You know, toxic maelstrom of politics that produced 9 11, right? I'm just thinking of some personalities to think about going back to the touching story job and with just observing, you know, real Muslims doing, doing things and then asking questions about it and try to understand through their eyes what tradition means to them. And then, you know, you have a we had we had a very narrow conversation about what Islam is that you know, generated immediately exploded in, you know, on the day of 9-11, right? Um and then of course um the antipathy toward Islam and Muslims, it was informed by by racism informed by xenophobia. So it became a perfect storm I think of demonization that didn't sit with, you know what I knew about the tradition and with the actual people that I had known because I'm going back to their other friends and encounters and so on. But just thinking about Afghanistan and talk for a moment. I mean just the thought about my friends who had been who had suffered a great deal in their short lives, who have been, you know, cast aside from country to country, but he found a place in Tosca with some relative stability and you know, they wanted to go out every night and you know, they explained, you know, one friend, we talked about the alcohol and he didn't get crazy, but he was like you can drink but just don't get drunk. That's that's permissible within Islam, right? Um and he was you know ethnic pashtun, I think those bags had different view. You know often the more vodka the better. Yeah. And it doesn't violate as I understand Islam. So even, you know, it's kind of a silly example, but it's just an illustration of the ways in which different communities, different generations, different people can comment at this very complex rich tradition in some different ways. So obviously what kind of scholar you are any kind of extra, whatever you you know, it's always disconcerting to see your field of specialization be flattened, right? And then B flat. And then he turned to arguments for violence mixed </s><s>[INST] up with the natural human feelings of hate and [/INST] uh hurt and pain. So I, you know, I mean that day, I vividly remember I start with um other PhD historians in different fields. We, you know, we oddly enough had lunch that day and it kind of deserted Washington someplace was open. We went um and we just thought, you know, this is going to kind of open up like a great mall of destruction and you know, the american state is going to destroy and it's going to destroy in this geography. And I thought that was misplaced for lots of reasons. And then I think If one, you know, I been doing some research on Afghanistan, then I was kind of shifting the south and I've been looking at the taliban um from afar for some years. And you know, I think it's clear now that in respect, there were opportunities for alternative policies at that moment. </s><s>[INST] So what should the conversation have been like? What should we have done differently? Because, you know, from a perspective of the time the United States was invaded by a foreign force, what is the proper response or what is the proper conversation about the proper response? You [/INST] think, you know, my colleague is safer, cons lisa Rice would tell me this is about my pay grade and um you know, she makes a point in her classes to talk about how difficult decision making is under such intense pressure and I appreciate that. Um you know, I am a historian who sits safely my office. I don't like battlefields. I don't like taking risks. Um So I can see all those limits. You I'm not a metal expert. I've been accused of being a spy wherever I've gone because of the way I look and because of my nationality and so on, but not a spy. So I defer you know, respect the expertise of all those communities, but I think they acted out of ignorance. They acted. I think because I mean you think of the in a way that was compensatory aspect of this decision making, I mean the Bush administration failed. This is an extraordinary failure, right? So if we start to </s><s>[INST] weigh if we're going to break [/INST] down the intelligence, I mean if they if you follow the story of Richard Clarke um who's Richard Clarke, he was a national security expert who was tasked with following Al Qaeda who had a producer dossier under the current administration that he passed on to the George W Bush administration. And if you look at the work of Conley's arise, she wrote a very famous, I think unpaid walled foreign affairs article that you can read announcing the George W Bush foreign policy kind of outlook. Um, and it was all about great powers is about the rise of china, is about Russia. I mean, there's definitely a kind of hangover of those who missed having Russia as the boogeyman who spoke the demonstration repeated again again, the idea of making sure the bear stayed in his cage. Um, which is why the United States threw a lifeline to the Central asian States, hoping to have pipelines hoping to shore up there national sovereignty as a way of containing Russia initially, but also Iran, you know, which sits to the south and west and then perfectly looking down the road to china to the east. So </s>

<s>[INST] it's not as sticky in many of the other situations here. The guilt couldn't really stay for a long time. [/INST] So you number one, it's we're talking about a progressive disease that can lead to death. And if somebody commits suicide, they wanted to commit suicide. And at least what I've been told is your you can't stop it, it's gonna happen, it's gonna happen. There's no magic words, There's nothing you can do. So, you know, people who've lost people to suicide, you know what I'm talking about? Like, you know, you you you can watch it happen in real time and there's there's nothing you could do um that being said, you know, being responsive to when it seems like someone's really reaching out for help and knowing that maybe even though it might if, especially if it's someone who's like, doesn't talk like this a lot of the time and sentences start coming out of their mouth that if you weren't really paying attention might not seem like a big deal. But for this person, it's kind of anomalous that all of a sudden that's happening now there, that's when you can be a good listener and, you know, open up to them and hear what they're saying and and see like, oh share they're asking me for, is this them asking for help? And even if you're like, I don't know what to do. You know? Uh at least you can like start checking in on them, you know, start like, help them understand that you're there for them and then hopefully get them into therapy, get them to a doctor, get them to a professional who can like see what's going on there so that and then there's hope and even then there might not be hope actually, you know, doctors can't stop it. There's no sometimes it just that's the way it goes. But you know, I know that like um being sensitive if somebody's like all of a sudden hitting you up for reaching out to you that normally isn't like that and just what's going on? How are you and just listen. </s><s>[INST] Which in general the pressure or not is probably a good thing to do. [/INST] Yeah to </s><s>[INST] to to to truly listen. Yeah. [/INST] Yeah because people have, you know, I don't this whole thing like cries for help man. They don't sometimes they just look like a weird text, you know something you don't realize that for the person to send that text, they've been thinking about it all morning. They've been just trying to get their get their phone up from the floor. So you know, I think that that's it. I mean what I don't know, I don't know, I've had friends like kill themselves so and uh many of them it wasn't like sadly it was like I don't know, I don't know what could have been done, but but </s><s>[INST] there's still still a guilt in the back of your head [/INST] for the rest of my life for sure. I always will be. Yeah, I mean, yeah, but again, what are you gonna do? You? </s><s>[INST] But even that it's a part of love. That's [/INST] right, that's right, yeah, that's right. You could, yeah, we, you know, we feel guilt grief. Part of grief is guilt, you know, like you we always could have been better people, We always could have been better people. You get into victor frankel </s><s>[INST] much [/INST] man's search for meaning the invitation to live your life as though you've been on your deathbed and have been given the chance to go back and not make the same mistakes. I returned to that idea all the time, meaning it's like, okay, whatever you did before this moment, it's too late, but now, you know this is where you can start, this is where you can start and yeah, so I think that's a neurotic like me, that's super important because otherwise I'll just get like two lost in the weeds of ship shitty things I did in the past. </s><s>[INST] So speaking of victor frankel, you and Hitler have the same birthday, [/INST] oh my God, you've really done your research. </s><s>[INST] Uh Well, I I often google um famous people that have a birthday same as Hitler and the person that shows up, you know, is you your face just really [/INST] big, you </s><s>[INST] and Hitler together, just pals next to each other. [/INST] No, it does not know. But April 20 is an embarrassing birthday for all my 420 friends out there. It's embarrassing. You share a birthday with Hitler. It's </s><s>[INST] 420s also has a humor and a lightness to it, right? [/INST] It's embarrassing. Your especially life </s><s>[INST] is embarrassing, [/INST] but if you like weed and you're born on Stoner Day and you believe in reincarnation, do you realize like when you start connecting the dots there, if there is like a bardo where you get to choose your next life, </s><s>[INST] so you're like a shitty Generic NPC, you're, you're like, of course, of course you would be born on 4.20. This computer [/INST] Get 20 man. Yeah, </s><s>[INST] but isn't it interesting that on that same day Hitler is also born, there's a there's attention to that. Um and that Hitler is an artist, so it's like that hippie mindset could, could go anywhere. [/INST] Oh yeah, right? Like Yeah. You know, and I like I was just having this conversation with a friend of mine who's a wonderful skeptic, and we were talking about this uh which is the thing where you start attributing To the day you were born these kind of significance and based on maybe people who were born on that day, maybe some other things and you know, it's like, think of how many people by now in the course of human history have been born on April 20. I mean how many someone could probably do the math and come up with some number close to it now. This is how you know how rotten Hitler is? Like, he's the one that like fucks up every all the birthday for everybody else, but I think </s>

<s>[INST] And they do accomplish that. What is it? They want to show their people they're on their side. Yeah and the tribes are usually color-coded conveniently enough. What would you say, it's the Churchill question democracies, the crappiest form of government, but it's the best one we got. What's the best form of government? For this, our seven billion human civilization and the maybe as we get farther and farther, you mentioned a lot of stuff that's fascinating about human history as we become more forager-like and looking out beyond what's the best form of government in the next 50, 100 years as we become a multi-planetary species. [/INST] So the key failing is that we have existing political institutions and related institutions like media institutions and other authority institutions and these institutions sit in the vast space of possible institutions. And the key failing, we're just not exploring that space. So, I have made my proposals in that space and I think I can identify many promising solutions. And many other people have made many other promising proposals in that space. But the key thing is we're just not pursuing those proposals. We're not trying them out on small scales. We're not doing tests. We're not exploring the space of these options. That is the key thing we're failing to do. And if we did that, I am confident we would find much better institutions than when we're using now, </s><s>[INST] but we would have to actually try. So there are a lot of those topics. I do hope we get a chance to talk again. You're a fascinating human being. So I'm skipping a lot of tangents on purpose that I would love to take. You're such a brilliant person. There's so many different topics. Let me take a stroll into the deep human psyche [/INST] of Robin Hanson himself. So first- May not be that deep. I might just be all on the surface. What you see, what you get, there might not be much hiding behind it. </s><s>[INST] Some of the first fun is on the surface and- [/INST] I actually think this is true of many of the most successful, most interesting people you see in the world. That is they have put so much effort into the surface that they've constructed. And that's where they put all their energy. So somebody might be a statesman or an actor or something else and people want to interview them and they want to say like, what are you behind the scenes? What do you do in your free time? And you know what? Those people don't have free time. They don't have another life behind the scenes. They put all their energy into that surface. The one we are the one we're fascinated by and they kind of have to make up the stuff behind the scenes to supply it for you, </s><s>[INST] but it's not really there. Well, there's several ways of phrasing this. So one of it is authenticity, which is if you become the thing you are on the surface, if the depths mirror the surface, then that's what authenticity is. You're not hiding something, you're not concealing something. To push back on the idea of actors, they actually have often a manufactured surface that they put on and they try on different masks, and the depths are very different from the surface. And that's actually what makes them very not interesting to interview. If you're an actor who actually lives the role that you play, so like, I don't know, a Clint Eastwood type character who clearly represents the cowboy, like at least rhymes or echoes the person you play on the surface, that's authenticity. [/INST] Some people are typecast and they have basically one persona they play in all of their movies and TV shows. And so those people probably is the actual persona that they are, or it has become that over time. Clint Eastwood would be one I think of Tom Hanks </s><s>[INST] as an ever, I think they just always play the same person. And you and I are just both surface players. You're the fun, brilliant thinker and I am the suit wearing idiot full of silly questions. All right, that said, let's put on your wise Sage hat and ask you what advice would you give to young people today in high school and college about life, about how to live a successful life in career [/INST] or just in general that they can be proud of? Most young people, when they actually ask you that question that they usually mean is how can I be successful by usual standards? I'm not very good at giving advice about that because that's not how I tried to live my life. So I would more flip it around and say, you live in a rich society, you will have a long life, you have many resources available to you. Whatever career you take, you'll have plenty of time to make progress on something else. Yes, it might be better if you find a way to combine your career and your interests in a way that gives you more time and energy but there are often big compromises there as well. So if you have a passion about some topic or some thing that you think just is worth pursuing, you can just do it. You don't need other people's approval and you can just start doing whatever it is you think if we're doing it might take you decades but decades are enough to make enormous progress </s><s>[INST] on most all interesting things. And don't worry about the commitment of it. I mean, that's a lot of what people worry about is, well, there's so many options. And if I choose a thing and I stick with it, [/INST] I sacrifice all the other paths I could have taken. But I mean, so I switched my career at the age of 34 with two kids age zero and two, went back to grad school in social science after being a research software engineer. So it's quite possible to change your mind later in life. How can you have an age of zero? Less than one. </s>

<s>[INST] The following is a conversation with Jonathan height social psychologists at N. Y. U. And critic of the negative effects of social media on the human mind and human civilization. He gives a respectful but hard hitting response to my conversation with Mark Zuckerberg and together him and I try to figure out how we can do better, how we can lessen the amount of depression and division in the world. He has brilliantly discussed these topics in his writing including in his book The coddling of the american mind and in his recent long article in the atlantic titled why the past 10 years of american life have been uniquely stupid when teddy Roosevelt said in his famous speech that it is not the critical counts. He has not yet read the brilliant writing of Jonathan height. I disagree with john on some of the details of his analysis and ideas but both his criticism and our disagreement is essential if we are to build better and better technologies that connect us. [/INST] Social </s><s>[INST] media has both the power to destroy our society and to help it flourish. It's up to us to figure out how we take the letter path. And now a quick few second mention of the sponsor. Check them out in the description is the best way to support this podcast. We've got a Ncruz for adventure notion for startups, blankets for nonfiction. Magic for snacks and eight sleep for sweet sweet naps choose wisely. My friends and now on to the full lottery ads. No ads in the middle. I hate those. I try to make these ad reads interesting but if you skip them please check out our sponsors. I enjoy their stuff. Maybe you will too. This show is brought to you by a Ncruz Adventures, small ships, cruises, sailing to Alaska, Mexico, costa rica hawaii and so on. You can go hiking, kayaking, whale watching and seeing the northern Lights. There's something um not just humbling but somehow revealing about who we are, what we're doing here. When you look at nature, there's something about the calmness, the quiet of water stretching out to the horizon. There's something about trees as far as the eye can see. That reminds you what this is all about and somehow it's impossible to put into words. That's why it's great to take little journeys like this. You can save $500 on Alaskan adventures through june for bookings made within 30 days of departure, go to a Ncruz dot com slash pages slash lex. This show is also brought to you by notion, a note taking and team collaboration tool. It combines note taking, document sharing wookies, project management and much much much more into one space that's simple, powerful and beautifully designed. Obviously I've been using notion for a long time. Now, what I really mean to say is all the cool kids have been telling me for a long time about notion. I'm originally [/INST] if </s><s>[INST] I might admit an imax person. So a lot of the in terms of an I. D. Perspective. What I use for programming is still imax but much much less so I use the more optimized tools for the job for no taking specifically notion is just far above anything else I've used. It's an incredible tool and it's also good for the work, the company setting, that startup setting And they're running a special offer for startups. You can get up to $1,000 off the team plan To give you a sense that's almost a year of free notion for a team of 10 go to notion.com slash startups. This show is also brought to you by blink ist My favorite app for learning new things, blinkers takes the key ideas from thousands of nonfiction books and condenses them down to just 15 minutes you can read or listen to. Yeah actually the Rise and fall of the third Reich unfortunately is not on there. There's not many books about Hitler or Stalin on there perhaps for a good reason but the best I would say nonfiction books are all on there. So you're talking about sapiens meditations by Marcus Aurelius that goes on and on. [/INST] I use it </s><s>[INST] for all kinds of reasons. So one of course is to review the books I've already read two is to select the books I want to read in the future and three perhaps most powerfully is books that I just don't have time to read but are culturally and intellectually important. This life is about hard choices. And uh for the books you don't choose. Sometimes blinkers can save your ass. As a listener, you can get a free seven day trial and 25% off of a blink is premium membership at blankets.com slash flex. This episode is also brought to you by an old and favorite sponsor of this podcast. My fellow travelers on this journey of the podcast is magic spoon. Something [/INST] beautiful </s><s>[INST] that this podcast was originally and still sponsored by serial and that connects to my Sort of 10 years when Syria was such [/INST] a source of joy. </s><s>[INST] But it was also a source of gigantic amount of sugar. But that's not the case with magic spoon, which is why it's awesome. It's low carb keto friendly, zero g of sugar, 13 to 14 g of protein, only 49 g of carbs, 140 calories in the serving. And it's freaking delicious. My favorite flavor is Coco. They have a bunch of other ones. Peanut butter is pretty good too. [/INST] They have </s>

<s>[INST] spray what's thermal plasma? That's the hot kind of [/INST] That's a high temperature plasma. </s><s>[INST] Okay, so what's cold plasma then? And what kind of temperatures that we're talking about? What's this world in terms of applications and theory that's now fundamentally different from the heart kind. [/INST] Uh, cold plasma it is, it's a situation when you have electrons only electrons are hot and they generate a lot of active species radicals atoms so they can treat different materials, they can make very sophisticated structures but temperature is low food and the damage. So let's say jumping artificial intelligence. If you're talking about computer, how to make computer, how to make this a way first, how to make these chips. You have to be able to dig tiny, tiny, tiny, tiny, tiny ditches, how to do that. You have to have, you cannot use mechanical devices. So you have to have something different Beams, lasers? No, because laser is heating its temperature. But you cannot take if you just use laser, you you go to temperature reading 1,000°, you damage your phone, cannot withstand this temperature the same computer. So that's why there is no alternative today. Only called plasma to make, I would say the vast majority of electronics devices. So hardware, it's almost you say hardware. It is bad. </s><s>[INST] So let me beautifully put. What's now you said application? We'll talk about some applications including plasma medicine. But from uh, if you put on your theoretical physicists or chemists like fundamental science, hat, what are the interesting problems in plasma mysteries? They're not yet understood or things that have been recently understood. I've seen you talk about incredible applications, but let's step, let's not cover that first. Is there some open problems? How well is it understood from a theoretical perspective, [/INST] I can give you a couple of examples. It's a lot of mysteries. A lot. Why? Because this is strongly non equilibrium medium. Almost every sales which we have around us. It's an equilibrium. </s><s>[INST] What does that mean? What does it mean for a medium to be in equilibrium [/INST] equilibrium means it has temperature </s><s>[INST] has temperature. Yeah. [/INST] Some temperature like this is, let's say room temperature. </s><s>[INST] Well, no, I mean, what you mean by that is there's a uniformity to it [/INST] uniformity temperature uh not space uniformity but become a community like it's a temperature. Now, can you imagine something which has a couple of different temperatures at the same point? Is it possible? Yeah, that's what it is. So electrons are very hot but they are inside of gas and gas is called like like a uh people that are swimming in the ocean. So temperature of a person is higher. But here the temperature is way, way, way higher. Now what starts happening in this case? It's a lot of finding miracles. A lot of funny miracles. For example, electron impact creates expectation of molecules molecules the stylist oscillate, mhm And people they learn the distribution is becomes very strange energy rich molecules they they take more energy when they have already something and okay, rich people, they become richer and poor people then becomes more poor. Exactly the same thing they call it capitalism. In molecular life happens in plasma. So what is going on? You take molecules in class maybe excite and very fast against all rules of whatever nature, couple of molecules they have to quantum and they have more and more and more and more and more and more and very soon make some molecules they have everything and most of molecules have nothing. As a result, we have this kind of non equilibrium immediately creates lasers. So this is one of the reasons why lasers. First all First lasers they were created in plasma even now the most energetic like C. 02 laser is a plasma lasers and there's also plasma laser so plasma is very accelerated application but physics is here, I can explain it a bit longer how it works but it's very similar to what is going on with people. If you already have money it's easier for you to attract new money if you are actually poor sooner or later you will lose your money in the favor of rich </s><s>[INST] people. Not sure how well the analogy works but probably but they're saying that there's some fascinating complicated instability about that whole. [/INST] But it's interesting capitalism, it's an interesting instability, it's instability not space instability, it's energy and stability. It's like a </s><s>[INST] uh as you said capitalism, capitalism at the molecular level [/INST] it's a capitalism, it's like a wild capitalism where just everything works against middle class. </s><s>[INST] Who's the Bernie Sanders in this physics analogy? I'm just kidding. That's who's the socialist. Okay, I don't know. Let's not take this analogy. [/INST] That's interesting that you know that plasma works works against Bernie Sanders. So Nature. Nature. </s><s>[INST] Nature is a is a is a Republican, this is more Republican. Nature's Republican. Well [/INST] no not nature. I mean plasma it's only non equilibrium plasma </s><s>[INST] non equilibrium plasma [/INST] living in plasma it's everything is very much Bernie Sanders is very much honest distribution. </s><s>[INST] Yeah. Well non equilibrium plasma is uh live a short life and die quickly. So so if you want a long peaceful existence, you want to go. And that's one of the reasons why Bernie Sanders in physics. [/INST] That's very interesting that for this reason non equilibrium plasma cold plasma is able to produce way more miracles as uh </s><s>[INST] miracles, meaning very interesting, strange pattern [/INST] structures, patterns, treatment like you cannot use hot plasma to make electronic device. Well, you can do, it is just one example. Another example is like recently I came yesterday. Well, yeah, yesterday from Japan. So we presented ionization of liquids. Not guesses. So it's a lot of interesting new </s>

<s>[INST] So but but the reality is that Bitcoin used to be In the single digits of a dollar and now has crossed $50,000 for a single Bitcoin. Do you think it's possible it reaches something like $1 million? [/INST] I don't think we have a good theory of the value of Bitcoin. If people decide it's worth $1 million, it's worth $1 million. </s><s>[INST] But isn't that money like you said isn't the ultimate state of money. Confusion however beautifully put [/INST] it, it's like valuing an Andy Warhol painting. So when Warhol started off probably those things have no value sketches, early sketches of shoes. Now a good Warhol could be worth over 50 million. That's an incredible rate of price appreciation. Bitcoin is seeing a similar trajectory. I don't pretend to know where it will stop but it's about trying to figure out what do people think of Andy Warhol? He could be out of fashion in a century maybe. Yes maybe no. Uh but you don't think about Warhol's as money. They perform some money like functions you can even use them as collateral for like deals between gangs but they're not basically money nor is Bitcoin. And the transactions velocity of Bitcoin I would think is likely to fall if anything. </s><s>[INST] So you don't think there will be some kind of phase shift. Will it become adopted become mainstream for the trend for for the main for one of the main mechanisms of transactions. [/INST] Bitcoin know now you know ether has some chance at that. I would bet against it but I wouldn't give you a definitive no and you would coin is too costly. It may be fine to hold it like gold but gold is also costly. You have smart people trying to make say either much more effective as a currency than Bitcoin and there's certainly a decent chance they will succeed. </s><s>[INST] Yeah there's a lot of innovation and smart contracts with the N. F. T. S. As well. There's there's a lot of interesting like innovations that are plugging into the human psyche somehow just like money does you know money seems to be this viral thing. Our ideas of money, right? And if the idea is strong enough it seems to be able to take hold like there's network effects that just take over and like I I particularly see that with, I'd love to get your comment on uh dash coin which is basically by a single human being. Elon musk has been created. You know it's like these celebrities can have a huge ripple effect on the impact of money. Is it possible that in the 21st century people like Elon musk and celebrities, I don't know, donald trump the rock, whoever else uh can have can actually define you know the currencies that we use maybe candles going behind the primary currency of the world. [/INST] I think of it as like baseball cards. So right now every baseball player has a baseball card and the players who are stars. Their cards can end up worth a fair amount of money and that's stable. We've had it for many decades uh sort of the player defines the card, they sign a contract with tops or whatever company now could you imagine celebrities, baseball players Lebron James having their own currencies instead of cards. Absolutely and you're somewhat seeing that right now as you mentioned, artists with these unique works on the Blockchain. But I'm not sure those are macro economically important. If it's just a new class of collectibles that people have fun with. Again, I say bring it on. But whether there are use cases beyond that challenge fiat monies, which actually work very well. Yesterday I sent money to a family in Ethiopia that I helped support In less than 24 hours. They got that money digitally. Yes. No, not digitally through my bank, my primitive dinosaur bank BB and T mid atlantic bank headquartered in north Carolina. You know, chartered by the Fed regulated by the F D A. C. And the zero cc. Now you can say, well the exchange rate was not so great. Uh, I don't see crypto as close to beating that. Once you take into account all of the last mile problems, fiat currency works really well. People are not sitting around bitching about it. And when you talk to crypto people, the number who have to postulate some out of the blue hyperinflation, there's no evidence for that whatsoever. That's to me is a sign. They're not thinking clearly about how hard they have to work to out compete. Fiat currency. </s><s>[INST] There's a bunch of different technologies that are really exciting that don't want to address how difficult it is to out compete. The current accepted alternative. So for example, autonomous vehicles. A lot of people are really excited but it's not trivial to out compete. Uber on the cost and the effectiveness and the user experience and all those kinds of, sorry, Uber driven by human. So, uh, and it's not, you know, that's taken for granted. I think that look, wouldn't it be amazing? How amazing would the world look when the cars are driving themselves fully? You know, it's going to drive the cost down and you can remove the cost of drivers, all those kinds of things. But when you actually get down to it and have to build a business around it, it's actually very difficult to do. And I guess you're saying your senses, similar competition is facing Cryptocurrency like you have to actually present a killer app reason to switch from fiat currency, uh, to uh, to ethereum [/INST] and the biden people are going to regulate crypto and they're going to do it soon. So something like defi I fully get why that is cheaper or for some can be cheaper than other ways of conducting financial intermediation. But some of that is regulatory arbitrage. It will not be allowed to go on forever for better or worse. I would rather see it given greater tolerance. And, but the point is banking lobby is strong. The government will only let it run so far. There'll be capital requirements, reporting requirements imposed and it will lose a lot of those advantages. </s>

<s>[INST] consequence that Lauren's talking about. That's the category of security that Bitcoin has talked about that it's very difficult to do that with Bitcoin. But I would argue that's exceptionally difficult to do that with gold. [/INST] It is now, it is now, but the thing is there's not a huge incentive. If gold is the basis and if gold is worth that much, it's right. Gold isn't worth that much, gold is worth— I'm saying in this world that we're talking about, in the future. In the future, yeah. Gold is not going to be worth more—let's say right now gold is about $2,000. Let's say it's $2,000. That a price in terms of dollars, you'd have to— it would have to be worth your while to create something that's $2,000, how much would you be willing to put into it? At some point you're right, and at that point I think gold stops bring money because it's useless. Once I can create it like silicon, then once I can make out official gold. I'm just not, I don't think Bitcoin is the solution. I think, I don't know what the solution is. I wish I was that innovative, but I think you need a solution that has more of the characteristics of gold than Bitcoin currently has. And I guess I'm surprised because they're useless at a lot of the technologists who view Bitcoin as the end game, where it strikes me as it's the birth of a new technology, it represents the birth of a new technology. And who the winner in that technology is going to be, we have no clue, Bitcoin is one of the players, there are other players. They might be a new technology that is even better than anything we can imagine right now. So Bitcoin doesn't strike me as optimal, and that we should be moving towards something Can you please stop shilling Rand coin for five minutes? You know where there was Rand coin? South Africa? No. There's currencies for Rand. No, that's true. Iron Rand is the South African, there's currencies for Rand. That's true. No. Iron Rand is the South African $1 dollar. Iron Rand coin was, I was in China in 20, I think it was 2015 or 2014. China. China. I was in China 20, something like that, and this entrepreneur came up to me, she said she's bought this massive quantity of land in this area in China, it's a little secluded. She's starting what she's calling Goldsculch, she's serious, and she's issuing, and she issued cryptocurrency based on the land, right, backed by the land called Rand, but Ayn Rand, a little portrait of Ayn Rand, you know, a little portrait in the in the in the marketing. I don't think it went anywhere. You're not gonna be a janitor? A janitor? You're not gonna be a janitor? A janitor in China Goldsculch, yeah. By the way, I do want to point out something I do enjoy about objectivists. I constantly talk about Ayn Rand and her vampire novels, and that's the joke you're on, thank you. And inevitably someone feels the need to point out that she did not write vampire novels, and her name is actually Ayn, so thank you. We've been talking for two hours, I own her copy of Fountainhead, somehow I thought her name was Ayn thank you. Ayn is an anthem. We've been talking for two hours, thank you. So this is really interesting way of phrasing it. I was kidding with the Ein. I know you knew how to pronounce it. I know you know you know. Yeah, he just got </s><s>[INST] confusing. I think we all know and we all know that we're jokers here. We're all one. There's no Batman in this conversation. So it's an interesting way to frame it is Bitcoin the end or the beginning of something and I've as sort of with an open mind and seeing kind of all the possibilities of technologies out there, I also kind of thought that Bitcoin is the beginning of something. But what the Bitcoin community argues is that Bitcoin is the end of the base layer, meaning all the different innovations will come on top of it. Like for example, there's something called Lightning Network where it's basically just like gold is the end and everything is built like the monetary systems like cash and all that is built on top of gold. Bitcoin is the end in that other technologies that build on top of Bitcoin. That's their argument. I get that and I hear that [/INST] all the word jokers here. We're all one. There's no Batman in this conversation. I get that and I hear that all the time and I don't quite understand that and I think Bitcoin has limitations that potentially other cryptocurrencies might not have. My attitude too with something like this is large extent I don't understand technology. My view is let it play out. I think I have more fear of physical the ability of the government to crush these things than I think many in the community. So for example, so I gave a talk of Bitcoin and they were hyping the acceptance now. A lot of vendors are willing to accept Bitcoin and this is great. I said, yeah, it's absolutely great. More options is better than fewer options. But I said, you know that that could be taken away like that. Now it's true that we could exchange Bitcoin and the government wouldn't know, I think wouldn't know that we do. But once he's advertising on his website that he accepts Bitcoin or once he tries to turn his Bitcoin into particular goods, once you manifest it in the physical world, now the government can step in. So the government could say you can't sell anything to anybody using Bitcoin. They can do that and you won't be able to sell it. It will have to go into the black market. That isn't able to sell it just to just sell you in the black market. Yeah. But that's where the government thrives, right. The government thrives on letting you do stuff in the black markets so they can decide when to put your jail or not. So if I'm buying a sweatshirt from the government, sorry, if I'm buying a sweatshirt from somebody using Bitcoin, the government can't monitor my exchange of Bitcoin to him, but they can monitor the sweatshirt being sent to me. That's where they can interfere. And I think that at some point, to the extent Bitcoin is successful, it will be stopped. And that's what will stop it from becoming money. See, money can only become money if people are using it as money. And if the government can stop it being used, if I can't go to the grocery store and use my ATM that charges on Bitcoin or whatever, jail or not, then it's not money. And I think that the government is going to step in and stop people from doing that. And that's what I saw. I have more respect and fear for the power of government today. I don't see that at all. However, I could be wrong. And I'm sure Yaron hopes he's wrong. Absolutely. I hope the government just give in and the Fed tomorrow says, yeah, let Bitcoin thrive. But I think that one of regulated control and </s>

<s>[INST] hard problem, a hard problem. But you haven't shied away from hard problems so well, you know. Uh So deep learning has been at the core of a lot of this technology. Are you optimistic about the current deep learning approaches to solving the hardest aspects of what we're talking about or do you think there will come a time where new ideas need to for the, you know, if you look at reasoning, so open the I. D. Mind a lot of folks are now starting to work in reasoning, trying to see how you can make your own networks, reason. Do you see that new approaches need to be invented to take the next big leap? [/INST] Absolutely. I think there has to be a lot more investment and I think in many different ways. And there are these, I would say nuggets of research farming in a good way, like learning with less data or uh like zero short learning, one short learning </s><s>[INST] and the active learning stuff you've talked about it. Yes, it's incredible. [/INST] So transfer learning is also super critical, especially when you're thinking about applying knowledge from one task to another or one language to another. Right? It's really right. So these are great pieces Deep learning has been useful to and now we're sort of marrying deep learning with uh transfer learning. Uh an active learning of course, that's more straightforward in terms of applying deep learning and an active learning setup. But but I do think in terms of uh now looking into more reasoning based approaches is going to be key for our next wave of technology. But there is a good news. The good news is that I think for keeping on to delight customers that a lot of it can be done by prediction tasks. Uh so and so we haven't exhausted back, so it's uh we don't need to give up on the deep learning approaches for that. So that's just, I wanted to uh </s><s>[INST] sort of creating a rich, fulfilling, amazing experience that makes amazon a lot of money and a lot of everybody a lot of money because it does awesome things. Deep learning is enough. The point, the point, I don't [/INST] think uh no, I mean I wouldn't say deep learning is enough, I think for the purposes of Alexa accomplished the task for customers, I'm saying there's still a lot of things we can do with prediction based approaches that do not reason, right? I'm not saying that and we haven't exhausted those, but for the kind of high utility experiences that I'm personally passionate about what Alexa needs to do, reasoning has to be solved to the uh to the same extent as you can think of natural language understanding and speech recognition to the extent of understanding intense has been, how accurate it has become. But reasoning, we have very, very early days, </s><s>[INST] let me ask you another way, how hard of a problem do you think that is [/INST] hardest of them? I would say hardest of them because again uh the hypothesis space of Israeli really large and when you go back in time, like you were saying, I wanna, I want Alexa to remember more things that once you go beyond a session of interaction, which is by session, I mean a time span which is today to worse is remembering which restaurant I like and then when I'm planning a night out to say do you want to go to the same restaurant now? You're up the stakes big time. And and this is where the reasoning dimension also goes very, very bigger. </s><s>[INST] So you think the space be elaborate on that a little bit just philosophically speaking, Do you think when you reason about trying to model what the goal of a person is in the context of interacting with Alexa, you think that space is huge? It's [/INST] huge? Absolutely. </s><s>[INST] You think so like another sort of devil's advocate would be that we human beings are really simple and we all want like just a small set of things. And there, so do you think you think it's possible cause we're not talking about fulfilling general conversation perhaps actually the Alexa prize is a little bit more about after that creating a customer, like there's so many of the interactions, it feels like are clustered in groups that are don't require general reasoning [/INST] I think yeah, you right in terms of the head of the distribution of all the possible things customers may want to accomplish. The tail is long and its diverse. Uh Right, so </s><s>[INST] from many, many long [/INST] tails from that perspective, I think you have to solve that problem otherwise uh and everyone is very different, like I mean we see this already in terms of the skills, right? I mean if you if you're an average surfer, which I am not right, but somebody is asking Alexa about surfing conditions, right? And there is a skill that is there for them to get to, right, that tells you that the tail is massive, like in terms of like what kind of skills people have created, it's humongous in terms of it and which means there are these diverse needs. And uh and when you start looking at the combinations of these, right? Even if you are pairs of skills, uh 90,000 to 2, it's still a big concern of combinations you're going. So I'm saying there's a huge to do here now uh and I think customers are, you know, wonderfully frustrated with things and they keep getting to do better things </s>

<s>[INST] can't communicate with them [/INST] yet. Peacock or something of the kind of standard. And this is not quite what I work on. But the standard answer is that its female mate choice. She is looking for good genes. And if you can have a tail that's like this and still survive still be alive. Not actually have been taken down by the nearest predator then you must have got pretty good genes because despite this handicap you're able to survive. So </s><s>[INST] so those are like human interpret a ble things like with a peacock. But I wonder, I'm sure echoes of the same thing are there with more primitive organisms basically your pr like how you advertise yourself that you're worthy of. [/INST] Absolutely. So </s><s>[INST] one big advertisement is the fact that you survived at all. Let [/INST] me give you 11 beautiful example of of an algal bloom. And this can be this can be a sign of bacteria that can be in bacteria. So so if if suddenly you you you know you pump nitrate or phosphate or something into the ocean and everything goes green. You end up with all this algae growing there. Um a viral infection or something like that can kill the entire bloom overnight. And it's not that the virus takes out everything overnight. It's that most of the cells in that bloom kill themselves before the virus can get onto them. And it's through a form of cell death called programmed cell death. And we do the same things is how we have the different, you know, the gaps between our fingers and so on is how we craft synapses in the brain. Um You know, it's fundamental again to to to multicellular life. They have the same machinery in these in these algal blooms. How do they know who dies? The answer is they will often put out a toxin and that toxin is kind of a challenge to you either you can cope with the toxin or you can't if you can cope with it, you form a spore and you will go on to become the next generation. Your your your form a kind of a resistance spore. You sink down a little bit. You get out of the way you're out of the out of you can't be attacked by a virus if you're a spore or at least not so easily. Whereas if you can't deal with that toxin you pull the plug and you you you you you trigger your death apparatus and you kill yourself </s><s>[INST] truly life and death. [/INST] Yeah so it's really it's a challenge and this is a bit like sexual selection is it's not so they're all pretty much genetically identical but they had different life histories. So have you had a tough day. Did you did you happen to get infected by this virus or did you run out of iron or did you get a bit too much sun? Whatever it may be? If this extra stress of the toxin just pushes you over the edge. Then you have this binary choice. Either you or the next generation or you kill yourself now using the same machinery. </s><s>[INST] It's also actually exactly the way I approach dating. But that's that's probably why I'm single. Okay what about if you can step back D. N. A. Just mechanism of storing information? R. N. A. D. N. A. How big of an invention was that? That seems to be? That seems to be fundamental to like something deep within what life is is the ability as you said, to kind of store and propagate information. But then you also kind of infer that with your and your students work that there's a deep connection between the chemistry and the ability uh to have this kind of genetic information. So how big of an invention is is it to have a nice representation. Nice hard drive for info to pass on [/INST] huge I suspect. I mean but when I was talking about the code, you see the code in RNA as well. An RNA almost certainly came first. Um and there's been an idea going back decades called the RNA world because RNA in theory can copy itself and can catalyze reactions. So it kind of cuts out this chicken and egg loop, </s><s>[INST] the D. N. A. It's possible it's not that special. [/INST] So our RNA RNA is the thing that does the work really. And the code lies in RNA. The code lies in the interactions between RNA and amino acids. And it still is there today in the river zone for example which is just kind of a giant rivers. I'm which is to say it's an enzyme that's made of of RNA. Um so getting to R. N. A. I suspect it's probably not that hard but getting from R. N. A. How do you you know there's multiple different types of RNA Now. How do how do how do you distinguish this is something we're actively thinking, how do you distinguish between you know a random population of RNA. Some of them go on to become a messenger RNA. That this is the transcript of the code of the gene that you want to make. Some of them become transfer RNA. Which is which is this kind of the unit that holds the amino acid that's going to be plagiarized. Some of them become reversible RNA. Which is the machine which is joining them all up together. How do they discriminate themselves And you know some kind of phase transition going on? There was I don't know it's a difficult question and we're now in the region of biology where information is coming in. But the thing about RNA is very very good at what it does but the largest genome supported by RNA of RNA viruses like HIV for example they're pretty small. Um And and so there's a limit to how complex life could be unless you come up with D. N. A. Which chemically is a really small change. But how easy it is to make that change. I don't really know. As soon as you got D. N. A. Then you've got an amazingly stable molecule for information storage and you can do absolutely anything but how likely that transition from RNA to DNA was. I don't know either how </s>

<s>[INST] to linger on the little thread they started pulling on this man, Genghis khan that was a [/INST] leader. </s><s>[INST] What do you think makes a great leader. Maybe if you have other examples throughout history and great again, let's lose that use that term loosely. [/INST] He's going to ask for a definition. </s><s>[INST] Great uniter of whether it's evil or good. It doesn't matter. Uh huh is there somebody who stands out to you alexander the grace, we're talking about military or ideologies, you know, some people bring up FDR or or I mean it could be the finding fathers of this country or we can go to uh was he man a man of the century up there, Hitler of the 20th century and Stalin and these people had really a mass, the amount of power that probably has never been seen in the history of the world. Is there somebody who stands out to you by way of trying to define what makes a great uniter, great leader in one man or a woman, maybe in the future. [/INST] It's an interesting question and I would have thought a lot about because let's take alexander the Great as an example because alexander fascinated the world of his time, fascinated ever since people have been fascinated with the guy, but alexander was a hereditary monarch, right? He was handed, the kingdom is fascinating, but he did not need to rise from nothing to get that job. In fact, he reminds me of a lot of other leaders of Frederick the Great for example, in Prussia, these are people who inherited the greatest army of their day, alexander unless he was an imbecile was going to be great, no matter what, because I mean, if you inherit the very mock you're going to be able to do something with it, right alexander's father may have been greater Philip. Uh, he Philip the second was the guy who, who literally did create a, a strong kingdom from a disjointed group of people that were continually beset by their neighbors. He's the one that reformed that army, uh, took things that he had learned from other greek leaders, like the theme and leader of team a ninja's. Um and and then laboriously over his lifetime stabilized the frontiers built this system. He lost an eye doing it. He, his leg was made lame. I mean this was a man who looked like he built the empire and lead from, from the front ranks, I mean um so and then, and then who may have been killed by his son, We don't know who assassinated Philip, but then handed the greatest army the world had ever seen to his son who then did great things with it. You see this, this pattern many times in my mind, I'm not sure alexander really can be that great when you compare him to people who arose from nothing. So the difference between what we would call in the United States, the self made man or the one who inherits a fortune. There's an old line that, you know, it's, it's a slur, but it's about rich people and it's, it's like he was born on, he was born on third base and thought he hit a triple, right? Um, Philip was born at home plate and he had to hit alexander started on third base and so I try to draw a distinction between them. Genghis khan is tough because there's two traditions, the tradition that we grew up with here in the United States and that I grew up learning was that he was a self made man, but there is a tradition and it may be one of those things that's put after the fact because a lot a long time ago, whether or not you had blue blood in your veins was an important distinction. And so the distinction that you'll often hear from Mongolian history is that this was a nobleman who had been deprived of his inheritance. So he was a blue blood. Anyway, I don't know which is true. Uh, there's certainly, I mean when you look at agendas condo, you have to go, that is a wicked amount of, of things to have achieved. Uh he's very impressive as a figure until is very impressive as a figure. Um Hitler is an interesting figure. He's one of those people, you know, the more you study about Hitler, the more you wonder where the defining moment was because um if you look at his life, Hitler was a relatively common soldier in the First World War. I mean he was brave, he got uh he got some decorations. In fact, the highest decoration he got in the First World War was given to him by a jewish officer and it was uh, he often didn't talk about that decoration, even though it was the more prestigious one because it would open up a whole can of worms you didn't want to get into. But Hitler's, I mean if you said who was Hitler today, one of the top things you're going to say is he was an anti Semite. Well then you have to draw a distinction between general regular anti Semi Semitism that was pretty common in the era and something that was a rabid level of anti Semitism. But Hitler didn't seem to show a rabid level of of anti Semitism until after or at the very end of the First World War. So if this is a defining part of this person's character and much of what we consider to be his, his evil stems from that. What happened to this guy when he's an adult, right, He's already fought in the war to change him. So, I mean it's almost like the old, there was always a movie theme. Somebody gets hit by by something on the head and their whole personality changes, right? I mean it almost seems something like that. So I don't think I call that necessarily a great leader. To me, the interesting thing about Hitler is What the hell happened to a nondescript person who didn't really impress anybody with his skills. And then in the 1920s is all of a sudden, as you said, sort of the man of the hour, right? So that to me is kind of, I have this feeling that Genghis Khan and we don't really know was an impressive human being from the get go and then he was raised in this environment with pressure on all sides. You start with this diamond and then you polish it and you harden it his whole life. Hitler seems to be a very unimpressive gemstone most of his life and then all of a sudden, so I mean, I don't think I can label great leaders and I'm always fascinated by that idea that I'm trying remember who the quote was by that great men, Lord Acton. So great men are often not good men. Uh and that in order to be great, you would have to jettison many of the moral qualities that we normally would consider, jesus or Gandhi or you know, martin these qualities that one looks at as, as the good upstanding moral qualities that we should all aspire to as examples, right? The buddha, whatever it might be. Um those people wouldn't make good leaders because what you need to be a good leader often requires the kind of choices that a true philosophical diogenes moral man wouldn't make. Um so I don't have an answer to your question, How about that? That's a very long way of saying, </s>

<s>[INST] You're saying some of the magic is in the early stages of what the closer to the raw information, high brain interesting I believe so um [/INST] you know the stimulus you know there are only encodes that stimulus. So you know the transformation when I say this for those who don't think about sensory transformations it's like I can show you a red um circle and then I look at how many times the neuron fires in response to that red circle and then I can show the red circle a bunch of times green circles, see if it changes and then essentially the number of times that is the transformation you've converted red circle into like three action potentials, you know B. P. P. Or whatever you want to call it, you know for those that think in sound space. So that's what you've created. You know the transformation and you march up the it's called the neuro axis as you go from the periphery up into the cortex and we know that and I know lisa um Feldman Barrett or visit Barrett, Feldman Barrett film. Excuse me. Um lisa um talked a lot about this that you know birds can do sophisticated things and whatnot as well but humans there's a strong, what we call civilization, A lot of the processing has moved up into the cortex and out of these sub cortical areas but it happens nonetheless. And so as long as you know, the transformations you are in a perfect place to build machines or add machines to the brain that exactly mimic what the brain wants to do, which is take events in the environment and turn them into internal firing of neurons. So the </s><s>[INST] mastery of the brain can happen at their early, you know, another perspective of it is uh you're saying this means that humans aren't that special. Uh if you look at the evolutionary time scale the leap to intelligence is not that special. So like the extra layers of abstraction isn't where most of the magic happens of intelligence, which gives me hope that maybe if that's true, that means the evolution of intelligence is not that rare of an event. [/INST] I certainly hope not. Um, </s><s>[INST] you you hope there's [/INST] I hope there are other forms of intelligence. I mean I think what humans are really good at. Um and here I want to be clear that this is not a formal model, but what humans are really good at is taking that um plasma Barbell that we were talking about earlier and not just using it for analysis of space, like the your immediate environment, but also using historical information. Like I can read a book today about the history of medicine. I happen to be doing that lately for some stuff I'm researching and I can take that information and if I want I can inject it into my plans for the future. Other animals don't seem to do that over the same time scales that we do now. It may be that the chipmunks are all hiding little like notebooks everywhere in the form of like little dirt castles are something that we don't understand. I mean the waggle dance of the bee is in the most famous example, bees come back to the hive, they orient relative to the honey comb and they waggle. There's a guy down in Australia named Srinivasan who studied this. It's really interesting. No one really understands it. So he understands it best. The bee waggles at a couple of ways relative to the orientation of the honeycomb and then all the other bees see that it's visual and they go out and they know the exact coordinate system to get to the, to the source of whatever it was the food and bring it back. And he's done it where they isolate the bees, He's changed the visual flight environment all this stuff they are communicating and they're communicating something about something they saw recently, but it doesn't extend over very long periods of time. The same way that you and I can both read a book or you can recommend something to me and then we could converge on a set of ideas later. And uh in fairness because she was the one that said it and I didn't and I hadn't even thought of it. Um when you talk to lisa on your podcast, she brought up something beautiful which is that I had never really occurred to me and I was sort of embarrassed that it hadn't, but it's really beautiful and brilliant. Which is that you know, we don't just encode senses in the form of color and light and sound waves and tastes. But ideas become a form of sensory mapping. And that's where the you know, the really, really cool and exciting stuff is. But we just don't understand what the receptive fields are for ideas. What's an idea of receptive field </s><s>[INST] and how they are communicated between humans because we seem to be uh to be able to encode those ideas in some kind of way. Yes, it's taking all the raw information and the internal physical states. The that sensor information put into this concept blob that would come in the store and they were able to communicate that [/INST] your abstractions are different than mine. I actually think the comment section, you know on on social media is a beautiful example of where the abstractions are different for different people. So much of the misunderstanding of the world is because of these these idea receptive fields. They're not the same. Whereas I can look at a photo receptor neurons are olfactory neuron or a V. One neuron and I am certain I would bet my life that yours look and respond exactly the same way that lisa's due in mind you but once you get beyond there it gets tricky. And so when you say something where I say something and somebody gets upset about it or even happy about it, their concept of that might be quite a bit different. They don't really know what you mean, they only know what it means to them. </s>

<s>[INST] a [/INST] real experiment you have to have observation and you have sees that all done the right way I don't want to have somebody that starts with what if as a question and then to resist what if into the only argument and the only conclusion there </s><s>[INST] as [/INST] you understand one but still </s><s>[INST] I think it's valuable to appreciate the mystery and not deny the mystery so [/INST] other mysteries there but what I don't want these people taking advantage of the public and making money out of folklore </s><s>[INST] let me flip that I I understand but so there's a full court and like with the stuff I do A. I. robotics for example there's a clear fear terminator and movies and all this kind of stuff you could say that I'm very concerned about this miss calibrated our understanding of the public of what robots rule are in society or you could see it as a let's use a metaphor of a wave you can say this giant wave they'll call for core is a really bad idea we need to avoid it we need to hide need to build dams or you can be a surfer and ride the wave as a scientist you could it be that to me the fact that people are wondering about the mystery of your foes in ms wondering [/INST] no they are but the thing I I I will stop surfing that wave when it comes back to bite and entire scientific </s><s>[INST] science teacher [/INST] for now the past sixty years we were not able to raise money from the government no grants hi it's a discipline that has no political very little post doc just because there is a fear of that folklore on the political arena people don't want to be associated with that because they confuse the two so I stopped there N. as the director of the call siguen center I am just very happy to see now that there is a course correction in the government seeking scientific investigators for these kind of issues and hopefully that will right the ship there </s><s>[INST] I love it I love to see it but I want in a lover little disagreements I'm I'm doing so obviously respectfully with love and it's it makes for a fun conversation but I think you know just like with surfing a wave there there there's some level of even more you resist it the worse it is so I [/INST] couldn't resist it </s><s>[INST] yes they [/INST] got from us and we pay the price </s><s>[INST] I just think that the role of this scientist in part in the twenty first century on talk about social media is to direct this sense of wonder that people have into a direction of the rigors of science [/INST] I think we do that pretty well </s><s>[INST] I would disagree I don't think Sadie does much better but there's other places in science work [/INST] for life you still it felt easy place to you know draw the wonder of people yes because it's a profound question that pretty much everybody has </s><s>[INST] but I think I just want to highlight the fact that I think a lot of scientists my colleagues friends think that all you need to do is science all you need to do is this the the scientific process the peer review process the data and so on but I think communication is actually a fundamental part of the process is it has to do with funding but also is to to protect where where wedgie humans trying to ask big questions trying to figure this whole puzzle out and [/INST] really agree we do have more public presentation at the institute than peer reviewed articles and believe me we have a </s><s>[INST] lot [/INST] of peer review articles so our scientists allowed there and they are sharing the wonder of discoveries and it's so easy these days I mean there is not a one day tell me about writing a book right now about the search for life in the universe I mean it's almost every single day I had to correct something in the chapters I was writing </s><s>[INST] so city in terms of both signatures and signals is a pretty active field [/INST] so it's getting better right now it's getting better of the remember that the city institute is not only about the search for extraterrestrial intelligence this is the route of that you sorry go route of the institute but it's about ten percent of what we do in fact we are searching for life in the universe from the origins of life to extraterrestrial intelligence so ninety percent of everything else's exoplanet of for instance we have a good chunk of the camera team that is actually a with the city institute and they are working with test right now some already have some time on the gem sweat we have a stroke by allergies we have astronomers </s><s>[INST] and those are looking for data for signals for planets out there goes out of arsenal and [/INST] a goal to another places to try and understand the type of like a survive in planetary type environments I mean people are always surprised when I tell them you know whatever flies in the solar system S. one or will be flying we're involved so this is not something that pops in everybody's mind when they are thinking about the the study institute because we started off as the search for extraterrestrial intelligence but the institute has really blown into the search for life along the Drake equation all the terms of the Drake equation </s>

<s>[INST] So just like thinking about it long enough. Like studying looking at sample data, like you said driving my intuition is really flawed on this. Like I don't have a good intuition about tracked ability. It could be either, it could be anything, it could be solvable. Like uh, you know, the driving task could be simplified into something quite trivial. Like uh, the solution to the problem would be quite trivial and at scale more and more cars driving perfectly might make the problem much easier. The more cars you have drive, like people learn how to drive correctly, not correctly, but in a way that's more optimal for heterogeneous system of autonomous and semi autonomous and manually driven cars that could change stuff. Then again also have spent a ridiculous number of hours just staring at pedestrians crossing streets, thinking about humans and it feels like the way we use our eye contact, it sends really strong signals and there's certain quirks and edge cases of behavior and of course a lot of the fatalities that happen have to do with drunk driving and um, both on the pedestrian side and the driver's side. So there's that problem of driving at night and all that kind of so I wonder, you know, it's like the space of possible solution to autonomous driving includes so many human factor issues that it's almost impossible to predict. There could be super clean, nice solutions. [/INST] Yeah, I would say definitely like to use a game analogy, there's some fog of war, but you definitely also see the frontier of improvement and you can measure historically how much you've made progress. And I think for example, at least what I've seen and roughly five years of Tesla when I joined, it barely kept laying on the highway. I think going up from Palo Alto to SF was like three or four interventions anytime the road would do anything geometrically or turn too much, it would just like not work. And so going from that to like a pretty competent system in five years and seeing what happens also under the hood and what the scale of what the team is operating now with respect to data and computer and everything else, uh, is just a massive progress. So </s><s>[INST] just you're climbing a mountain and fog, but you're making a lot of progress, [/INST] You're making progress and you see what the next directions are and you're looking at some of the remaining challenges and they're not like, uh, they're not perturbing you and they're not changing your philosophy and you're not control contorting yourself. You're like actually these are the things that we still need to do. </s><s>[INST] The fundamental components of solving the problems seem to be there for the data engine, to the computer, the computer on the card, to the computer, the training, all that kind of stuff. So you've done over the years, you've been a test, you've done a lot of amazing breakthrough ideas and engineering, all of it. Um, from the data engine to the human side, all of it can you speak to why you chose to leave Tesla, [/INST] basically, as I described, that ran? I think over time, during those five years I've kind of gotten myself into a little bit of managerial position, most of my days where you know, meetings and growing the organization and making decisions about sort of high level strategic decisions about the team and what it should be working on and so on and uh it's kind of like a corporate executive role and I can do it, I think I'm okay at it, but it's not like fundamentally what I what I enjoy. And so I think when I joined um there was no computer vision team because Tesla was just going from the transition of using mobile, I a third party vendor for all of its computer vision to having to build this computer vision system. So when I showed up there were two people training deep neural networks and they were training them at a computer at their at their legs. Like down there was a </s><s>[INST] basic classification task [/INST] and so I kind of like grew that into what I think is a fairly respectable deep learning team, massive computer cluster, very good data annotation organization. And uh I was very happy with where that was, it became quite autonomous. And so I kind of stepped away and I, you know, I'm very excited to do much more technical things again. Yeah, and kind of like we focused on a G I </s><s>[INST] what was this soul searching like you took a little time off and think like what how many mushrooms did you take? I mean what what was going through your mind, the human lifetime is finite? [/INST] You </s><s>[INST] did a few incredible things, You're you're one of the best teachers of ai in the world, You're one of the best and I don't mean that, I mean that in the best possible way you're one of the best tinkerers in the Ai world, meaning like understanding the fundamental fundamentals of how something works by building it from scratch and playing with the basic intuitions, it's like Einstein Feinman, we're all really good at this kind of stuff, like a small example of a thing to to play with it, to try to understand it. So that and obviously now will you help build a team of machine learning um uh like engineers and a system that actually accomplished something in the real world, given all that, like what what was the soul [/INST] searching? Like? It was hard because obviously I love the company a lot and I love I love Ellen, I love Tesla, I want um it was hard to leave, I love the team basically. Um but yeah, I think actually I would potentially like interested in revisiting it when you're coming back at some point, are working optimist, working on a gi at Tesla, I think Tesla is going to do incredible things. It's basically like uh it's a massive large scale robotics kind of company with a ton of in house talent for doing really incredible things and I think uh human robots are going to be amazing. I think autonomous transportation is going to be amazing. All this is happening at Tesla. So I think it's just a really amazing organization. So being part of it and helping it along I think was very, basically enjoyed that a lot. Yeah, it was basically difficult for those reasons because I love the company but you know, I'm happy to potentially at some point come back for Act two. But I felt like at this stage I built the team, it felt autonomous and I became a manager and I wanted to do a lot more technical stuff, I wanted to learn stuff, I want to teach stuff. Uh and uh I just kind of felt like it was a good time for for a change of pace a little bit. </s>

<s>[INST] It takes a brave person, a person of character to not buy in and I'm I'm like a like a baby deer trying to find his legs, you don't have to buy in because I love people and I think I'm kind of an idiot. And so when other people say do this and do that, it uh there's a, there's a pressure there. It's actually very difficult to not listen necessarily to the advice of others and yet keep yourself fragile and open to the world, it's easy to be like, I'm always right, you know, just kind of sticking a ground, but if you want to be like vulnerable, if you want to connect with people and just wear your heart on your sleeve, then you're going to listen to them? I mean that's the double edged sword of it and but then again, that pain, like if you don't let it destroy, you can grow grow from that has fame affected you at all. Did you unplug from the system at some point? [/INST] Same, I've always been sort of removed, I don't feel like I'm part of any system. </s><s>[INST] Do you feel famous? Um [/INST] I'm aware that when I go out, people, you know, say nice things to me, which is great, </s><s>[INST] but [/INST] that's about it, that's about as far as it, </s><s>[INST] but it doesn't affect your art, about your creativity or your thoughts, like when you're sitting alone and thinking about the world, [/INST] it can't it's a destructive force. The the thing, the reason that you're who you are and the reason that you're finding the success you're finding is because you've been true to yourself, to get to that stage. So to start changing that to either conform to someone else's idea of what you should be doing, It just seems like it doesn't make sense. </s><s>[INST] Do you have a sense of who you are? Because I don't necessarily have a [/INST] I don't know, I I know that I really like making good things and I know that I'm crazy about it in that it's like an obsession and I want things to be as good as they could be, whatever it is, and if I'm if I finish a music project and I have a window of time where I'm not working on music, I might be moving the furniture around in the house. You know, I'm always looking for a product, a creative outlet to find a way to make something better. Or there was a period of time where I was in a weird corporate situation that was, that didn't allow me to flourish and I turned, I focused the creativity and on myself and I lost a bunch of weight and changed my life. And so </s><s>[INST] that was the kind of art, like you've gone through the whole process of losing weight, getting in shape, being healthy. That was a kind of creative act. [/INST] It certainly was, it wasn't an intentional creative act, but I had a lot of energy and I just, a series of events happened. I read a book at the time, that was my heaviest. I weighed about £318 and I've never been, I've been sedentary in my whole life, basically laying on a couch, working on music. So I've never been physically active in my life And read a book about a guy named Stu Mittleman, a runner who ran 1000 miles in 11 days. And I thought, Wow, I, you know, get out of breath walking to the corner and another human being can run 1000 miles in 11 days. I feel like I have bad information, you know, I'm doing clearly I'm doing something wrong and, and I reached out to a person that you mentioned in the book, film, Atherton </s><s>[INST] who was a legend, I really appreciate him as well. He's math 1 80 method to, he's such an interesting, I think he focuses on [/INST] heart rate training and he was the first person to talk about essentially paleo keto diet for </s><s>[INST] 40 [/INST] years ago </s><s>[INST] for a person who is going to be healthy, who can exercise and actually perform at an early level. He's the first person when I um, you know, talking about heart rate training him and other endurance athletes, he influenced, he gave me permission to like run [/INST] slower. </s><s>[INST] This is the first time I realized, oh, I can run long distances if I just run slower and and I take that seriously. And I actually fell in love with running very much so because for me, everyone's different. But for me, the love of running happens in the longer distances. [/INST] Did you read Born to run? Great book, </s><s>[INST] Amazing book. There is something special about running and everybody has their own, their own journey with it and even ultra marathon running, those kinds of things. It's, it's a, it is like many journeys, one that can pull you in, like you won't be the same person after. And I, I try to be delivered about making deliberate about making choices after which you will not be the same [/INST] person. </s>

<s>[INST] How much is fast they I of course is free. [/INST] Everything we do is free. We have no revenue sources of any kind, it's just a service to the community </s><s>[INST] years ST okay. Once a person understands the basics, trains a bunch of models. If we look at the scale of years, what advice do you have for someone wanting to eventually become an expert? [/INST] Train lots of models, specifically trained lots of bottles in your domain area. So an expert what? Right. We don't need more expert. Like uh, create slightly evolutionary research in areas that everybody's studying. We need experts at using deep learning to diagnose </s><s>[INST] malaria. [/INST] Or we need experts at using deep learning to analyze language to study media bias or we need experts in, um, um, analyzing fisheries to identify problem areas in the ocean. You know, that that's, that's what we need. So like become the expert in your passion area and this is a tour which you can use just about anything and you'll be able to do that thing better than other people, particularly by combining it with your passion and domain expertise. </s><s>[INST] So that's really interesting. Even if you do want to innovate on transfer learning or active learning, your thought is it means one I certainly share is you also need to find a domain or dataset that you actually really care [/INST] for. If you're not working on a real problem that you understand? How do you know, if you're doing it any good, how do you know, if your results are good, how do you know, if you're getting bad results, why you're getting bad results? Is it a problem with the data? Like how do you know, you're doing anything useful? Yeah. The only to me the only really interesting research is not the only, but the vast majority of interesting research is like try and solve an actual problem and solve it really well. </s><s>[INST] So both understanding sufficient tools on the deep learning side and becoming a domain expert in particular domain, really things within reach before anybody. [/INST] Yeah, I mean to me, I would compare it to like studying self driving cars, having never looked at the car or been in a car or turn the car on, which is like the way it is for a lot of people, they'll study some academic data set where they literally have no idea about that by </s><s>[INST] the way, I'm not sure how familiar with autonomous vehicles, but that is literally you describe a large percentage of robotics folks working self driving cars as they actually haven't consider driving. They haven't actually looked that we're driving, looks like they haven't driven it [/INST] a problem because you know, when you've actually driven, you know, like these are the things that happened to me when I was driving </s><s>[INST] it, there's nothing that beats the real world examples of just experiencing them. You've created many successful startups, what does it take to create a successful startup? [/INST] Same thing is becoming successful, deep learning practitioner, which is not getting up so you can run out of money or run out of time or run out of something, you know, but if you keep costs super low and try and save up some money beforehand. So you can afford to have some time then just sticking with it is one important thing. Doing something you understand and care about is important by something. I don't mean the biggest problem I see with declining people is they do a PhD in deep learning and then they try and commercialize their PhD is a waste of time because that doesn't solve an actual problem. You picked your PhD topic because it was an interesting kind of engineering or math or research exercise. But if you've actually spent time as a recruiter and you know that most of your time was spent sifting through resumes and you know that most of the time you're just looking for certain kinds of things and you can try doing that with a model for a few minutes and see whether it's something which the model is going to do as well as you could, then you're on the right track to creating a start up and then I think just being just be pragmatic and try and stay away from venture capital money as long as possible, preferably forever. </s><s>[INST] So yeah, at that point, do you venture capital. So did you were able to successfully Iran startups with self funded? [/INST] So my first two was self funded and that was the right way to do it. </s><s>[INST] That's scary. [/INST] No species startups are much more scary because you have these people on your back who do this all the time and you have done it for years telling you grow, grow, grow, grow and I don't, I don't care if you fail. They only care if you don't grow fast enough. So that's scary. Where else doing the ones myself well with partners who were friends. It's nice because like we just went along at a pace that made sense and were able to build it to something which was big enough that we never had to work again. But it was not big enough that any VC would, I think it was impressive and that was enough for us to be excited, you know. Uh, so I thought that so much better way to do things that most people </s><s>[INST] generally speaking that for yourself. But how do you make money during that process? Do you cut into savings? So [/INST] Yeah. So for, so I started fast male and optimal decisions at the same time in 1999 With two different friends and for fast mail I guess I spent $70 a month on the server. And when the server ran out of space, I put a payments button on the front page and said if you want more than 10 mega space you have to pay $10 a yeah. </s>

<s>[INST] But those aren't, [/INST] they're not long. The minority of cases. This minority, there is a very rare event. But </s><s>[INST] nevertheless science is an institution, I didn't make corrections in that case. They didn't. So what do you make of that? I mean it's very unfortunate those few things can destroy trust. [/INST] But I don't think that lasts till today. I think today is a different era, right? And most people don't know about those stories and I tell them to you because that's what could happen. I think it could happen today. Um If you look at the history of the polio vaccine, the U. S. Public Health Service wanted kids to be vaccinated. So they did things that probably weren't correct to get the vaccine back online, right? But they did it and they pushed it through. Um So we're to the question is what do we do today? So I can look at as we just said, I can look at what might happen and I can make reasonable decisions about the likelihood of them happening. And I can also say I don't want to get covid of any kind because I've seen how nasty it can be and I decide I'm taking the risk whatever small of of a long term effect I'm going to take the risk. My family took the risk and many other people did vaccine of getting vaccinated because I think it's very small. But I understand where people can't make that decision and that begs the question, what would they need to make a decision. So if you're concerned about An effect in 40 years, We're not gonna know for 40 years. </s><s>[INST] Yeah. So I think if I were to speak because I suppose I talked to like I mentioned offline to joe Rogan and his podcast yesterday, I talked to him all the time about this. I think the concern is less about the uh long term effects. Like on paper, it's more about the the instant. Like um people like Anthony Fauci and people at the top are simply misrepresenting the data or like are are not accurately being transparent, not collecting the data properly, not reporting on the data properly, not being transparent, not representing the uncertainties, not uh openly saying they were wrong two months ago. Like in a way that's not like dramatic but revealing the basic process of science when you have to do your best under uncertainty. Just also just being inauthentic. There's there's a sense especially with like a younger generation now there's a certain way on the internet, like the internet can smell bullshit much better than previous generations. So they they see there's a kind of uh in authenticity that comes with being uh like representing authority. Like I am a scientist. I'm an expert of a PhD have four decades of work therefore everyone should listen to me. And somehow that maps to this feeling of what, what are they hiding if they're speaking from authority like this. If everyone is in agreement like this, that means they all have emails between each other. They said we're going to tell this this is the message. We're going to tell the public then what is the truth? The actual truth? Maybe there's a much bigger uncertainty. Maybe there's dead people in the basement that they're hiding from from bad M RNA vaccine experiments maybe there and then and then the conspiracy theories start to grow naturally when there is this kind of mistrust of the that so it's less about kind of um like a deep concern about long term effects. It's a concern about long term effects. If we find out that there is some secret stuff that we're not being told it all runs on that. So what the heck I mean So I put the blame not on the data but basically on the leaders and the communicators of the science at the top. [/INST] Well to that I would say all the data as far as I know are made public so you can dive into it. And I know a lot of people ask me questions and I just say it's right here in the data and I know a lot of people can't do that. They can't dive into it. But that's one solution for people who are able it's now you could argue well maybe they've left data out. Well then not even I can help because then they're hiding it from me to and I think that's highly unlikely. I think for the most part, the FDA requires the release of all the clinical trial data. Right? </s><s>[INST] So, ok, what? So this clinical trial data? That's one thing. So that's the data that we should be focusing on. Right? So there's there's a lot of different data sets here. [/INST] So there's pre clinical data which is everything that was done in the lab before this vaccine ever went into a human arm. It's all the cell culture work that we talked about. A little experiments in animals. All of that is publicly accessible. Most of it gets published. And then there's the initial drug filing which is huge books of die. You can get that and look at </s><s>[INST] this is the sort of asking sort of difficult questions here. Uh So there is a there's a lot of money to be made by makers the vaccine. So for these companies, obviously there's a distrust of those folks to they've done a lot of really good things in this world. But they there's the incentives are such that you want to sweep stuff under the rug If if you're not 100% pure in your ethics and how hard is it for for that data to be fabricated? Uh manipulated like what's your intuition for the pretrial stuff. [/INST] I think when you when you start fabricating then you get inconsistencies which are pretty easy to pick up </s>

<s>[INST] and I should mention because we haven't that a lot of this calculation from an objective point of view, you have to include the United States and NATO into the pressure they apply into the region that said, I care little about leaders that do cruel things onto the world, they lead to a lot of suffering, but I still believe that the Russian people and the Ukrainian people are great people that stand up and I admire people that stand up and are willing to give their life and I think Russian people are very much um that to especially when the enemy is coming for your home over the hill sometimes standing up to an authoritarian regime is difficult because you don't know, it's not a monster that's attacking your home directly. It's kind of like the boiling of a lobster or something like that. It's a slow control of your mind and the population and our minds get controlled even in the west by the media, by the narratives. It's very difficult to wake up one day and to realize sort of what people call red pilled is to see that there, you know, maybe the thing I've been told all my life is not true and at every level that's the thing very difficult to do in north Korea very in the more authoritarian regime. The more difficult it is to see maybe this idea that I believe that I was willing to die for is actually evil. It's very difficult to do for americans, for Russians, for Ukrainians, for chinese, for indians, for pakistanis, for everybody. [/INST] I think thinking about this Ukrainian, whether you want to call it nobility or intransigence or whatever is key. I think um the authoritarian nous of Russia and Putin's control or the control of his cabal is the other thing I would really point to is what's going on here and if I had to, if you ask me like big picture, what do I think is the fundamental cause of most violence in the world? I think it's unaccountable power. I think in fact for me, an unaccountable power is the source of underdevelopment. It's the source of pain and suffering. It's the source of warfare. It's basically the root source of most of our problems. And in this particular case, it's also one of our buckets in the sense that like, why, what is it that why did Russia asked these things? Like, well, it was democracy in the in Ukraine a threat to an average Russian? No. Was capitalism, is NATO is whatever is this a threat to average Russians? No, it's a threat to the pull the apparatus of political control and economic control that Putin and cronies and this sort of group of people that, that rule this elite in Russia. Um, it was a threat to them. And so they had to ask the Ukraine to be neutral or to give up NATO or to have a puppet government or whatever they were seeking to achieve. And have been trying to achieve through other means for decades, right. They've been trying to undermine these things without uh invasion. And they've been doing that because it threatens their interests. And that's like one of these other logics before. It's not just that there's something that I value so much that I'm willing to injure the cost, it's that there are people not only do does this oligarchy or whatever elite group that you want to talk about in Russia. Not first of all, they're not bearing bearing some costs of war right there very and they're certainly bearing costs of sanctions, but they are, they don't bear all the costs of war, obviously. And so they're more, they're quick to use it. But more importantly, like in some sense, I think there's a strong argument that they had a political incentive to invade or at least to ask Ukraine, this sort of impossible to give up thing and then invade despite Ukrainian nobility intransigence because they were threatened. Um, and so, so that's extremely important I think. And so that's those two things in concert make this a very fragile situation as I think why we ended up is go go not all the way, but a long way to understanding, you know, you could layer on to that these intangible incentives, these other things that are valued that are valued on Putin's side. Maybe there's a nationalist ideal. Maybe he uh seeks status and glory. Like maybe those things are all true and I'm sure they're true to an extent. And and and that'll weigh against his costs of war as well, but fundamentally, I think he just saw his regime as threatened, that's what he cares about. And and so he asked, he made, he made this cruelest of demands. </s>

<s>[INST] although sometimes to push back, sorry to interrupt, [/INST] I've done it to you 1000 times. So you can get me back. </s><s>[INST] Sometimes the deadline you, you know, some of the greatest, like movies and books have been, you think about like dusty Sk I forget which one knows from underground or something. He needed the money. So he had to write it real quick. Sometimes the deadline creates is powerful at taking a creative mind of an artist and just like slapping it around to force some of the good stuff out. Now. The problem with history of course, is there's there's different definitions of good, um, that like, it's not just about what you talk about, which is the storytelling, the richness of the storytelling. And I'm sure you're, you know, again not to compliment you too much, but you're one of the great storytellers of our time. That, that I'm sure if you put in a jail cell and forced at a, like somebody point a gun at you, you could tell one hell of a good story, but you still need the facts of history or not necessarily the facts, but you know, like making sure you painting the right full picture not perfectly [/INST] right. That's what I meant about the audience doesn't understand what a history podcast, you can't just riff and be wrong. So let me let me both both oppose what you just said and back up what you just said? So I have a book that I wrote, right and uh in a book you have a hard deadline, right? So harper Collins had a hard deadline on that book. So when I released it I was mad because I would have worked on it a lot longer, which is my style, right, get it right. But we had a chapter in that book entitled Pandemic Prologue question mark, and it was the book about the part about the black death in the 1918 flu and all that kind of stuff. And and I was just doing an interview with a spanish journalist this morning who said, did you ever think how lucky you got on that on that? You know? And first of all, lucky on a pandemic, it strikes you. But had I had my druthers, I would have kept that book working in my study for months more and the pandemic would have happened. And that episode that would have looked like a chapter I wrote after the fact I would have to rewrite the whole thing, it would've been. So that argues for for what you said at the same time, I I would have spent months more working on it because to me it didn't look the way I wanted it to look yet, you know, </s><s>[INST] can you drop a hint of the things that you're keeping on the shelves, [/INST] the alexander, the great podcast, I've talked around, I talked to somebody today said, do you know that the very first word in your very first podcast in the title? The very first thing that anybody ever saw with hardcore history is the, is the word alexander because the show is entitled Alexandre versus Hitler. I have talked around the career, I've done show after I talked about his mother in one episode, I talked about the funeral games after his death. I've talked around this, I've specifically left this giant alexandria in size hole in the middle because we're going to do that show one day and I'm going to lovingly enjoy talking about this crazily interesting figure of alexander the Great, so that's one of the ones that's on the back pocket list. And what we try to do is whenever this we're doing um Second World War in Asia and the pacific Now, I'm on part five, whenever the heck we finish this, the tendency is to then pick a very different period because we've had it and the audience has had it. Um so it's time. So, um I will eventually get to the alexander saga. </s><s>[INST] What about just one last kind of a little part of this is what about the other half of that first 10 minute, 15 minute episode, which is so you've done quite a bit about the World War, you've done quite a bit about Germany will you ever think about doing Hitler and the man, [/INST] it's funny because uh I talked earlier about how I don't like to go back to the old shows because our standards have changed so much with a long time ago. One of my standards for not getting five hour podcast done or or not getting too deeply into them was to flit around the interesting points, but we didn't realize we were going to get an audience that wanted the actual history. We thought we could just go with assume the audience knew the details and just talk about the weird stuff that only makes up one part of the show now. So we did a show called Nazi Tidbits and it was just little things about, you know, it's totally out of date now, like, you know, you can still buy them, but they are out of date um where we dealt a little with it. Uh you know, it would be interesting, but I'll give you another example, I mean history is not stagnant as you know, uh and we had talked about Stalin earlier and ghosts of the Austrian was done years ago and people will write me from Russia now and say, well your portrayal of Stalin is totally out of out of uh it's outdated because there's all this new stuff from the former soviet union and you do you turn around and go, okay, um there, right, And so when you talk about Hitler, it's very interesting to think about how I would do a Hitler show today versus how I did 1 10 years ago, um and you would think, well, what's new? I mean, it happened so long, but there's lots of new stuff and there's lots of new scholarship and and so, um yeah, I would think that would be an interesting one to do someday. I haven't thought about that, that's not in the back pocket, but uh but yeah, that'd be interesting. </s>

<s>[INST] the mission of the former company is to maximize not profit and maximize benefit for society. Yeah. [/INST] Although there still will be profits. And the profits that we're going to make are going to be used towards the mission of maps, which is again, is this mass mental health and ending the drug war. And and in fact, we've hired the boston consulting group to help us plot our commercialization strategy. And so there is some suggestions based, there's so many different assumptions in this. The number of therapists that we train. The price that we said for the M. D. M. A. Whether insurance companies will cover it. But there's the possibility of somewhere in the range of three quarters of a billion dollars in profits during this period of data. Exclusivity Just from the US and we're talking about trying to do this research around the world as well. So that's what the benefit corporation is. The benefit corporation is, our pharmaceutical arm were about 130 people now, somewhere in that fluctuates, but one third of them are in the non profit. We do harm reduction psychedelic harm reduction. We helped, you know, create programs for people with difficult psychedelic experiences at burning man at festivals all over the world. Even in cities we're now negotiating with the police, the city of Denver because Denver has made the mushrooms the lowest enforcement priority. You know, we Oregon has passed the organ psilocybin initiative. So in those areas where maybe more people are going to gravitate to do psychedelics. We want there to be harm reduction so that we don't have bad stories coming out. That would change that. So maps does the psychedelic harm reduction. We do public education. We do a lot of it. That's what you and I are doing right now. We're doing that now. So </s><s>[INST] but but also research [/INST] towards, well the research now is done in the benefit corp in the benefit or. Yeah. So what happens is people donate to maps get a tax deduction, maps, transfers the money or you could say invests in the benefit corp the benefit corp will do the research and then maps is the sponsor. But then we will license the sale of MD made to the benefit corp So but </s><s>[INST] the research is done with an eye towards creating something that has a big impact versus just research for knowledge sake. [/INST] Yeah. Yeah because um I'm interested in political change. Um You can the other part of it and which is that the brain is the most complex thing we know in the in the universe. It's gonna it's endless. I mean when when are we going to really like this idea of, well we figure out telepathy. Well we figure out tapping into the collective unconscious what what is the extent of our brain, you know? How does the brain actually work? Do you ask chemistry questions? You know? So if if it's just the pursuit of knowledge, that is an endless thing and how does that end the drug war, how does that help people directly. So that's why we're focused on drug development more than mechanism of action. Before </s><s>[INST] I ask you about uh one but several really exciting studies um let me ask sort of a personal question for me. So if I wanted to get psychedelics from the maps public benefit corporation and explore my own mind. Um how do I get to do that? Uh And when [/INST] you won't be able to, you'll never be able to? It's very unfortunate because the reason is because the benefit corp is designed as a pharmaceutical company, so we can only work on clinical indications. So let's say you you come to me and you just say oh I'm really depressed, can I get M. D. M. A. To overcome my depression or overcome my PTSd? You know, we'll have to do research in those indications. Um </s><s>[INST] And by when you say me mean like a doctor. So this would be prescribed in theory by a doctor. So this would go through a doctor and a prescription. Okay, let me uh let me ask another question. [/INST] Well, but to further answer, So that's where the drug policy arm comes in. Drug policy reform. So you should be able to get access to psychedelics for your own personal growth, but that's not medicine. So that's why we need to medicalize to have things covered by insurance, to change people's attitudes, the public attitudes, and then we get this subsequent drug policy reform and and we're talking about it in terms of licensed legalization. So, my view is you should get a license to to psychedelics, you get a little education stuff and then then you should be able to buy it and do it on your own. So </s><s>[INST] let me rephrase the question and more specifically, so when can I if I happen to have um ailments of some kind where the doctor decides that psychedelics could help. When would you be a loose estimate for you of when a doctor will be able to prescribe to me something from uh maps public benefit. Co and then when for my personal growth and creativity would I be able to get something? So like just looking out this isn't like guaranteed. But like your vision your hope um for yeah for psychedelics in society. [/INST] Well the end of 2023 so 2.5 years from now we anticipate FDA approval for the prescription use of M. D. M. A. For PTSD because the FDA does not regulate the practice of medicine. There is what's called off label prescription. What that means the label is what it's approved for. So the labels have this is approved for PTSD. And but let's say you come and anything else social anxiety or whatever you can go to the doctor, they can give it to you. It might not be covered by insurance. They have to be a little bit careful about malpractice if there but I think the end of 2023 is when you will be able to do that. Now there's actually another program very limited called expanded access which is compassionate use Which means that and we have approval for 50 people for compassionate use right now we think that will grow. So that's going to open up in about two months. And so those are people with PTSD they have to be treatment resistant, nothing has worked for them and they can access M. D. M. A. While. We're doing the phase three studies and but they have to pay for it themselves. Were not the sponsors to pay for all the research but expanded access because there's no control group. Everybody gets the M. D. M. A. People can pay for it themselves. And we think that will start in a couple of months but it's very limited. It's limited to certain cities. There's also a program called Right to Try which is um passed through Congress. It's similar this idea of compassionate use but it cuts the FDA out of it and um patients can negotiate directly with pharma companies to get access to their drugs. Um that's starting to happen I think in Canada now they're letting people have compassionate access to psilocybin for life threatening illness because there has been studies with psilocybin for cancer patients and others with life threatening illness. As far as your question about when will you be able to access this for personal growth outside of medicine? I'll take that to mean you know fully legally where you can just go by pure drugs somewhere. When will that happen? You know we already are starting to see the decriminalization in certain areas of plants, psychedelics and we see overall drug dri crim like that passed in Oregon so that any drug is now it's not legal. You can't really fully set up clinics to offer it to people or there's no legal supply like that but it's decriminalized. So my sense of things is based a lot on watching what happened with medical marijuana and marijuana legalization. So we're sitting here in massachusetts where marijuana is legal. But what happened first was medical marijuana. So what we see is that medicalization by demonstrating that under certain contexts that risks are much less than the benefits And then there are benefits. And then people hear stories about people that have gotten better and then that changes their minds and then eventually that builds up to why are we throwing people in jail culture. Yeah. Yeah. So I think that what we're going to have 2023 is M. D. M. A. Um approved by the FDA, chances are psilocybin will be a year to after that. Then what we're going to need is a decade of psychedelic clinics that are going to roll out across America also other countries as well. Thousands of these psychedelic clinics, we already have hundreds of ketamine clinics that are ketamine for depression. Um more and more people are realizing that ketamine when it's used with therapy. It's better than when it's not. Um But the therapists wannabe psychedelic therapists, they don't want to be a ketamine therapist or an M. D. M. A therapist. So there's the cross trained. So we will have a decade of these thousands of psychedelic clinics and all these stories of people getting better in 2035 is when I think that we will move to licensed legalization, which is when you will have the option of just going somewhere once you've done this educational stuff, potentially. I also think it would be better to have the opportunity for people to go for free, paid for by tax money to these clinics. And you have your first experience with psychedelics under supervision And you know what you're getting into, you know, task the questionnaire. What the risks are with the drugs, then you get your license. So 2035. So I think that will happen and the clinics will be sites of these initiations. Yes. </s>

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

<s>[INST] crap? But they didn't, [/INST] they were nowhere to be freaking found. I physically, I I literally witnessed them hiding in cloakrooms, running down hallways away from us. Those freaking cowards. That's </s><s>[INST] cowardice. Can I just linger on the Jon Stewart thing? The comedian, actor Jon Stewart, his testimony before congress over the benefits for 9 11. 1st responders. I mean there's a lot of important human beings in this story, but he has a big voice and he spoke from the heart. What do you make of that testimony? [/INST] Oh, it was heartfelt. I mean he spoke, look, I mean john john was uh, you know, polarizing guy right? There's certain things like over the years, he, he was cutting edge and I might not have agreed with all of his, you know, well, you know, some stuff sometimes, you know, like we all, but, but I'll tell you, I found him as funny. I, I enjoyed this humor. </s><s>[INST] I would love to, to you to have a conversation. [/INST] But again, I love a guy where you can have, you can have a difference in opinions. That's the beautiful thing about the firehouse kitchen. I mean it could get raucous and now I don't know, it's a little different situation, but back in the day, some funny stuff. But yeah, john john literally just took his talents. You would think he was speaking from the heart of a fireman or a cop or soldier or marine or you know someone who was there. But I think he, especially, you got to know Ray so well. And Ray had this stack of mass cards from, you know, the funeral cards they give out, it looks like a, you know, a larger business card that's laminated. And Ray had a stack of them. He would carry around. I think it was close to 100 cards And john saw it. And he said, what's that? He says, these are my cards for what he says for my brother's funerals. He was like, oh my God, you've been to that many funerals. He goes, yeah, this, this is just the ones I made like, like, you know, and john I think was was just stunned. Yeah. And john actually had that stack of cards after after ray past and like said, look, this, look at these, look, there's gonna be more of these cards. We, we have one guy a week or girl, 11 responder or recovery worker or someone who actually resided down there. There's more than one a week dying. It's one a day dying on average. And on average, two people are diagnosed with a 9 11 cancer or disease right now. The worst part is there's autoimmune diseases flying off the graph and you're not covered under the legislation By the grace of God. My cancer is covered if my, if my cancer comes back, I mean, I'm in remission technically incurable, but I'm, I've been blessed them staying ahead of this stuff going on 10 years. But if it comes back with a vengeance tomorrow and takes me at least my, my wife will get my pension and be able to live her life without fear. But my friends who are suffering from these advanced Auto immune, their wives get nothing. Their pension dies with them. And we're hoping that that, you know, john and his army can, can shame these politicians once again to have the kindness and decency to cover these Auto immune, you know, they're throwing a lot of money around that a lot of things lately and this is one that they won't and these are lives in the balance who really need it. </s><s>[INST] And john had this strong line. They did their jobs do yours talking to the [/INST] politicians </s><s>[INST] and it's a strong wake up call that um it's not about the twitter, the social media or all that kind of stuff you have a job to do and you have to, it's that compassion uh implemented in form of money of helping people that were there for you when you needed help. [/INST] Well we had a guy, I mean I might get audited out of this one. We had a congressman from out west. I won't say where but he prided himself on saying he was a retired cop. Yeah busy cop. 22 years. He said no on the legislation. I witnessed a cop who was dying get out of his wheelchair and said hey brother I got a half a million dollars in medical bills and I'm a short timer. I got a few months to live who the f is gonna pay him. Do the right thing. You say you're a cop, you show me you're a cop and you sign that paper and the guy started tearing up the congressman and he signed it but he had to be freaking shamed and you know what he said. Well this doesn't really confront me, this is pork. As far as my district concerned he goes, oh yeah. Do you know there's 10 guys from your district who came across the country to help us that are also dying. He had no idea. He had no idea. And that's the sad part about Alex. There's there's it's a failure in leadership, you know, I mean, I think some people would vote for mickey mouse just because if he ran, I mean, I know offense against mickey mouse, I like him. He's a good guy, right? I mean, but like, like </s><s>[INST] allegedly [/INST] allegedly supposed, Yeah, yeah. You know, but seriously, like I look at, I look at some of the leadership sometimes ago weren't. </s>

<s>[INST] Do you have other worries, like some people like Elon and others have worries of existential threats of artificial intelligence of artificial general intelligence or if you think more narrowly about threats and concerns about more narrow artificial intelligence, like what are your thoughts in this domain? You have concerns are you more optimistic? I think [/INST] You've all in his in his book 21 lessons for the 21st century, his last chapters around meditation. And uh you look at the title of the chapter and you're like, oh it's kind of you know, it's all meditation. But the what was interesting about that chapter is he believes that um you know, kids being born today growing up today, um Google has a stronger sense of their preferences than they do, which you can easily imagine. I can easily imagine today that google probably knows my preferences more than my mother does. Um maybe not me per se, but for someone growing up only knowing the internet only knowing what google is capable of or facebook or twitter or square or any of these things. Um the self awareness is being offloaded to other systems and particularly these these algorithms. And his concern is that we lose that self awareness because the self awareness is now outside of us and it's doing such a better job at helping us direct our decisions around. Should I stand. Should I walk today? Um what doctor should I choose? Who should I date all these things? We're now seeing play out very quickly. So he sees meditation as a tool to build that self awareness and to bring the focus back on why do I make these decisions? Why do I react in this way? Why did I have this thought? Where did that come from? </s><s>[INST] That's the way to regain control. [/INST] Your awareness may be not control but but awareness so that you can be aware that yes, I am offloading this decision to this algorithm that I don't fully understand and can't tell me why it's doing the things that's doing because it's so complex. </s><s>[INST] That's not to say that the algorithm can't be a good thing. And to me recommend our systems. The best of what they can do is to help guide you on a journey of learning new ideas of of learning period. [/INST] It can be a great thing. But do you know you're doing that? Are you aware that you're inviting it to do that to you? I think that's that's the risk he identifies, right? Um is uh that's perfectly okay. But are you aware of that? Do you have that invitation? And it's it's being acted upon. </s><s>[INST] And so that that's your that's a concern. You're kind of highlighting that without a lack of awareness, you can just be like floating at sea. So, awareness is key in in the the future of these artificial intelligence systems. [/INST] The other movie wall e which I think is one of Pixar's best movies besides predatory credit to you. Was you </s><s>[INST] had me until right into [/INST] it. Okay. The tour is </s><s>[INST] incredible. Mm hmm. All right. We've come to the first point where we disagree. Okay, [/INST] see entrepreneurial story in the form of Iraq. </s><s>[INST] Mhm. I just remember just the soundtrack was really good. So excellent. What are your thoughts sticking on artificial intelligence? A little bit about the displacement of jobs? That's another perspective that candidates like Andrew [/INST] yang talk about yang gang </s><s>[INST] forever, yang gang. So he unfortunately speaking of yang gang is recently dropped [/INST] out. It was very disappointing and depressing. </s><s>[INST] Yeah, but on the positive side, he's I think launching a podcast. So uh really cool. Yeah, he just announced that I'm sure he'll try to talk you into trying to come on to the podcast. [/INST] So about predatory. </s><s>[INST] Yeah, maybe he'll be more welcoming of the repertory argument. What are your thoughts on his concerns that the displacement of jobs of automation is that of the of course there's positive impacts that could come from automation and ai but it could also be negative impacts. And within that framework, what are your thoughts about universal basic income? So, these interesting new ideas of how we can empower people in the economy. [/INST] I I think he was 100% right on almost every dimension. Um we see this in squares business. I mean he identified um truck drivers, I'm from Missouri. Um and he certainly pointed to the concern and the issue that people from where I'm from, feel every single day that is often invisible and not talked about enough. The next big one is cashiers, this is where it pertains to Square's business. Um we are seeing more and more of the the point of sale moved to the individual customer's hand in the form of their phone and apps and pre order and order ahead. We're seeing more kiosks, we're seeing more things like amazon go and the number of workers in as a as a cashier and re tos immense and you know there's no real answers on how they transform their skills and work into into something else. And I think that does lead to a lot of really negative ramifications and the important point that he brought up around universal basic income is given that the shift is going to come and given it is going to take time two um set people up with new skills and new careers, they need to have a floor to be able to survive and This $1,000 a month is such a floor um it's not going to incentivize you to quit your job because it's not enough but it will enable you to not have to worry as much about just getting on day to day so that you can focus on what I'm what am I going to do now and what am I going to um what skills do I need to acquire. Um and I think I think you know a lot of people point to the fact that you know during the industrial age we we have the same concerns around automation factory lines and everything worked out okay. But the biggest change is just the the velocity and the centralization of a lot of the things that make this work which is the data um and the algorithms that work on this on this data. I think the second biggest scary thing is just how around ai is just who actually owns the data and who can operate on it. And um are we able to share the insights from the data so that we can also build algorithms that help our needs our help our business or whatnot? So that's where I think regulation could play a strong and positive part. Um First looking at the primitives of AI and the tools we use to build these services that will ultimately touch every single aspect of the human experience and then how data um where data is owned um and how it's how it's shared. Um So those those are the answers that as a society as a world we need to have better answers around which we're currently not, they're just way too centralist into a few very very large companies but I think it was spot on with identifying the problem and proposing solutions that would actually work at least that we learned from that you could expand or evolve. Um But I mean it's I think it's U. B. I. S. Well well past its its do I mean it was certainly trumpeted by martin Luther king and even even before him as well </s>

<s>[INST] are like [/INST] very angry. Uh, you know, only vegetarian or vegan folks because they will tear you apart and try to convert you as much as </s><s>[INST] possible. Did [/INST] you just, did you just </s><s>[INST] point a large number of, of haters onto this very podcast? Is this what just hap no. Is there like several people that were very upset at you right now throwing things? [/INST] No, that's always the joke that I've made because if people have chest dot com and I love all people, but I'm just saying chess dot com patrons do not try to actively convert folks, only chess folks on </s><s>[INST] are like, [/INST] you know, there's a meme chess dot com </s><s>[INST] started, started, [/INST] started somewhere in red unrated anarchy chazz kind of </s><s>[INST] solely chess is a little bit of an anarchist organization. Would you, would you go as far as to say there are terrorist terrorist extremist organization. Are we going there for [/INST] legal reasons. That's uh, I thought leeches has like </s><s>[INST] really good analysis. Somebody does it have an engine for analysis of like games or is that is that an open source thing that like [/INST] They both do? They both use stock fish? 15. </s><s>[INST] Okay. And then the rest is the interface around stock stock fish that shows [/INST] it's tough. It's it's the life. So chest has a live server where you and I can play a game against each other. We just both seek and if we have the same rating, we have the same criteria. We'll play a game. But there's also reviewing your own games, there's an opening database so you can see what the most popular trends are. So leeches is great. Like I'm sponsored by dot com and I will openly say that, but you can't </s><s>[INST] have your deeply biased. [/INST] Yes. But I'm also complementing the competitor but </s><s>[INST] can you play games only chess or is it just for analysis? [/INST] You can So </s><s>[INST] it's the same exact thing. So they're like legitimately competitors, not exactly the same thing, but they have the they're trying to match for features, but you're saying lee chess is more chaotic and then chest dot com is more like professional. [/INST] Yeah. I don't, I don't know. I don't know if it's chaotic. I just know that it's uh, you have to you no one's gonna hold your hand If you, if you go to you absolutely can, you can play games, you can analyze your games but you have to discover yourself. The whole point of dot com is to make the journey as simple as possible. Uh But I also firmly believe you can't have any sort of growth in chess without a chess dot com or a chess 24 </s><s>[INST] What's What's Chess 24. [/INST] So Chess 24 was another live server with some lesson libraries and so on. But they were, I think the process was they were bought by play Magnus. So </s><s>[INST] what's play magnus [/INST] Play magnus? </s><s>[INST] That's magnus Carlsson's [/INST] Yeah, he doesn't own it. He owns some stake in it. I think nine or 10%. They owned a bunch of chess companies including chess 24 but now it seems like they're either merging or basically getting acquired by chess. Dot com. </s><s>[INST] Got it. And then play magnus. It's an app also where you can play magnus at different levels, but there's also the educational [/INST] stuff. </s><s>[INST] Okay. The [/INST] for profit chess companies make the option for grand masters to make a living to make chess in the sport leeches is great. It doesn't put on any events, There's no commentary so you, you can have both in theory and probably some controversy is good. </s><s>[INST] Does chess dot com. Like sponsor you that help you out in some way, Like what's the connection between your videos and streams and so on and chest dot com. Like are they supporting peop [/INST] my content? They don't necessarily, I just make whatever I want. Like I don't have not sense like they do something stupid. I will call out their leadership. It's not like but I too have the logo up like in my Youtube videos or Yeah, it's just </s><s>[INST] that kind of stuff. Yeah. So anyway, back to, I mean that was really helpful. I was confused about all that. Um the guessing people's rating. So the thing you mentioned about the end game, if you don't know what the hell you're doing with the end game, what does that mean about your writing? If you don't know how to finish with just a few pieces on the board. You [/INST] could be my rating. </s><s>[INST] The [/INST] game is tough. </s><s>[INST] That's the self deprecating humor. We tuned in for. Uh [/INST] games are hard man </s><s>[INST] there. You [/INST] can't have, there's a reason magnus is the best because seven hours into a game when everybody's given up, he's still squeezing juice out of the fruit. So that's the way I would describe it. So </s><s>[INST] that's not good source of information. If you [/INST] Know within the 1st 15 moves generally, you can </s><s>[INST] tell [/INST] because you can tell how well they played the opening. So how well they knew what they were supposed to memorize what they were supposed to play and then how they react to piece interactions. So if they are faced with a move that a more advanced player would deal with very swiftly. Because there's kind of a natural response that gives you information if they move their king when they're in check, when they didn't have to. That's a massive giveaway. Some people just think I'm in check so I have to move my king. </s>

<s>[INST] Uh Perhaps he just said it for religious reasons and so on, but in particular sort of a world of interaction without contact. So action at a distance, it didn't make sense to them. On a sort of a human interpretation level doesn't make sense to you, that things can affect other things at a distance. [/INST] It does. But you know that. So that was one of Newton's worries. You're actually right in a slightly different way about the religious worries. He um he was smart enough. This is off the topic, but still fascinating. Newton almost invented chaos theory. As soon as he invented classical mechanics, he realized that in the solar system. So he was able to explain how planets move around the sun. But typically you would describe the orbit of the earth, ignoring the effects of jupiter and Saturn and so forth, just doing the Earth and the sun. He kind of knew, even though he couldn't do the math, that if you included the effects of jupiter and Saturn, the other planets in the solar system would be unstable, like the orbits of the planets would get out of whack. So he thought that God would intervene occasionally to sort of move the planet's back into orbit, which is how the only way you could explain how they were there, presumably forever. But the worries about classical mechanics were a little bit different to worry about gravity in particular, it wasn't worried about classical mechanics were about gravity. How in the world does the earth know that there's something called the sun 93 million miles away that is exerting gravitational force on it. And he said he literally said, you know, I leave that for future generations to think about because I don't know what the answer is and in fact people under emphasize this, but future generations figured it out. Pierre Simone laplace in uh circa 1800 showed that you could rewrite Newtonian gravity as a field theory. So instead of just talking about the force due to gravity, you can talk about the gravitational field or the gravitational potential field and then there's no action at a distance. It's exactly the same theory empirically, it makes exactly the same predictions. But what's happening is instead of the sun just reaching out across the void, there is a gravitational field in between the sun and the earth that obeys an equation Laplace equation cleverly enough, and that tells us exactly what the field does. So even in Newtonian gravity, you don't need action at a distance. Now, what many people say is that Einstein solved this problem because he invented general relativity and in general relativity, there's certainly a field in between the earth and the sun, but also there's the speed of light as a limit in laplace theory, which was exactly Newton's theory, just in a different mathematical language, there could still be instantaneous action across the universe, Whereas in general relativity, if you shake something here, it's gravitational impulse radiates out at the speed of light, and we call that a gravitational wave, and we can detect those. So, but I I really it rubs me the wrong way to think that we should presume the answer should look one way or the other, like, if it turned out that there was action at a distance in physics, and that was the best way to describe things that I would do it that way. It's actually a very deep question, because when we don't know what the right laws of physics are, when we're guessing at them, when we're hypothesizing at what they might be? We are often guided by our intuitions about what they should be. I mean, Einstein famously was very guided by his intuitions and he did not like the idea of action at a distance. We don't know whether he was right or not. It depends on your interpretation of quantum mechanics, and it depends on even how you talk about quantum mechanics within anyone interpretation. </s><s>[INST] So, if you see every forces a field or any other interpretation of action at a distance, he's just stepping back to sort of cave man thinking, do you really? Can you really sort of understand what it means for a force to be a field that's everywhere. So, if you look at gravity, like what do you think [/INST] about? I think so </s><s>[INST] is this something that you've been conditioned by society to think that to map the fact that science is extremely well predictive of something to believing that you actually understand it. Like you can intuitively on the how as the degree that human beings can understand anything that you actually understand it. Are you just trusting the beauty and the power of the predictive power of science [/INST] that depends on what you mean by this idea of truly understanding something, right? You know I mean can I truly understand Fermat's last theorem? You know? It's easy to state it. But do I really appreciate what it means for incredibly large numbers? Right. Um Yeah, I think yes, I think I do understand it but like if you want to just push people on well but your intuition doesn't go to the places where Andrew wiles needed to go to prove Fermat's last theorem and I can say fine. But I still think I understand that the arab and likewise, I think that I do have a pretty good intuitive understanding of fields, pervading space time, whether it's the gravitational field or the electromagnetic field or whatever. The Higgs field. Um Of course one's intuition gets worse and worse as you get trickier in the quantum field theory and all sorts of new phenomena that come up in quantum field theory. So our intuitions aren't perfect. But I think it's also okay to say that our intuitions get trained right? Like you know, I have different intuitions now that I had when I was a baby. That's okay. That's not an intuition is not necessarily intrinsic to who we are. We can we can train it a little bit. </s><s>[INST] So that's where I'm gonna bring in. Noam chomsky for a second who thinks that our cognitive abilities are sort of evolved through time. And so they're they're biologically constrained. And so there's a clear limit as he puts it to our cognitive abilities and it's a very harsh limit. But you actually kind of said something interesting and nature versus nurture thing here is we can train our intuitions to sort of build up the cognitive muscles to be able to understand some of these tricky concept. Do you think there's limits to our understanding that's deeply rooted, hard coded into our biology, that we can't overcome, [/INST] there could be limits to things like our ability to visualize. Okay. But when someone like Ed witten proves a theorem about you know, 100 dimensional mathematical spaces, he's not visualizing it. He's doing the math that doesn't stop them from understanding the result I think. And I would love to understand this better. But my rough feeling which is not very educated is that you know, there's some threshold that one crosses in abstraction. When one becomes kind of like a touring machine, right? One has the ability to contain in one's brain logical formal symbolic structures and manipulate them. And that's a leap that we can make as human beings that dogs and cats haven't made. And once you get there, I'm not sure that there are any limits to our ability to understand the scientific world at all. Maybe there are, there's certainly limits our ability to calculate things, right? You know, people are not very good at taking cube roots of million digit numbers in their head, but that's not an element of understanding is certainly not limited principle. </s><s>[INST] So of course, as a human, you would say that doesn't feel to be a limit to our understanding, but sort of uh have you thought that the universe is actually a lot simpler than it appears to us? And we just will never be able to like it's outside of our Okay, so us our cognitive abilities combined with our mathematical prowess and whatever kind of experimental simulation devices we can put together. Is there limits to that? Is it possible there's limits to that? [/INST] Well, of course it's possible </s><s>[INST] for There are limits that [/INST] is there any good reason to think that we're anywhere close to the limits is </s><s>[INST] a harder [/INST] Question. Look, imagine asking this question 500 years ago to the world's greatest thinkers, right? Like are we approaching the limits of our ability to understand the natural world? And by definition there are questions about the natural world That are most interesting to us that are the ones we don't quite yet understand, right? So there's always we're always faced with these puzzles, we don't yet know and I don't know what they would have said 500 years ago, but they didn't even know about classical mechanics, much less quantum mechanics. So we know that they were nowhere close to how well they could do right? They could do enormously better than they were doing at the time. I see no reason why the same thing isn't true for us today. So of all the worries that keep me awake at night, the human mind's inability to rationally comprehend the world is low on the </s><s>[INST] list. We'll put so one interesting philosophical point. And quantum mechanics bring up is the that you talk about the distinction between the world as it is and the world at as we observe it. So staying at the human level for a second, how big is the gap between what our perception system allows us to see and the world as it is outside our minds? I sort of sort of not at the quantum mechanical level, but as just are these particular tools we have which is a few senses and cognitive abilities to process those senses. [/INST] Well, that last phrase having the cognitive abilities to process them carries a lot. Right? I mean there is our sort of intuitive understanding of the world. You don't need to teach people about gravity for them to know that apples fall from trees, right? That's something that we figure out pretty quickly object permanence, things like that. The three dimensionality of space. Even if we don't have the mathematical language to say that we kind of know that it's true. Um on the other hand, no one opens their eyes and these atoms, right? Or molecules or cells for that matter. Forget about quantum mechanics. So but we got there, we got to understanding that there are atoms and cells using the combination of our senses and our cognitive capacities. So adding the ability of our cognitive capacities to our senses is adding an enormous amount. And I don't think it is a hard and fast boundary. You know if if you believe in cells, if you believe that we understand those and there's no reason you believe we can't believe in quantum mechanics just as well. </s><s>[INST] What to you is the most beautiful idea in physics. Mm hmm, [/INST] conservation of momentum. </s><s>[INST] Can you elaborate? [/INST] Yeah. If you were Aristotle when Aristotle wrote his book on physics, he made the following very obvious point, we're on video here, Right? So people can see this. So if I push the bottle, let me cover this bottle. So we do not have a mess. But okay, I pushed the bottle it moves. And if I stop pushing himself moving. Yes. And this is this kind of thing is repeated a large number of times all over the place. If you don't keep pushing things, they stop moving. This is a indisputably true fact about our everyday environment. Okay, and for Aristotle this blew up into a whole picture of the world in which things had natures and till ecologies and they had places they wanted to be and when you were pushing them, you were moving them away from where they wanted to be and they would return and stuff like that. And it took 1000 years or 1500 years for people to say actually, uh if it weren't for things like dissipation and air resistance and friction and so forth, the natural thing is for things to move forever in a straight line, uh constant velocity, right? Conservation of momentum. And that is the reason why I think that's the most beautiful idea in physics, is because it shifts us from a view of nature's and tilly ology to a view of patterns in the world. So when you were Aristotle you needed to talk a vocabulary of why is this happening? What's the purpose of it? What's the cause, et cetera because, you know, it's nature does or does not want to do that. Whereas once you believe in conservation momentum things just happen. They just follow the pattern. You give me you have laplace demon ultimately right? You give me the state of the world today. I can predict what's going to do in the future, I can predict where it was in the past, it's impersonal and it's also instantaneous, it's not directed towards any future goals. It's just doing what it does given the current state of the universe. I think even more than either classical mechanics or quantum mechanics, that is the profound deep insight that gets modern science off the ground. You don't need natures and purposes and goals. You just need some patterns. </s><s>[INST] So it's the first moment in our understanding of the way the universe works, where you branch from the intuitive physical space to kind of the space of ideas. And also the other point you said, which is conveniently most of the interesting ideas are acting in the moment. You don't need to know the history of time or the future. [/INST] And of course this took a long time to get there, right. I mean, the conservation momentum itself took hundreds of years. It's weird because like someone would say something interesting and then the next interesting thing would be said like 150 or 200 years later, right? They weren't even talking to each other that was reading each other's books. And probably the first person to directly say that in outer space in the vacuum, projectile would move at a constant velocity was of Asana ibn Sina in the Persian golden age circa 1000. And he didn't like the idea he used that just like Schrodinger used Schrodinger's cat to say, surely you don't believe that right. Um even senior was saying, surely you don't believe there really is a vacuum because if there was a really vacuum, things could keep moving forever, right? But still he got right the idea that there was this conservation of something impetus or mile he would call it And uh that's 500 years, 600 600 years before classical mechanics and Isaac Newton. So you know Galileo played a big role in this, but he didn't exactly get it right. And uh so it just takes a long time for this to sink in because it is so against our everyday experience. </s><s>[INST] Do you think it was a big leap, a brave or a difficult leap of sort of math and science to be able to say that momentum is conserved. [/INST] I do you know, I think it's a example of human reason in action. You know, even Aristotle knew that his theory had issues because you could fire an arrow and it would go a long way before it stopped. So if his theory was things just automatically stop what's going on. And he had this elaborate story. I don't know if you've heard this story, but the arrow would push the air in front of it away and the molecules of air would run around the back of the arrow and push it again? Anyone reading this is going really? That's that's what you thought it was, that kind of thought experiment that ultimately got people to say like actually know if it weren't for the air molecules at all, the arrow would just go on by itself, and it's always this give and take between thought and experience. Back and forth. Right theory and experiment, we would say today. </s><s>[INST] Another big question that I think comes up certainly with quantum mechanics is what's the difference between math and physics to you, [/INST] To me very, very roughly, math is about the logical structure of all possible worlds, and physics is about our actual world </s><s>[INST] and it just feels like our actual world is a gray area when you start talking about interpretations of quantum mechanics or no, [/INST] I'm certainly using the word world in the broadest sense, all of reality. So, um I think the reality is specific. I don't think that there's every possible thing going on in reality, I think there are rules, whether it's the schrodinger equation or whatever. So I think, I think that there's a sensible notion of the set of all possible worlds and we live in one of them, the world that we're talking about might be a multiverse might be many worlds of quantum mechanics might be much bigger than the world of everyday experience, but it's still one physically contiguous world in </s><s>[INST] some sense. But so if you look at the overlap of math and physics, it feels like when physics tries to reach for understanding of our world, it uses the tools of math to sort of reach beyond the limit of our current understanding. What do you make of that process of sort of using math to uh you start maybe with intuition or you might start with the math and then build up an intuition or but this kind of reaching into the darkness into the mystery of the world with math. [/INST] Well, I think I would put a little bit differently. I think we we we have theories, theories of the physical world, which we then extrapolate and ask, you know, what do we conclude if we take these seriously? Well beyond where we've actually tested them. It is separately true that math is really, really useful when we construct physical theories and you know, famously Eugene Wagner asked about the unreasonable success of mathematics and physics. I think that's a little bit wrong because anything that could happen, any other theory of physics that wasn't the real world with some other world, you could always describe it mathematically, it's just that might be a mess. The surprising thing is not that math works, but that the math is so simple and easy that you can write it down on a t shirt, right? I mean that's what is amazing. That's an enormous compression of information that seems to be valid in the real world. So that's an interesting fact about our world which maybe we could hope to explain or just take as a brute fact, I don't know, but once you have that, you know, there's this indelible relationship between math and physics, but philosophically, I do want to separate them what we what we extrapolate. We don't extrapolate math because there's a whole bunch of wrong math. You know, that doesn't apply to our world, right? We extrapolate the physical theory that we best think explains our world </s><s>[INST] again. An unanswerable question. Why do you think our world is so easily compressible into beautiful equations? [/INST] Yeah, I mean like I just hinted at, I don't know if there's an answer to that question. There could be </s><s>[INST] what would an answer look [/INST] like? Well, an answer could look like if you showed that there was something about our world that maximize something, you know, the the mean of the simplicity and the powerful nous of the laws of physics or you know what, maybe we're just generic maybe in the set of all possible worlds. This is what the world would look like, right? Like I I don't really know. I I tend to think not, I tend to think that there is something specific and Rock bottom about the facts of our world that don't have further explanation. Like the fact of the world exists at all. And furthermore the specific laws of physics that we have. I think that in some sense we're just gonna at some level we're going to say and that's how it is and you know, we can't explain anything more. We I don't know how if we're anywhere close to that right now, but that seems plausible to me. </s><s>[INST] And speaking of rock bottom. One of the things your book kind of reminded me of reveal to me is that what's fundamental, what's emergent? It just feels like I don't even know anymore what's fundamental in uh in physics. If there's anything it feels like everything especially the quantum mechanics is revealing to us is that most interesting things that I would as a as a limited human would think are fundamental can actually be explained as emergent from the more deeper laws. [/INST] I mean we don't know of course you have to get that on the table. Like we don't know what is fundamental. We do know, we do have reason to say that certain things are more fundamental than others. Right? Um atoms and molecules are more fundamental than cells and organs. Quantum fields are more fundamental than atoms and molecules. Um we don't know if that ever bottoms out. I I do think that there's sensible ways to think about this. The if you if you describe something like this table as a table, it has a height and a width and it's made of a certain material and has a certain solidity and weight and so forth. Um that's a very useful description as far as it goes. There's a whole another description of this table in terms of a whole collection of atoms strung together in certain ways. The language of the atoms is more comprehensive than the language of the table. You could break apart the table, smash it to pieces. Still talk about it as atoms, but you could no longer talk about it as a table. Right? So I think of this comprehensiveness, the domain of validity of the theory gets broader and broader as the theory gets more and more fundamental. </s><s>[INST] So what do you think Newton would say? Maybe write in the book review if you read your latest book on quantum mechanics, something deeply hidden. [/INST] It would take a long time for him to think that any of this was making any sense. </s><s>[INST] You catch him up pretty quick in the beginning. [/INST] Yeah. </s><s>[INST] You give him a shout out [/INST] in the beginning. That's right. I mean he used the man, I'm happy to say that Newton was the greatest scientists who ever lived. Um I mean he invented calculus in his spare time which would have made in the greatest mathematician just all by himself. Right, all by that one thing. But of course, you know, it's funny because Newton was, in some sense, still a pre modern thinker. Rocky Kolb, who is a cosmologist at the University of Chicago said that you know Galileo. Even though he came before Newton was a more modern thinker than Newton was like if you got Galileo and brought him to the present day, you take him six months to catch up and then he'd be in your office telling you why your most recent paper was wrong. Whereas Newton just thought in this kind of more mystical way. You know, he he wrote a lot more about the bible and alchemy than he ever did about physics and uh but he's also more brilliant than anybody else and and way more mathematically astute than Galileo. So I really don't know. You know, he might have, he might just yeah, give me the textbooks, leave me alone for a few months and then be caught up. But he but he might have had mental blocks against against seeing the world in this way, I really don't know </s><s>[INST] or perhaps find an interesting mystical interpretation of quantum mechanics [/INST] very possible. </s><s>[INST] Yeah. Is there any other scientists or philosophers through history that you would like to know? Their opinion of your book? [/INST] That's a that's a good question. Um I mean, Einstein is the obvious one, right? We all. I mean, he was not that long ago, but you can speculate at the end of my book about what his opinion would be. I am curious as to, you know, what about older philosophers like hume or Kant, right? Like what would they have thought or Aristotle? You know, what would they have thought about modern physics? Because they do in philosophy? Your predilections end up playing a much bigger role in your ultimate conclusions because you're not as tied down by what the data is in physics. You know, physics is lucky because we can't stray too far off the reservation as long as we're trying to explain the world that we actually see in our telescopes and microscopes. But it's just not fair to play that game because the people were thinking about didn't know a whole bunch of things that we know right. Like we lived through a lot that they didn't live through. So by the time we got them caught up, they'd be different </s><s>[INST] people. So let me ask a bunch of basic questions. I think it would be interesting, useful for people are not familiar, but even for people who are extremely well familiar. Let's start with, what is quantum mechanics? [/INST] Quantum mechanics is the paradigm of physics that came into being in the early part of the 20th century that replaced classical mechanics and it replaced classical mechanics in a weird way that were still coming to terms with. So in classical mechanics, you have an object that has a location, has a velocity and if you know, the location of velocity of everything in the world, you can say whatever thing is going to do. Quantum mechanics has an aspect of it that is kind of on the same lines. There's something called a quantum state or the wave function and there's an equation governing what the quantum state does. So it's very much like classical mechanics, the wave function is different. It's sort of a wave, it's a vector in a huge dimensional vector space rather than a position and velocity. But okay, that's a detail. And the equation is the schrodinger equation, not Newton's laws, but okay, again, a detail where quantum mechanics really becomes weird and different is that there's a whole nother set of rules in our textbook formulation of quantum mechanics. In addition to saying that there's a quantum state and it evolves in time. And all these new rules have to do with what happens when you look at the system, when you observe it. When you measure it. In classical mechanics, there were no rules about observing, You just look at it and you see what's going on. That, that was it. Right. In quantum mechanics, the way we teach it, there is something profoundly fundamental about the act of measurement or observation and the system dramatically changes its state even though it has a wave function, like the electron in an atom is not orbiting in a circle is sort of spread out in the cloud. When you look at it, you don't see that cloud. When you look at it, it looks like a particle with a location. So it dramatically changes its state right away. And the effects of that change can be instantly seen and what the electron does next. So that's that again, we need to be careful because we don't agree on what quantum mechanics says. So that's why I need to say, like in the textbook view etcetera. Right? But in the textbook view, quantum mechanics, unlike any other theory of physics places, gives a fundamental role to the act of measurement. </s><s>[INST] So maybe even more basic. What is an atom and what is an electron? [/INST] Sure. This all came together, you know, in a few years around the turn of the last century, right around the year 1900 Adams predated then, of course the word Adam goes back to the ancient Greeks. But it was the chemists in the 1800s that really first got experimental evidence for atoms. They realized, you know, that there were two different types of tin oxide and in these two different types of tin oxide, there was exactly twice as much oxygen in one type as the other. And like why is that why is it why is it never 1.5 times as much. Right. And so uh Dalton said, well, it's because there are 10 atoms and oxygen atoms and one form of tin oxide is one atom of tin and one atom of oxygen and the other is one atom of 10 and two atoms of oxygen. And on the basis of this, uh you know, speculation, the theory, right, a hypothesis. But then on the basis of that, you make other predictions. And the chemists became quickly convinced that atoms were real. The physicist took a lot longer to catch on, but eventually they did. And I mean Holzman who believed in atoms, was he had a really tough time his whole life because he worked in Germany where Adams were not popular. They were popular in England, but not in Germany. </s><s>[INST] And they're in general the idea of atoms is it's the most the smallest building block of the universe for for them. That's the kind of how the [/INST] Greek idea. But the chemist in the 1800s jumped the gun a little bit. So these days in Adam is the smallest building blocks of a chemical element, right, hydrogen, 10, oxygen, carbon, whatever. But we know that atoms can be broken up further than that. And that's what physicists discovered in the early 1900s, Rutherford especially and his colleagues. So the atom that we think about now the cartoon is that picture you you've always seen of a little nucleus and the electrons orbiting it like a little solar system and we now know the nucleus is made of protons and neutrons. So The weight of the atom, the masses almost all in its nucleus, protons and neutrons or something like 1800 times as heavy as electrons are, electrons are much lighter. But because they're lighter, they give all the life to the atoms. So when atoms get together combine chemically when electricity flows through a system, it's all the electrons that are doing all the work </s><s>[INST] and where quantum mechanics steps in, as you mentioned with the position of velocity with classical mechanics. And quantum mechanics is modeling the behavior of the electron. I mean you can model the behavior of anything but the electron because that's where the fun is [/INST] the electron was. Was the biggest challenge. Right from the start. Yeah. </s><s>[INST] So what what's the way function you said? It's an interesting detail. But in any interpretation, what is the way function in quantum mechanics? [/INST] Well, you know, we had this idea from Rutherford that Adams look like little solar systems but people very quickly realized that can't possibly be right because if an electron is orbiting in a circle it will give off light. All the light that we have in this room comes from electrons zooming up and down and wiggling. And that's what electromagnetic waves are. And you can calculate how long would it take for the electron to spiral into the nucleus. And the answer is 10 to the -11 seconds. Okay, 100 billions of a second. So that's not right. Meanwhile, people had realized that light, which we understood from the 1800s was a wave had properties that were similar to that of particles. Right. This is Einstein and Planck and stuff like that. So, if something that we agree was a wave had particle like properties, then maybe something we think is a particle. The electron has wavelike properties. Right. And so a bunch of people eventually came to the conclusion. Don't think about the electron is a little point particle orbiting in like a solar system. Think of it as a wave that is spread out. They cleverly gave this the name, the wave function, which is the dopest name in the world for one of the most profound things in the in the in the universe. There's literally, you know, a number at every point in space, which is the value of the electron's wave function at that point. </s><s>[INST] And there's only there's only one way function [/INST] that Yeah, they eventually figured that out. That took longer. But when you have two electrons you do not have a wave function for electron one in a wave function for electron to you have one combined wave function for both of them. And indeed, as you say, there's only one way function for the entire universe at once. </s><s>[INST] And that's where this beautiful dance. Can you say? What is entanglement? It seems one of the most fundamental ideas of quantum [/INST] mechanics. Let's temporarily by into the textbook interpretation of quantum mechanics. And what that says is that this wave function. So it's very small outside the atom. Very big in the atom, basically the wave function, you take it and you square it, you square the number that gives you the probability of observing the system at that location. So if you say that for two electrons there's only one wave function and that wave function gives you the probability of observing both electrons at once doing something. Okay, so maybe the electron can be here or here here here and the other electron can also be there. But we have a wave functions set up where we don't know where either electron is going to be seen, but we know they'll both be seen in the same place. Okay, So we don't know exactly what we're going to see for either electron, but there's entanglement between the two of them. There's a sort of conditional statement. If we see one in one location, then we know the other one is going to be doing a certain thing. So that's a feature of quantum mechanics that is nowhere to be found in classical mechanics and classical mechanics. There's no way I can say, well, I don't know where either one of these particles is, but if I know if I find out where this one is, then I know where the other one is, that just never happens there truly separate. </s><s>[INST] And in general it feels like if you think of a way function like as a dance floor, it seems like entanglement is strongest between things that are dancing together closest. So there's a there's a closeness that's important. Uh [/INST] well that's another that's another step. We have to be careful here because in principle, if you if you're talking about the entanglement of two electrons for example, they can be totally entangled or totally un entangled, no matter where they are in the universe, there's no relationship between the amount of entanglement and the distance between two electrons. But we now know that, you know the reality of our best way of understanding the world is through quantum fields, not through particles. So even the electron, not just gravity and electromagnetism, but even the electrons and the quarks and so forth are really vibrations in quantum fields. So even empty space is full of vibrating quantum fields. And those quantum fields in empty space are entangled with each other in exactly the way you just said, if they're nearby, if you have like two vibrating quantum field that are nearby, then they will be highly entangled. If they're far away they will not be entangled. </s><s>[INST] So what do quantum fields in a vacuum look like empty space? [/INST] Just like empty space? It's as empty as it can be. </s><s>[INST] But there's still a field, it's just it uh what is nothing just like [/INST] here? This location in space? There's a gravitational field which I can detect by dropping </s><s>[INST] something, I [/INST] don't see it, but there it is. </s><s>[INST] So we got a little bit of uh idea of entanglement now, what is Hilbert space and Euclidean space. [/INST] Yeah. You know, I think that people are very welcome to go through their lives not knowing what Hilbert spaces, but if you if you want to dig in a little bit more into quantum mechanics, it becomes necessary. You know the english language was invented long before quantum mechanics or various forms of higher mathematics were invented. So we use the word space to mean different things. Of course most of us think of space as this three dimensional world in which we live right? I mean some of us just think of it as outer space. Okay. But space around us gives us the three dimensional location of things and objects. But mathematicians use any generic abstract collection of elements as a space. Okay. A space of possibilities, you know, momentum space etcetera. So Hilbert space is the space of all possible quantum wave functions. Either for the universe or for some specific system and it could be an infinite dimensional space or it could be just really, really large dimensional but finite. We don't know because we don't know the final theory of everything. But this abstract Hilbert space is really, really, really big and has no immediate connection to the three dimensional space in which we live. </s><s>[INST] What what do dimensions in Hilbert space means? [/INST] You know, it's just a way of mathematically representing how much information is contained in the state of the system. How many numbers do you have to give me to specify what the thing is doing? So in classical mechanics, I give you the location of something by giving you three numbers right up down X, Y Z coordinates. But then I might want to give you its entire state physical state which means both its position and also its velocity. The velocity also has three components. So it's state lives in something called phase space Which is six dimensional 3 dimensions of position three dimensions of velocity. And then if it also has an orientation in space, that's another three dimensions and so forth. So as you describe more and more information about the system, you have an abstract mathematical space that is more and more numbers that you need to give and each one of those numbers corresponds to a dimension in that space. </s><s>[INST] So, in terms of the amount of information, what is entropy, this mystical word that's overused in math and physics but has a very specific meaning in this context, [/INST] sadly it has more than one very specific meeting. This is this is the reason why it is hard. Entropy means different things even to different physicists. But one way of thinking about it is a measure of how much we don't know about the state of a system. Right? So if I have a bottle of water molecules and I know that okay, there's a certain number of water molecules, I could weigh it right and figure out. I know the volume of it and I know the temperature and pressure and things like that. I certainly don't know the exact position and velocity of every water molecule. Right? So there's a certain amount of information. I know certain amount that I don't know that is that is part of the complete state of the system and that's what the entropy characterizes how much unknown information there is the difference between what I do know about the system and its full exact microscopic state. </s><s>[INST] So when we try to describe quantum mechanical system, is it infinite or finite but very [/INST] large. Yeah, we don't know. It depends on the system. You know, it's easy to mathematically write down a system that would have a potentially infinite entropy, an infinite dimensional Hilbert space. So let's let's let's go back a little bit. We said that the Hilbert space was the space in which quantum wave functions lived for different systems that will be different sizes. They could be infinite or finite. So that's the number of numbers, The number of pieces information you could potentially give me about the system. So the bigger Hilbert spaces, the bigger the entropy of that system could be depending on what I know about it. If I don't know anything about it, then has a huge entropy. Right? But only up to the size of its Hilbert space. So we don't know in in the real physical world whether or not, you know, this region of space that contains that water bottle has potentially infinite entropy or just a finite entropy? We have we have different arguments on different sides. </s><s>[INST] So if it's infinite. How do you think about infinity, is this something you can uh your cognitive abilities are able to process or is it just a mathematical tool? [/INST] It's somewhere between. Right? I mean we can say things about it, we can use mathematical tools to manipulate infinity very, very accurately, we can define what we mean. You No, for any number n there's a number bigger than it. So there's no biggest number. Right? So there's something called the total number of all numbers that's infinite. But it is hard to wrap your brain around that. And I think that gives people pause because we talk about infinity as if it's a number, but it has plenty of properties that real numbers don't have. You know, if you multiply infinity by two, you get infinity again, right? That's a little bit different than what we're used to. </s><s>[INST] Okay, but are you comfortable with the idea that in thinking of what the real world actually is, the infinity could be part of that world. Are you comfortable that the world in some dimension? And some [/INST] are comfortable with lots of things? I mean, you know, I I don't want my level of comfort to affect what I think about the world. You know, I'm pretty open minded about what the world could be at a fundamental level. </s><s>[INST] Yeah, but infinity is a is a tricky one. It's not almost a question of comfort. It's a question of uh is it an overreach of our intuition sort of it could be a convenient, almost like when you add a constant to an equation just because it will help. It just feels like it's useful to at least be able to imagine a concept. Not directly, but in some kind of way that this feels like it's a description of the real [/INST] world. Think of it this way, there's only three numbers that are simple, there's zero, there's one and there's infinity a number like 318 is just bizarre like that you need a lot of bits to give me what that number is, but zero and one infinity. Like once you have 300 things, you might as well have infinity things, right? Otherwise you have to say when to stop making the things right? So there's a sense in which infinity is a very natural number of things to exist </s><s>[INST] that was never comfortable with it because it's just such a it was too good to be true because in math it just helps make things work out when things get very, it's when things get very large. Close to infinity things seem to work out nicely. It's kind of like uh because of my, my deepest passion is probably psychology and I'm uncomfortable how in the average the beauty of the very, how much we vary is lost in that same kind of sense. Infinity seems like a convenient way to erase the details. [/INST] But the thing about infinity is it seems to pop up whether we like it or not right? Like you're trying to be a computer scientist. You ask yourself well, how long will it take this program to run? And you realize well for some of them, the answer is infinitely long. It's not because you tried to get there, you wrote a five line computer program. It doesn't halt. </s><s>[INST] So coming back to the textbook definition of quantum mechanics, this idea that I don't think we talked about, can you this one of the most interesting philosophical points. We talked at the human level, but at the at the physics level that at the at least the textbook definition of quantum mechanics separates what is observed and what is real uh one. How does that make you feel? And and uh and to what does it then mean to observe something and why is it different than what is real? [/INST] Yeah. You know, my personal feelings such as it is is that things like measurement and observers and stuff like that are not going to play a fundamental role in the ultimate laws of physics. But my feeling that way is because so far that's where all the evidence has been pointing. I could be wrong. And there's certainly a sense in which it would be infinitely cool if somehow observation or mental computation did play a fundamental role in the in the nature of reality. But I don't think so, and I don't I don't see any evidence for it. So I'm not spending a lot of time worrying about that possibility. So what do you do about the fact that in the textbook interpretation of quantum mechanics, this idea of measurement or or looking at things seems to play an important role. Well you come up with better interpretations of quantum mechanics and there are several alternatives. My favorite is the many worlds interpretation which says two things. Number one, you the observer are just a quantum system like anything else. There's nothing special about you don't get so proud of yourself. You know, you're just a bunch of atoms, you have a wave function, you obey the schrodinger equation like everything else. And number two, when you think you're measuring something or observing something, what's really happening is you're becoming entangled with that thing. So when you think there's a wave function for the electron, it's all spread out but you look at it and you only see it in one location. What's really happening is that there's still the way functionally electron and all those locations. But now it's entangled with the wave function of you in the following way. There's part of the wave function that says the electron was here and you think you saw it there, the electron was there and you think you saw it there, the electron was over there and you think you saw it there, et cetera. So and all of those different parts of the wave function, once they come into being no longer talk to each other, they no longer interact or influence each other. It says if they are separate worlds. So this was the invention of Hugh Everett the third who was a graduate student at Princeton in the 19 fifties. And he said basically, look, you don't need all these extra rules about looking at things. Just listen to what the schrodinger equation is telling you. It's telling you that you have a wave function that you become entangled and that the different versions of you no longer talk to each other. So just accept it. It's just he did therapy more than anything else. You know, he said like it's okay, you know, you don't need all these extra rules. All you need to do is believe the schrodinger equation. The cost is there's a whole bunch of extra worlds out there. </s><s>[INST] So the world is being created, whether there's an observer or not, [/INST] the world has created any time. A quantum system that's in a superposition becomes entangled with the outside world. </s><s>[INST] What's the outside world? [/INST] It depends. Let's back up whatever it really says, what his theory is is there's a way function of the universe and it obeys the schrodinger equation all the time. That's it. That's the full theory right there. Okay. The question all of the work is how in the world do you map that theory onto reality onto what we observe? Right. So part of it is carving up the wave function into these separate worlds, saying, look, look, it describes a whole bunch of things that don't interact with each other that's called them separate worlds. Another part is distinguishing between systems and their environments and the environment is basically all the degrees of freedom. All the things going on in the world that you don't keep track of. So again in the bottle of water, I might keep track of the total amount of water and the volume. I don't keep track of the individual positions and velocities. I don't keep track of all the photons or the air molecules in this room. So that's the outside world. The outside world is all the parts of the universe that you're not keeping track of when you're asking about the behavior of sub sub system of it. </s><s>[INST] So how many worlds are there? [/INST] You want to know that one? Either there could be an infinite number. There could be only a finite number, but it's a big number one way or the other. </s><s>[INST] So it's a very, very big number. In one of the talk, Somebody asked, well if it's a if it's finite. So actually I'm not sure exactly the logic you used to derive this, but is there going to be uh you know, overlap, a duplicate world that you return to. So you've mentioned. And I love that if you can elaborate on sort of idea that it's possible that there's some kind of equilibrium that these splitting world's arrive at and then maybe over time may be somehow connected to entropy. You get a large number of worlds that are very similar to each other. [/INST] Yeah. So this question of whether or not Hilbert space is finite or infinite dimensional is actually secretly connected to gravity and cosmology, Uh this is the part that we're still struggling to understand right now, but we discovered back in 1998 that our universe is accelerating and what that means, if it continues, which we think it probably will, but we're not sure. But if it does, that means there's a horizon around us. There's because the universe is not only expanding but expanding faster and faster. Things can get so far away from us that from our perspective it looks like they're moving away faster than the speed of light. You'll never see them again. So there's literally a horizon around us and that horizon approaches some fixed distance away from us. And you can then argue that within that horizon there's only a finite number of things that can possibly happen. The finite dimensional Hilbert space, in fact, we even have a guest for what the dimensionality is. It's 10 to the power of 10 to the power of 122. That's a very large number. Just to compare the age of the universe is something like 10 of the 14 seconds, 10 of the 17 or 18 seconds, maybe the number of particles in the universe is 10 to the 88. But the number of dimensions of Hilbert spaces, 10 to the 10 to the 122. So that's just crazy baby. If that story is right that in our observable horizon there's only a finite dimensional Hilbert space, then this idea of branching of the wave function of the University of multiple, distinct separate branches has to reach a limit at some time. Once you branch that many times you run out of room in Hilbert space and roughly speaking that corresponds to the universe just expanding and emptying out and cooling off and and entering a phase where it's just empty space, literally forever. </s><s>[INST] What's the difference between splitting and copying? Do you think? Like in terms of a lot of this is uh an interpretation that that helps us sort of model of the world. So perhaps shouldn't be thought of as like, you know philosophically or metaphysically. But even at the physics level, do you see a difference between sort of generating new copies of the world or splitting? [/INST] I think it's better to think of in quantum mechanics in many worlds, the universe splits rather than new copies because people otherwise worry about things like energy conservation and no one who understands quantum mechanics worries about energy conservation because the equation is perfectly clear. But if all you know is that someone told you the universe duplicates, then you have a reasonable worry about where all the energy for that came from. So a preexisting universe splitting into two skinnier universes is a better way of thinking about it. And mathematically it's just like, you know, if you draw an X and Y axis and you draw a vector of length one 45° Angle, you know that you can write that vector of length one as the sum of two vectors pointing along X and Y. Of length one over the square root of two. Okay, so I write one arrow as the sum of two arrows, but there's a conservation of baroness right? Like there's now two arrows, but the length is the same, I just describing it in a different way. And that's exactly what happens when the universe branches the way function of the universe is a big old vector. </s><s>[INST] So to somebody who brings up a question of saying, doesn't this violate the conservation of energy? Can you give further elaboration? [/INST] Right, so let's just be super duper perfectly clear. There's zero question about whether or not many worlds violates conservation energy, it does not. And I say this definitively because there are other questions that I think there's answers to, but they're legitimate questions right? About, you know, where does probability come from? And things like that? This conservation of energy question, we know the answer to it and the answer to it is that energy is conserved. All of the effort goes into how best to translate what the equation unambiguously says into plain english, right? So this idea that there's a universe that has that the universe comes equipped with a thickness and it sort of divides up into thinner pieces, but the total amount of universe is conserved over time is a reasonably good way of putting english words to the underlying mathematics. </s><s>[INST] So one of my favorite things about many worlds is uh I mean I love that there's something controversial in size and for some reason it makes people actually not like upset but just get excited. Why do you think it is a controversial idea? So there's there's a lot of, it's actually one of the cleanest ways to think about quantum mechanics. So why do you think there's a discomfort a little bit amongst certain people? [/INST] Well, I draw the distinction of my book between two different kinds of simplicity in the physical theory. There's simplicity in the theory itself, right? How we describe what's going on according to the theory by its own rights. But then, you know, theory is just some sort of abstract mathematical formalism, you have to map it onto the world somehow. Right? And sometimes like for Newtonian physics, it's pretty obvious like, okay, here is a bottle and has a center of mass and things like that. Sometimes it's a little bit harder with general relativity curvature of space, time is a little bit harder to grasp. Quantum mechanics is very hard to map what you're the language you're talking out of wave functions and things like that on to reality. And many worlds is the version of quantum mechanics, where it is hardest to map on the underlying formalism to reality. So that's where the lack of simplicity comes in, not in the theory, but in how we use the theory to map onto reality. In fact, all of the work in sort of elaborating many worlds, quantum mechanics is in the effort to map it on to the world that we see. So it's perfectly legitimate to be bugged by that right to say like, well, no, that's just too far away from my experience. I am therefore intrinsically skeptical of it. Of course you should give up on that skepticism. If there are no alternatives and this theory always keeps working, then eventually you should overcome your skepticism. But right now there are alternatives that are that people work to make alternatives that are by their nature closer to what we observe directly. </s><s>[INST] Can you describe the alternatives? I don't think we touched on it. So, the Copenhagen interpretation and uh the many worlds, maybe there's a difference between the ever have already in many worlds and many worlds as it is now like has the idea of sort of developed and so on. And just in general, what is the space of promising contenders? We have Democratic debates Now there's a bunch of [/INST] candidates, 12 candidates, </s><s>[INST] 12 candidates on stage. What are the quantum mechanical candidates on stage for the debate. [/INST] So if you had a debate between quantum mechanical contenders, there'll be no problem getting 12 people up there on stage, but there would still be only three front runners and right now the front runners would be Everett hidden variable theories are another one. So the hidden variable theories say that the wave function is real, but there's something in addition to the wave function, the wave function is not everything is part of reality, but it's not everything. What else is there? We're not sure. But then the simplest version of the theory, there are literally particles. So many worlds says that quantum systems are sometimes our wave like in some ways and particle like in another because they really, really are waves, but under certain observational circumstances they look like particles. Whereas hidden variables says they're they look like waves and particles because there are both waves and particles involved in the dynamics. And that's easy to do if your particles are just non relativistic Newtonian particles moving around, they get pushed around by the wave function roughly. Uh It becomes much harder when you take quantum field theory or quantum gravity into account. The other big contender are spontaneous collapse theories. So, in the conventional textbook interpretation, we say, when you look at a quantum system, its wave function collapses and you see it in one location, a spontaneous collapse theory says that </s><s>[INST] every [/INST] particle has a chance per second of having its way functions spontaneously collapse. The chance is very small. For a typical particle, it will take hundreds of millions of years before it happens even once, But in a table or some Macroscopic object, there are way more than 100 million particles and they're all entangled with each other. So when one of them collapses collapses, it brings everything else along with it. There's a slight variation of this, that's a spontaneous collapse theory. There are also induced collapse theories like Roger Penrose thinks that when the gravitational difference between two parts of the wave function becomes too large, the wave functions uh collapses automatically. So those are basically, in my mind the three big alternatives many worlds, which is just, there's a wave function and always a basic schrodinger equation, hidden variables. There's a wave function that always obey the schrodinger equation, but there are also new variables or collapse theories which the wave function sometimes obey the schrodinger equation and sometimes it collapses. So you can see that the alternatives are more complicated in their formalism than many worlds is, but they are closer to our experience. </s><s>[INST] So just this moment of collapse, do you think of it as uh so is it way function fundamentally sort of probabilistic description of the world and its collapse, sort of reducing that part of the world into something deterministic? Where again, you can now describe the position and the velocity in the simple classical model? [/INST] Well, there is </s><s>[INST] how you think about collapse, [/INST] There's 1/4 category is a 4th contender. There's a mayor pete of quantum mechanical interpretations which are called epistemological terp rotations and what they say is all the way function is a way of making predictions for experimental outcomes. It's not mapping onto an element of reality in any real sense. And in fact two different people might have two different way functions for the same physical system because they know different things about it. Right? The wave function is really just a prediction mechanism. And then the problem with those epidemic interpretations is if you say okay, but it's predicting about what like what is the thing that is being predicted and they say no, no, no, that's not what we're here for. We're just here to tell you what the observational outcomes are going to be. </s><s>[INST] But the other the other interpretations kind of think that the way function is real. Yes, [/INST] that's right. So that's an antic interpretation of the wave function, ontology being the study of what is real, what exists as opposed to an epistemological interpretation of the wave function. Epistemology being the study of what we know. </s><s>[INST] Actually just love to see that debate on stage. [/INST] There was a version of it on stage at the World Science Festival a few years ago that you can look up </s><s>[INST] online on Youtube. [/INST] Yeah, it's on </s><s>[INST] Youtube. Okay, awesome. [/INST] I wouldn't </s><s>[INST] get and watch it. [/INST] Many were won by one. I don't know, there was no vote, there was no vote, but those, there's brian Greene was the moderator and David Albert stood up for spontaneous collapse and Shelly Goldstein was there for hidden variables and Rudiger shock was there for epidemic approaches? </s><s>[INST] Why do you, I think you mentioned it but just elaborate. Why do you find many worlds so compelling? [/INST] Well there's two reasons actually. One is like I said it is the simplest right? It's like the most bare bones, austere pure version of quantum mechanics and I am someone who is very willing to put a lot of work into mapping the formalism onto reality. I'm less willing to complicate the formalism itself. But the other big reason is that there's something called modern physics with quantum fields and quantum gravity and holography and space time doing things like that. And when you take any of the other versions of quantum theory, they bring along classical baggage, all of the other versions of quantum mechanics, prejudice or privilege. Some version of classical reality like locations in space. Okay. And I think that that's a barrier to doing better at understanding the theory of everything and understanding quantum gravity in the emergence of spacetime. Whenever if you change your theory from, you know, here's a harmonic oscillator. Oh there's a spin, here's an electromagnetic field in hidden variable theories or dynamical collapse theories you have to start from scratch. You have to say like well what are the hidden variables for this theory or how does it collapse or whatever where as many worlds as plug and play, you tell me the theory and I can give you as many worlds version. So when we have a situation like we have with gravity and spacetime where the classical description seems to break down in a dramatic way, then I think you should start from the most quantum theory that you have, which is really many </s><s>[INST] worlds. So start with the quantum theory and try to build up a model of spacetime, the emergence of space time. Okay, so I thought spacetime was fundamental. [/INST] Yeah. So this </s><s>[INST] sort of dream that Einstein had that everybody had and everybody has of, you know, the theory of everything. So how do we build up from many worlds from quantum mechanics? Uh a model of space time model of gravity? [/INST] Well, yeah, I mean, let me first mention very quickly why we think it's necessary. You know, We've had gravity in the form that Einstein bequeathed it to us for over 100 years now, like 1915 and 1916, he put general relativity in the final form. So gravity is the curvature of space time and there's a field that pervades all the universe that tells us how curved spacetime is </s><s>[INST] and that's a fundamentally classical, [/INST] that's totally classical. Right. Exactly. But we also have a formalism, an algorithm for taking a classical theory and quantum izing it, this is how we get quantum electrodynamics for example and it could be tricky. I mean you think you're quantized something that that means taking a classical theory and promoting it to a quantum mechanical theory, um but you can run into problems. So they ran into problems and they did that with electromagnetism namely that certain quantities were infinity and you don't like infinity. Right? So uh Feinman and Tomonaga and Swinger won the Nobel prize for teaching us how to deal with the infinities. And then ken Wilson wanted another Nobel prize for saying you shouldn't have been worried about those infinities after all. But still, that was the it's always the thought that that's how you will make a good quantum theory. You'll start with a classical theory and quantized it. So, if we have a classical theory, general relativity, we can quantized it or we can try to but we run into even bigger problems with gravity than we ran into with electromagnetism. And so far those problems are insurmountable. We have not been able to get a successful theory of gravity quantum gravity by starting with classical general relativity and quantum izing it. Um and there's evidence that there's a good reason why this is true that the whatever the quantum theory of gravity is, it's not a field theory, it's something that has weird non local features built into it somehow that we don't understand, We get this idea from black holes and Hawking radiation and information conservation and a whole bunch of other ideas I talked about in the book. So if that's true, if the fundamental theory isn't even local in the sense that an ordinary quantum field theory would be that we just don't know where to start in terms of getting a classical precursor and quantized in it. So the only sensible thing, it's at least the next obvious sensible thing to me would be to say, okay, let's just start intrinsically quantum and work backwards, see if we can find a classical limit. </s><s>[INST] So the idea of locality, the fact that locality is not fundamental uh to the nature of our existence sort of, you know, I guess in that sense modeling everything is the field makes sense to me stuff that's close by, interact stuff that's far away doesn't So what's what's locality and why is it not fundamental? And how is that even possible? [/INST] Yeah, I mean, locality is the answer to the question that Isaac Newton was worried about back at the beginning of our conversation, right? I mean how can the earth know what the gravitational field of the sun is? And the answer has spelled out by Laplace and Einstein and others is that there's a field in between and the way a field works? Is that what's happening to the field at this point in space only depends directly on what's happening at points right next to it. But what's happening at those points depends on what's happening right next to those, right? And so you can build up an influence across space through only local interactions, that's what locality means. What happens here is only affected by what's happening right next to it. That's locality. The idea of locality is built into every field theory, including general relativity as a classical theory. It seems to break down when we talk about black holes, and, you know, Hawking taught us in the 1970s that black holes radiate, they give off, they eventually evaporate away. They're not completely black. Once we take quantum mechanics into account, and we think we don't know for sure, but most of us think that if you make a black hole out of certain stuff, then, like La Plaza's Demon taught us, you should be able to predict what that black hole will turn into if it's just obeying the schrodinger equation. And if that's true, uh there are good arguments that can't happen while preserving locality at the same time, it's just that they're, the information seems to be spread out non locally and interesting ways </s><s>[INST] and people should uh you talk about holography with the Leonard Susskind and your mindscape podcast [/INST] podcast. I didn't even mention that. I'm terrible. I'm gonna I'm </s><s>[INST] gonna ask you questions about that too, and I've been not shutting up about, it's my favorite science podcasts or not. It's uh it's not even science podcast, it's like uh it's a scientist doing a [/INST] part. That's right, That's what it is. Absolutely, yes. Uh anyway, so holography is this idea when you have a black hole and black hole is a region of space inside of which gravity is so strong that you can't escape. And there's this weird feature of black holes that again, it's totally a thought experiment feature because we haven't gone and probed any yet. But there seems to be one way of thinking about what happens inside a black hole as seen by an observer who's falling in, which is actually pretty normal, Like everything looks pretty normal until you hit the singularity and you die. But from the point of the view of the outside observer, it seems like all the information that fell in is actually smeared over the horizon in a non local way. And that's puzzling. And that's so holography because that's a two dimensional surface that is encapsulating the whole three dimensional thing. Inside right? Still trying to deal with that. Still trying to figure out how to get there. But it's an indication that we need to think a little more subtly when we quantized gravity </s><s>[INST] because you can describe everything that's going on in the in three dimensional space by looking at the two dimensional projection of it means that locality doesn't it's not necessary. [/INST] Well, it means that somehow it's only a good approximation. It's not really what's going on, how we're supposed to feel about that. I just feel liberated. You know, space is just a good approximation and this was always going to be true once you started quantized gravity. So we're just beginning now to face up to the dramatic implications of quantized gravity. </s><s>[INST] Is there other weird stuff that happens to quantum mechanics in black hole? [/INST] I don't think that anything weird happen with quantum mechanics, that weird things happened with space time. I mean that's what it is, like. Quantum mechanics is still just quantum mechanics, but our ordinary notions of space time don't really quite work. And there's a principle that goes hand in hand with holography called complementarity, which says that um there's no one unique way to describe what's going on inside a black hole. Different observers will have different descriptions, both of which are accurate but sound completely incompatible with each other. So it depends on how you look at it. You know? The word complementarity in this context is borrowed from Niels Bohr who points out you can measure the position or you can measure the momentum, you can't measure both at the same time in quantum mechanics. </s><s>[INST] So, a couple of questions on many worlds, how does many worlds help us understand our particular branch of reality? So okay, that's fine and good, that is everything is splitting, but we're just traveling down a single [/INST] branch of it. So </s><s>[INST] how does it help us understand our little unique [/INST] branch? Yeah, I mean that's a that's a great question, but that's the point is that we didn't invent many worlds because we thought it was cool to have a whole bunch of worlds, right? We invented it because we were trying to account for what we observe here in our world and what we observed here in our world are wave functions collapsing. Okay. We do have a position of a situation where the electron seems to be spread out, but then when we look at it, we don't see it spread out, We see it located somewhere. So what's going on? That's the measurement problem of quantum mechanics. That's what we have to face up to. So many worlds is just a proposed solution to that problem. And the answer is nothing special is happening. It's still just the schrodinger equation, but you have a wave function too. And that's a different answer than would be given in hidden variables or dynamical collapse theories or whatever. So, the entire point of many worlds is to explain what we observe. But it tries to explain what we already have observed, right? It's not trying to be different from what we've observed because that would be something other than quantum mechanics. </s><s>[INST] But, you know, the idea that there's worlds that we didn't observe to keep branching off is kind of is uh you know, it's stimulating to the imagination. So, is it possible to hop from, you mentioned the branches are independent. Uh is it possible to hop from one to the other? It's so it's a physical limit. It the theory says it's impossible. [/INST] There's already a copy of you in the other world. Don't worry, yes. Leave them </s><s>[INST] alone. No, but there's a there's a fear of missing out. Fomo Yes. That I feel like immediately start to wonder if that other copy is having more or less fun. [/INST] So the downside of many worlds is that you're missing out on an enormous, that's always what it's going to be like. </s><s>[INST] And I mean there's a certain stage of acceptance and that in terms of rewinding, you think we can rewind the system back, sort of the nice thing about many worlds I guess is it really emphasizes the, maybe you can correct me, but the determinant, the deterministic nature of a branch and it feels like it could be rewound back. Is it is, do you see, is this something that could be perfectly One back reminded back, [/INST] you know, if you had a fancy french restaurant and there's a nice linen white tablecloth and you have your glass of bordeaux and you knock it over and the wine spills </s><s>[INST] across the tablecloth if the world were [/INST] classical. Okay. Uh it would be possible that if you just lifted the wine glass up, you'd be lucky enough that every molecule of wine would hop back into the glass. Right? But guess what? It's not going to happen in the real world. And the quantum wave function is exactly the same way it is possible in principle to rewind everything. If you start from perfect knowledge of the entire wave function of the universe In practice, it's never going to happen. </s><s>[INST] So time travel. Not possible, [/INST] nope. At least one mechanics has no help. </s><s>[INST] What about memory? Does the universe have a memory of itself or we could in its not time travel but peak back in time and do a little like replay. [/INST] Well, it's exactly the same in quantum mechanics and classical mechanics. So whatever you want to say about that, you know, the fundamental laws of physics in either many worlds, quantum mechanics or Newtonian physics conserve information. So if you have all the information about the quantum state of the world right now in your lap losses demon, like in your knowledge and calculation als capacity, you can wind the clock backward. But none of us is right. And you know, so in practice you can never do that. You can do experiments over and over again. Starting from the same initial conditions for small systems, but once things get to be large avocados number of particles, right, bigger than a cell. Uh no chance. </s><s>[INST] We uh we talked a little bit about era of time last time, but in many worlds that there is a kind of implied era of time. Right? So you've talked about the area of time that has to do with the second law alternative and dynamics, that's the arrow of time that's emergent or fundamental. We don't know. I guess [/INST] it's emergent </s><s>[INST] is that there's everyone agree on that. What [/INST] nobody agrees with everything They </s><s>[INST] so that arrow of time, is that different than the arrow of time that's implied by many worlds. [/INST] It's not different actually. No. In both cases, you have fundamental laws of physics that are completely reversible. If you give me the state of the universe at one moment in time, I can run the clock forward or backward equally well, there's no arrow of time built into the laws of physics at the most fundamental level. But what we do have our special initial conditions 14 billion years ago near the Big Bang. In thermodynamics, those special initial conditions take the form of things were low entropy and entropy has been increasing ever since. Making the universe more disorganized and chaotic. And that's the arrow of time. Uh In quantum mechanics, the special initial conditions take the form of there was only one branch of the wave function and the universe has been branching more and more ever since. </s><s>[INST] Okay, so if time is emergent, so it seems like our human uh cognitive capacity likes to take things that are emergent and assume and feel like they're fundamental. So what is inclusive of times, emergent and locality like space, emergent? Yes. Okay, [/INST] but I didn't say time was emerging. I said the arrow of time was emergent. Those are different. </s><s>[INST] What's the difference between the arrow of time and time are using arrow of time to simply mean the synonymous with the second law of [/INST] thermodynamics. No, but the arrow of time is the difference between the past and future. So there's space but there's no arrow of space. You don't feel that space has to have an arrow, right? You could live in thermodynamic equilibrium, there'll be no arrow of time, but there'd still be time, there'd still be a difference between now and the future or whatever </s><s>[INST] also. Okay, so if nothing changes, there is still [/INST] time. Well, things could even change, like if the whole universe consisted of the earth going around the sun. </s><s>[INST] Okay, [/INST] it would just go in circles or ellipses, right, things would change, but it's not increasing entropy. There's no arrow. If you took a movie of that and I played you the movie backwards, you would never know. </s><s>[INST] So the arrow of time can theoretically point in the other direction for brief briefly. [/INST] So important that it points in different directions, it's not a very good arrow. I mean the arrow of time in the macroscopic world is so powerful that there's just no chance of going back when you get down to tiny systems with only three or four moving parts then entropy can fluctuate up and down. </s><s>[INST] What does it mean for space to be an emergent phenomenon? [/INST] It means that the fundamental description of the world does not include the word space, it will be something like a vector in Hilbert space. Right. And you have to say, well why is there a good approximately description Which involves three dimensional space and stuff inside it. </s><s>[INST] Okay, so time and space are emergent we kind of mentioned in the beginning, Can you elaborate? What do you feel hope is fundamental in our universe? [/INST] Away function living in Hilbert </s><s>[INST] space. Away function Hilbert space that we can't intellectualize or visualize really. [/INST] We can't visualize it, we can intellectualize it very easily. </s><s>[INST] Like well how do you think about [/INST] It's a vector in a 10 to the 10 - 122 dimensional vector space? The complex vector unit norm. It evolves according to Schrodinger equation. </s><s>[INST] Uh When you put it that way, what's so hard? Really? It's like Uh huh, yep, quantum computers, there's some excitement, actually, a lot of excitement with people that it will allow us to simulate quantum mechanical systems. What kind of questions do about quantum mechanics? About the things we've been talking about? Do you think do you hope we can answer through quantum simulation? [/INST] Well, I think that there are there's a whole fascinating frontier of things you can do with quantum computers, both sort of practical things with cryptography or money privacy eavesdropping um sorting things, simulating quantum systems. Right? </s><s>[INST] So it's a it's a broader question. Maybe even outside of quantum computers, some of the theories that we've been talking about, What's your hope? What's most promising to test these theories? What are what are kind of experiments we can conduct, whether in simulation or in the physical world that would validate or disprove or expand these theories. [/INST] Well, I think for theirs too. Parts of that question. One is many worlds and the other one is sort of emergent space time for many worlds. You know, there are experiments on going to test whether or not wave functions spontaneously collapse and if they do then that rules out many worlds and that will be falsified. What if there are hidden variables? There's a theorem that seems to indicate that the predictions will always be the same as many worlds. I'm a little skeptical of this theorem. I'm not completely haven't internalized that. Haven't made it part of my intuitive view of the world yet. So there might be loopholes to that theory. I'm not sure about that. Part of me thinks that there should be different experimental predictions if there are hidden variables, but I'm not sure. But otherwise it's just quantum mechanics all the way down. And so there's there's this cottage industry in science journalism of writing breathless articles that say, you know, quantum mechanics shown to be more astonishing than ever before thought. And really it's the same quantum mechanics we've been doing since 1926. Whereas with the emergent spacetime stuff we know a lot less about what the theory is. It's in a very primitive state. We don't even really have a safely written down respectable, honest theory yet. So there could very well be experimental predictions we just don't know about yet. That is one of the things that we're trying to figure out. </s><s>[INST] But for emergent space time you need a really big stuff. [/INST] Right, well or really fast stuff or really energetic stuff. We don't know that that's the thing, you know. So there could be violations of the speed of light if you have emergent spacetime not going faster than the speed of light, but the speed of light could be different for light of different wavelengths, right? There will be a dramatic violation of physics as we know it. But it could be possible or not. I mean it's not an absolutely prediction. That's that's that's the problem. The theories are just not well developed enough yet to say. </s><s>[INST] Is there anything that quantum mechanics can teach us about human nature or the human mind? Do you think about sort of consciousness and these kinds of topics? Is there it's certainly excessively used as you point out the word quantum is used for everything besides quantum mechanics but in more seriousness, is there something that goes to the human level and can help us understand our mind? [/INST] Not really is the short answer. You know? Um minds are pretty classical. I don't think we don't know this for sure but I don't think that phenomena like entanglement are crucial to have the human mind works. Um </s><s>[INST] What about consciousness? So you mentioned, I think early on in the conversation you said it would be mm I may it would be uh unlikely but incredible if sort of the observers somehow a fundamental [/INST] part of? </s><s>[INST] So observer not to romanticize the notion but seems interlinked to the idea of consciousness. So if consciousness is as the pan cyclists believe is fundamental to the universe, is that possible? Is that wait, I mean every it's possible. Just like just [/INST] like joe Rogan likes to </s><s>[INST] say it's entirely possible, but okay, but is it a spectrum of crazy out there? How uh statistically speaking, how often do you ponder the possibility that consciousness is fundamental or the observer is fundamental [/INST] to personally don't at all. There are people who do. I'm a thorough physical list when it comes to consciousness. I do not think that there are any separate mental states or mental properties. I think they're all emergent, just like space time is and you know, spacetime is hard enough to understand. So the fact that we don't yet understand consciousness is not at all surprising to </s><s>[INST] you, as we mentioned, have an amazing podcast called mindscape. It's as I said, one of my favorite podcast, sort of both for your explanation of physics, which a lot of people of and when you venture out into things that are beyond your expertise. But it's just a really smart person exploring uh even the questions like, you know, uh morality for example, it's very interesting. I think you did a solo episode and so on. I mean there's a lot of really interesting conversations that you have. What are what are some from memory? Amazing conversations that pop to mind that you've had, What did you learn from them? Something that maybe change your mind or just inspired you or just what did this whole experience of having conversations? What stands out to? [/INST] It's an unfair question, Totally unfair. That's okay. That's all right. Um you know, it's often the ones I feel like the ones I do on physics and closely related science or even philosophy ones are like I know this stuff and I'm helping people learn about it, but I learned more from the ones they have nothing to do with physics or philosophy. Right? So talking to Wynton marsalis about jazz or talking to a Master Somalia about wine, talking to Will Wilkinson about partisan polarization and the urban rural divide. Uh talking to psychologists like carol Tavarez about cognitive dissonance and and how those things work. Scott Derrickson, who is the director of the movie Doctor Strange. I had a wonderful conversation with him when we went through the mechanics of making a blockbuster superhero movie, right? And he's also not a naturalist. He's a he's evangelical christians. So we talked about the nature of reality there. Um I want to have a couple more, you know uh discussions with highly educated theorists who know the theology? Uh really well, but I haven't quite arranged those yet? </s><s>[INST] I would love to hear that. I mean that's uh how comfortable are you venturing into questions of religion? [/INST] Uh, I'm totally comfortable doing it. You know, I did talk with Alan Lightman who is also an atheist, but he he is trying to rescue the sort of spiritual side of things for Atheism. And I did talk to very vocal atheists like Alex Rosenberg. So I need to talk to some, I've talked to some religious believers, I need to talk to more. </s><s>[INST] How have you changed through having all these conversations? [/INST] You know, part of the motivation was I had a long stack of books that I hadn't read and I couldn't find time to read them and I figured if I interviewed their authors forces me to read them, right. And that that is totally worked by the way. Now I'm annoyed that people write such long books. I think I'm still very much learning how to be a good interviewer. I think that's a skill that, you know, I I think I have good questions, but you know, there's the give and take that is still, I think I can be better at like I want to offer something to the conversation, but not too much. Right. I've had conversations where I barely talked at all and have conversations where I talked half the time and I think there's a happy medium in between there. </s><s>[INST] So I think I remember listening to without mentioning names, some of your conversations where I wish you would have disagreed more as a listener [/INST] is </s><s>[INST] more fun sometimes. [/INST] Well, that's a very good question because you know, my everyone has an attitude toward that. Like some people are really there to basically give their point of view and their their guest is supposed to, you know, respond accordingly. I want to sort of get my view on the record, but I don't want to dwell on it when I'm talking to someone like David Chalmers who I disagree with a lot. You know, I want to say like, here's why I disagree with you. Um, but you know, I want, we're here to listen to you. Like I have an episode every week and you're only on once a week, right? So I have an upcoming podcast episode with Philip Goff who is much more dedicated pants I kissed and so there we really get into it. I think that I probably have disagreed with him more on that episode than I ever have with another podcast cast, but that's what he wanted. So it worked very well. </s><s>[INST] Yeah, yeah. That kind of debate structure is beautiful when it's done right. Like when you're, when you can detect that the intent is that you have fundamental respect for the person that and that's for some reason it's super fun to listen to, when to really smart people are just arguing and sometimes [/INST] lose their shirt a little bit of family. Say there's a fine line because I have zero interest in bringing. I mean like, I mean maybe maybe you implied this, I have zero interest in bringing on people for whom I don't have any intellectual respect. Like I constantly get requests like you know, bring on a flat earth or whatever and really slap them down or creation is like a zero interest. I'm happy to bring on, you know, a religious person, a believer, but I want someone who is smart and can act in good faith and can talk not a charlatan or a lunatic, right? So I will only, I will happily bring on people with whom I disagree, but only people from whom I think the audience can learn something </s><s>[INST] interesting. So let me ask the idea of Charlton is an interesting idea. You might be more educated on this topic than me, but there's um there's folks for example who argue various aspects of evolution, sort of try to approach and say that evolution sort of our current a theory of evolution has many holes in it, as many flaws and they argue that I think like Cambridge Cambrian explosion, which is like a huge added variability of species doesn't make sense. Under our current description evolution theory of evolution sort of if you were to have the conversation with people like that, how do you know that they're the differences outside the box thinkers and people who are fundamentally unscientific and even bordering on Charlton's, [/INST] that's a great question and you know, the further you get away from my expertise, the harder it is for me to really judge exactly those things. And you know, yeah, I don't have a satisfying answer for that one. So I think the example you use of someone who, you know, believes in the basic structure of natural selection but thinks that, you know, this particular thing cannot be understood in the terms of our current understanding of darwinism. That's a perfect edge case where it's hard to tell, right? And uh, I would have, I would try to talk to people who I do respect and who do know things and I would have to, you know, given that I'm a physicist, I know that physicists will sometimes be too dismissive of alternative points of view. I have to take into account that biologists can also be too dismissive of alternative points of view. So, um, yeah, that's a tricky one. Have you gotten heat yet? He all the time. Like there's always something, I mean, it's it's hilarious because I do have, I try very hard not to like have the same topic several times in a row. I did have like to climate change episodes, but they were from very different perspectives, but I like to mix it up. That's the whole 0.1 having fun. And every time I do an episode, someone says, oh, the person you should really get on to talk about exactly that is this other person. I'm like, I don't but I did that now. I want to do that, </s><s>[INST] wow, I hope you keep doing it. You're inspiring millions of people, your books with your podcast. Sean. It's an honor to talk to you. Thank you so [/INST] much. Thanks very much like. </s>

<s>[INST] So at the that's what you mean, deeply at. We should start at the beginning. So the designer should be also the marketer. The engineer should be the marketer. [/INST] Exactly, stop impressing the geek next to you. What is the superpower you're bringing or the pain you're killing for your the end customer Right now, let's get let's contrast that think about a movie. A movie starts with a treatment. It has an audience that says the audience hears the characters, here's the story line, the plot, here's the here's the here's the arc of the story, right? It pulls that all out. Then there's a script that's written and that script is then produced and then you add all the flourishes and what have you, music and graphics and what have you, right? And then it comes out and then there's the marketing of the movie and that story was created at the beginning. What you need to do if you're going to do a great product is create that treatment for your product and I call that the press release, do the press release like the treatment, who's the audience, what what features do you have? What pains are you solving for people to have the virus of doubt there to remind them what pains they have and why you're solving them the price, all of those things. And you use that as the bar the measuring stick for what you do during development because what happens that along the route, you know this, Oh, we're not gonna be able to get that feature done on time, throw that one overboard, We gotta hit the we have to hit the date. Oh, we're not sure this products right yet. At another feature, add another feature creep. Right? If you don't have that story, you know, you're going to tell at the beginning, you don't have that bar, right? And then at the end, you don't know when you're done. If you don't have the source. So you can actually look at that press release, You might, you know, you change it over time, um that draft, but then when you're done, you know the what and the wise, you have all the things that the audience and everything. And then you can give that to marketing and say, well, marketing has been along the way, let's be clear. But then everybody's in sync and that's when you can tell a cohesive, non fictional story about and the product delivers on that story, or hopefully over delivers on that story. </s><s>[INST] So in the drafting from the beginning to the end of the press release, what is a successful team look like, who's part of the draft? Is it engineers designers, What what's the purpose of a marketing department in the company? Small, let's say small company, but more than two people. So from where does the y come from? Should it always come from the designer? Or should there be a marketing person that Yeah. And and ask the question. So, I'll just keep asking random questions. [/INST] I know these are great questions. So, because you're just like, I'm like, I can't wait to tell you the answer. Um So it's in the book as well, but you have to separate out the various functions of marketing when that's what I thought I was like, marketing is marketing, you know, when I was. And and it's really not. There's so many disciplines just like an engineering, mechanical, electrical software, and even software. It's, you know, use cloud services, firmware applications, marketing has that much diversity as well. Okay. And you have to honor that. And so there is marketing communications, like pr press press. There is um social marketing. There is a marketing creative, right? There's marketing activation. Um But there's another thing that also comes out and people uh confuse it with marketing, which is called product marketing or product management. And product management or product marketing is the voice of the customer. They're the person who sits there and listens to what's going on. And the competition in the marketplace, understanding the needs and those pains of the customer and they're representing them in every single meeting. So things don't get off track, right? So that, Um, and they're creating the messages, not the marketing. What happens is there's messages that product marketing creates. Like those are the deep messages, like we need to save 20% of energy, let's say, right? And then marketing turns that into something that's with creative and everything and brings that message across. Maybe it doesn't say that, but it comes maybe visually or some other way. So product management does that. And and and and holds that press release along the route and making sure that we're tracking. And then also marketing is tracking with that press release to make sure they're not telling a fictional story, right? Because they can also add extra adjectives or something. And then the product can't deliver that. It's like, no, no, no, no, no. Keeps everybody </s><s>[INST] grounded to the press release to the ross and [/INST] right to the customer needs, right? Because they're always representing the customer. So you have to have a product manager typically, that's the founder right in the beginning. And then over time you hire a product management team to then really, you know, watch over this the whole way and they are talking to customer support, they're talking to engineering, they're talking to design, they're talking to sales and marketing and they are always in the mix and it's the hardest thing to hire for. </s><s>[INST] Yeah. So it's they have this very important job of developing and maintaining the why [/INST] exactly why </s><s>[INST] is it the hardest to hire for? [/INST] Because you have to understand first? Nobody reports to you. </s><s>[INST] Right? You [/INST] so you're alone and you have to build great ties with all of these different these different functions. You have to understand what they do have. Be empathetic with what they do. And you have to get have to project the customers empathy or empathy for the customer to them and tell them why and why this customer needs us, why this doesn't work. And so that they learn more. They're not just doing but they learn about the customer's point of view and sit in there and and stand in their shoes to be able to then make better decisions on the engineering details or the operational details, customer support details. So they understand the even if they're not the customer that it's intended for, they start to live through and through their eyes and see through their eyes of that customer. So they make better decisions. </s>

<s>[INST] level, another connection to life. You think dan Bilzerian is telling the truth about having made, what is it? 50 $100 million Just a huge amount of money playing poker, [/INST] considering what I know about the private games And the types of players who play in these private games and the stakes that they play, I absolutely believe, you know Dan has made, I don't know how many millions, but you know whether it's 50 whatever, but it wouldn't surprise me that if you play in these games within a year or you know, you find the right businessman who has way too much Bitcoin money, you know, and you know, in one night you take him for 20 million, I absolutely could see it, I don't see any reason why listen, where he got his money initially, you know that's up to interpretation from his father or whatever, but what has he made a bunch of money playing poker? Absolutely no question, do you feel </s><s>[INST] like as somebody who loves the game, do you think there's something almost ethically wrong in playing people much worse than you. [/INST] So yeah, that's a good question because you know, part of the reason I played poker and wanted to become professional was like, I want to make my mother proud, right? And I don't think she would be proud of me taking like grandma, Betty's like last $5 you know, and get down the street, you know, sending her broke and taking her pension check. So I play at the high stakes against people who can afford it. They know who I am. I'm not a hustler, I'm not pretending I'm bad at poker to squeeze in. Like I was thinking about this just yesterday cause I played in a game that If I played that sort of role where a lot of guys do pros that sort of play down their skill level, pretend they're just one of the guys, these guys can make, $20, $30 million dollars in a year legitimately, like I believe that like if I did that, if I said, you know what, I'm gonna go down that path, get into these games in L. A. You know, and travel and do all this kind of stuff. I can make 20 year, but it feels a little greasy, right? I don't like to kiss anyone's ass. I don't like to ask it for any anyone for a favor or things like that. So, but but yeah, like I, I feel, listen a rich guy who wants to sit down with a million bucks and get drunk and lose it. I have no empathy for that, I'm like, I don't have any moral qualms with that </s><s>[INST] billionaire. [/INST] Send it, send it right, you know? Absolutely </s><s>[INST] not. Um Well, let me ask you about a tough period of your recent life, you had a rough, like we mentioned the world series of poker, um losing $1.1 million 48 days. What were you going through mentally during that? [/INST] So here's the thing, you know, I do, like you said, I do a Youtube vlog every day, so I kind of share my thoughts and listen, I can edit that thing and keep out the bad stuff, but I think it's more authentic and genuine to show people the actual struggles and the pain that I go through, you know, without it. And I'd say the one thing I'm most proud of throughout the entire thing is the resilience because there are moments you see me where I'm broken, just like I can't take it. I broke a selfie stick this year. Like I was filming it because you know, I do for my vlog, I smash the stick through it in the corner, right, It's just, that was my, like hit rock bottom moment and then I put the camera on me and I was like, alright, let people see it, but mentally it was very difficult because there was a feeling of hopelessness where you can, I was making good decisions. Like I genuinely felt like I'm playing really, really well. But every time my money went in, my opponent's money went in and say I was 60% 70% 80% for about a two week stretch. I lost every one of those and you start to wonder like I can't win if I never win, you know, in these spots. So it was difficult, luckily I have you know, 20 odd years of experience and how to deal with it and so as I said, I wake up the next day ready to go, </s><s>[INST] happened to [/INST] A certain degree. Obviously you know, the more the more it happens in the higher binds like the one where I broke the selfie stick, I lost 500,000 in that tournament right? It was like the last card. It was painful. </s><s>[INST] I think you lost [/INST] video. I think he lost </s><s>[INST] what led up to the selfies, that gate, like what? You just lost your ship for a like 100 milliseconds. Like it was very brief, you're just like what the world wasn't making any sense. Like how mike do I keep losing kind of thing. How did you, why did you lose your ship? [/INST] You should never really think like this. But part of me felt like I deserved to win this right? So part of me was like, listen, I've lost so many in the last two weeks. Alright, let you know the poker gods be kind to me right now, let me win this and it looked good. I was in a great situation on the flop, Great situation on the turn. I'm about to be a competitor. I'm gonna be a contender in this tournament to win a big prize pool and turn the whole thing around. It's all there for the taking and then boom, the last card, it just, you know, it was a couple of weeks of frustration in the moment of filming that I just had, you know, sort of a visceral reaction, you know, and I smacked, smacked the selfie stick and then like I it was, I see a corner safe through the selfie stick on the ground. And of course social media blows up about how, how, you know, it was a violent </s>

<s>[INST] my studio space. Well, if the cameras hold up, it will be one heck of a show, hopefully, of course, would not happen. How does that take us to an orbital launch? [/INST] When do you think that would happen? </s><s>[INST] In my opinion, this is a very fluid and this will change literally by the hour. You really think that it's very difficult to really say, even for something that could very well happen this year, even just a few months away, you should be making a prediction. By the way, you're superstitious on this kind of stuff a little bit, you're worried about jinxing it and that kind of stuff. I would imagine you would be waiting for all of these launches that keep getting delayed where you start thinking that there's certain things you do will control the weather. My socks. [/INST] Why am I wearing these socks? Why am I wearing these socks? </s><s>[INST] I just scrubbed again. [/INST] You have to wear the same lucky socks, otherwise there's going to be bad weather. The reason that I say this and why it's so difficult is they did a first full stack test in July of 2021 and the expectation was we're a month or two away from a launch. Realistically for 18 months, I've been in a purgatory thinking that we're a month or two away of an orbital launch. Now, I did say, for the record, when that thing stacked and when a lot of speculation was saying a month or two, I was saying, I don't expect it to fly in 2021. I just saw the amount of work that still needed to be done on the ground systems, the tanks, the launch mount, all the stuff. I'm sitting there like, there's still a lot of stuff. They're going to have to validate it. They're going to have to test everything, every component. People were like, how dare you say that even Gwen Shotwell, the president of SpaceX, is saying Q3 of 2020. I'm like, okay, but I'm not going to be surprised if it slips into 2022. Here we are at the beginning of 2023 and I think we're finally within two months. I'm expecting, I'm trying to keep my March and April as free as I can. </s><s>[INST] We'll put it that way. I love it. Actually, just on a small tangent on Gwen Shotwell, what do you, from everything I know, she's an instrumental, a really crucial person to the success of SpaceX in running the show. She's the president, the COO. What do you know about her that, the genius of Gwen Shotwell? [/INST] Man, my understanding is she's really the glue. She's the glue to the tornado. Tornado comes in and then she comes around and just really executes on, and helps. A famous story is that at some point, Elon walked in, or she sprinted into a meeting because Elon was actively trying to cancel Falcon Heavy, saying it's too far, like it's too much development. It's still too far away. This might've been end of 2017 or something and it flew for the first time in 2018. We're talking it's close to the end of development. There's hardware being built, all this stuff, and Elon's literally in a meeting telling people they're going to cancel it and we're going to move on to BFR, or now Starship, and just go full steam ahead on that. She runs into the meeting and reminds Elon, we have X amount of customers have already purchased a ride on Falcon Heavy. We can't delay that. It's that business sense of like, yes, it's great to innovate, but we also have to pay our dues and make the money to continue our operations. I think she's just a lot better at... I think she has such a great perspective on everything. It really seems like everything... I wish she did more interviews because I would love to hear more from her, but man, it just seems like... </s><s>[INST] Hear that Gwen? Man, it just seems like... Hear that Gwen? For both of us? [/INST] Yeah, she hasn't actually done them in interviews, right? Not really, no. I mean, Ted Talk, a couple of little things here and there, but not really many interviews. I would just love to hear what, on a daily basis, what is she doing to keep her head on and keep everything so organized? My understanding is that she is absolutely integral and does just an insane amount of </s><s>[INST] work at SpaceX. Yeah. It's the project planning, but also how the teams integrate together and the hiring, and [/INST] this is the management of the whole thing. I think it's a lot of it. Honestly, even just the business, making sure the money is flowing in a positive trend, more or less. Yes, Elon is obviously a money guy, but he thinks... I think Elon is so risky. He just loves to throw it all in that he leaves little margin for error. He's been really lucky with rolling his dice. especially like when he started SpaceX and Tesla, that was the ultimate roll of the dice. But I think she's a healthy balance to be like, well, here's our operations and now we can continue to do this without risking everything. And Starship's close, let me be clear, Starship is close to risking everything already. It's just such a big, fast-moving, high-risk developmental program that like, I personally think SpaceX would probably be fine if they shut the doors on Starship and just flew Falcon 9 and Falcon Heavy for the next 10 years, they would still be commercially valid. They could not spend another dollar on research and development. They could fire, I don't want them to, fire everyone involved in anything research and development and just ran operations on Falcon 9 and Falcon Heavy and they would still be dominant for 10 years, and they would still have a business case and they'd still be fine. But they're all in like, all chips are pretty much as many chips as possible are in. For </s>

<s>[INST] So now on the topic of interaction of computational systems with biology. So if you look at a company like neuralink or the whole effort of brain computer interfaces now there's a neurosurgery component there. We have to connect electrical systems with biological systems. Uh So just even the implanting is is difficult. Um Then the communication is difficult. But what would you say from what you know about the brain? What you know about the human body and all the the beautiful mess that's there. How difficult is the effort of neural link? Do you think it's feasible? [/INST] I think it's it's definitely feasible. I think that we need to probably no more than we do. Um And and know how to connect it. You know in all these ways. I think some advances for instance um you know much less sexy but really already impacting medical care is something called deep brain stimulation which is done for Parkinson's disease and others where neurosurgeons implant this this device that electrically stimulates the part of the brain um that is not functioning in Parkinson's disease. And it's quite dramatic how effective it works. And I remember as a med student watching a neurologist literally like turn the electricity up on this handheld thing and you could see the person's Parkinson tremor go away and you could see them start to walk in a more steady fashion. Um And I know there's studies there's actually studies or there may be studies in the future studying the same deep brain stimulation for everything from eating disorders to severe oh like severe O. C. D. Like paralyzing O. C. D. Not just like I want to wash my hands three times. But um and so I think the you know the potential is there but I guess connecting the brain in a microscopic way in sort of a multifaceted way. You know there needs to be sort of a million connections or some some very high number of connections for them to work fluidly as far as I know I'm not an expert in the area. </s><s>[INST] First of all I believe and I trust in the adaptability of the biological system to whatever crazy stuff you try to shove in there so it's going to potentially reject things but it's also going to if it doesn't reject things adapt and if we can create computational systems that also adapt ai systems that adapt and can kind of both of them reach towards each other and figure stuff out. But actually our current ai systems are not very adaptable to the what like in the wild way that biology is adaptable adaptable to anything and if we can build a i systems like that I feel like there's some interesting things you can do but of course there's ethics and there's real human lives at stake and there you can't quite experiment. You have to have things that work and maybe simulation can help but reality is it's a, it's a dangerous playground to play on, it's [/INST] messy. </s><s>[INST] You tweeted that quote, if you look back from far enough into the future, every doctor today will look like a total quack. Um yeah, first of all that's humbling to think about like we don't know what we're doing in the great, like there's been so much progress that we kind of have this confidence that we figured it all [/INST] out. If </s><s>[INST] you look at history and you read how people thought, I mean there's so many moments in history where people really thought that they figured it all out. It's almost like there's nothing else left to do at every stage in history. And uh, and then you realize no progress often happens like exponentially and every moment you continue to think you figured it all out. But if you're being [/INST] honest, </s><s>[INST] if you're being humble and you realize we're just shrouded in mystery. So what do we make of this? Like, how should we feel that? How should you feel as a doctor? How should we feel as scientific explorers of the human body? The fact that we're probably going to be wrong about everything we currently know, [/INST] right? There's a saying actually, by the time you finish med school, half of what you learned is wrong, um, which is quite illustrative and becoming more true as time goes on. You know, so much medical research going on, so much learning going on. It's really wonderful in a way. But in some ways we still learn these concepts, you know from the past. And I know when you take a test as a medical student sometimes, you know, they want to ask you, they they want you to give the old answer. But you know, there's a new answer because of recent science, but you know, to give the old answer that's now incorrect to get the question right on the test, that happens actually quite a bit because things change so quickly. Um yeah, you know, when I look back at doctors from centuries past, I mean it's absurd what they were doing to their patients. I mean probably for most of human history they were doing more harm than good. You know, they're draining people of their blood. Uh that was, you know, bloodletting was a huge part of of medical care. You know. Um George Washington died of a parent counselor abscess. An abscess right next to the Tunsil, which has the great name of Quincy and they bled him to death. You know, I mean kind of adding insult to injury. Doctors are a menace and do a lot of harm. I mean, hopefully not intentionally. You know, even medical errors are still a huge problem cause of death and morbidity. So we do a lot of things that are not great, but you know, our knowledge. Yes, it's it's very imperfect at this point, I do have some confidence, you know, I guess, perfect scientific studies that try to get at the reality of the universe are essential. Because when I think of why a certain medication works for a certain condition, it might make perfect sense in my head knowing the biology, the biochemistry, the anatomy. It makes perfect sense. It must work. I gave it to the patient, they got better and that's happened 20 times in the last year. But it's, you know, I'm wrong. Like when you actually do a study, it actually doesn't help. Maybe it hurts. Um And that's really, I think the way we explain medications working in our minds is often wrong when you end up finally doing the the study and some of the most interesting experiments um involve what we call sham surgery. So for instance, people who injured their knee, you know, arthroscopy where an orthopedic surgeon goes in there with a scope, gets bits of bone out, shaves down the cartilage, you know, cleans things up and it helps some people. But they actually did some studies where one group of people got the true arthroscopy and others just got sham surgery where they put them to sleep, made little cuts in the skin. So they woke up with scars. Um And then it turned out that it's not clear arthroscopy is actually helping. Um And the same. There was a recent huge um study of doing, putting a stent in someone's coronary arteries if they have stable chest pain, not like I'm having a heart attack, you need a stent, like, right then, but, you know, kind of chronic coronary artery disease, where every time I run up the stairs, I get chest pain, and then when I rest it goes away, like, obviously, you put a stent, you increased blood flow to the heart. Like, how could that not work? But then when they did this sham catheterization, it actually looks like it might not actually help better than the sham. So, I think those placebo controlled studies are essential. I mean, it is shocking. And this has been driven home during the last two years. How hard it is to figure out what the hell is going on in the universe. And with especially with our bodies, like, it is really hard to get at the truth and what you think makes sense. Like often turns out, I mean, his the history of modern medicine is littered with examples where it made perfect sense, and it seemed to help some patients, and it turns out it's not doing anything or it's harmful. </s>

<s>[INST] You know, they're kinda thinking ahead, I guess. Well, what about also just imagine a world where India and China doing fentanyl trade with Mexico or whatever transport. Imagine Chinese military moves, makes an agreement, [/INST] a NATO type of agreement with Mexico. That's pretty possible. Again, we're seeing militarized Mexico. It's another aspect of Mexico that, again, I haven't seen talked about a lot here in the US. The main promise that the current president had was he was gonna make the police, the federal police and the security issues in Mexico civilian. He was gonna do exactly the opposite as his main rival, Felipe Calderon, the guy that started off the drug war officially. And what does he do? He dissolves the civilian leadership of the federal police, dissolves the federal police, creates the National Guard, which is a military unit, and he puts the military in charge of that. Now the military has a full monopoly over all federal policing. When you cross into Mexico, you'll see them wearing these white camouflage uniforms. Those are National Guard people, but they're the military. So now you're seeing a militarized Mexico with some of these leaks that happened during the Wakamaya leaks. You're now seeing that Mexico has been hosting members of the Haitian military, and they've been training them up to go back to police their country. That's not something that Mexico has been known for hosting other nations and then training them in such a way. So, it's an interesting maneuver. Mexico has been historically neutral about getting involved in foreign conflicts, about voting in resolutions as far as invading or not invading or doing all these things. Mexico has been historically kind of neutral as it comes to some of these things. And now we're training foreign military forces to go and do that role somewhere else. We have the military building airports and building infrastructure in Mexico, and a lot of their higher-ups getting very wealthy around it. And they basically have a monopoly over who gets to have guns down there. There's one gun store in all of Mexico, and it's run by the military. And the only way you can buy a gun there is if you can buy a plane ticket to fly there and have enough money to sustain that right for that privilege. So you're seeing the military not being in its traditional role of just being the security force. Now it's policing. It's involved in, it's getting involved in politics in a big way. It's legislation that has passed to keep it on the streets in a policing role for more years now. So it should be looked at closer by anybody observing it from afar, the militarization of Mexico </s><s>[INST] and where it's going by the military. Because if you move towards a world where a World War III happens, it feels like Mexico will be the center. Because a hot war would be fought on the ground. And so you have a very difficult parallel between Mexico and Ukraine. Both don't have nuclear weapons. Both have relationships. So Ukraine has a relationship, or a pull towards the European Union and NATO. Mexico, at least currently, has a kind of slow pull towards China, India potentially, and Russia. And you have this divide between power centers in the world. And in terms of, just imagine hundreds of thousands of Mexican troops, hundreds of thousands of Chinese troops on the border, on the US border. Yeah. [/INST] On the Mexican side. And also the fact that that border doesn't mean anything to any sort of conflict that would happen regionally. Because that's a very easy to cross border. Doesn't matter how many walls you put across it. People are already here. This is not gonna be a war fought off in some overseas place. Like you're not gonna, this is something if it happens, if destabilization is utilized in Mexico to cause a conflict there. And it turns into a Vietnam, or a proxy war down there of a sort. Which I think in a way, you're already kind of seeing some of that through some of the conflicts going on down there. You have a new generation cartel that is being fed fentanyl from the Pacific side ports. And suspiciously, you wanna think that maybe it's favored by a foreign government of some sort in some way, shape or form, who knows. And then you have a historically in control seen in law cartel that may or may not be favored by the US in some way, shape or form. You can imagine a further conflict down there and people fostering it. And seeing the effects of basically setting a fire on the feet of the United States. Its second largest consumer of US products is Mexico. The massive wave of immigration that is going to be basically weaponized. You saw the collapse of the border security structure with a contingent of 3,000 Honduran, Guatemalan immigrants in that first wave of caravans coming to Tijuana. You saw, it was pretty bad. It was pretty bad and it could have gotten worse. Now what is gonna happen when that wave is no longer 3,000, but a million people being displaced by violence or being in fear of whatever conflict might originate down there. And just that massive wave of migration and move. I think that's an interesting thing that people should look at and how can you affect change </s><s>[INST] to try and stop some of these things that happen. Well, let me ask you at a philosophical, at a human level, what do you think about immigration? Illegal and illegal immigration from the direction of Mexico to the United States. So we have an estimated 11 million illegal immigrants in the United States and estimated 45 million legal immigrants in the United States. [/INST] A few things about that. When COVID hit, there was no shortages of produce in the supermarkets, which means that, I mean, illegal immigration is pretty much the backbone of all produce and some of the farming industries out there, most of it. So illegal immigration and illegal workers in those fields are essential workers in a way. And I think there's a weird relationship in the United States with some of these workers and how they're demonized and how they're called criminals. I think there was a state out there that passed anti-illegal immigrant worker legislation. The farmers had to look elsewhere for people to show up to work in some of these fields, which basically caused millions of dollars worth of losses for some of these farms. So anywhere you go out there in the United States, you go into the kitchens and there's gonna be paisano's there, high-level French restaurants. You'll see people from Puebla there that made their way legally and might have legalized or regularized their way into the country or in a sanctuary city. You go to the service industry, hotels, those are the people changing the blankets. Those are the people in the washrooms. You have them doing jobs that no American wants to do, realistically, and they're everywhere in this country. And they are the backbone of some of these industries that are essential in this country. </s>

<s>[INST] minimize the white space. [/INST] Um Yeah, well to maximize the amount that I can see at once. Right? So I like to be able to see a whole function and to understand what it does rather than have to go scroll, scroll, scroll and remember, </s><s>[INST] yeah, I'm with you on that and people don't like that. [/INST] Yeah, I've had I've had, you know, multiple times when engineering teams have uh staged what was effectively an intervention, um you know, where they invite me to a meeting and everybody has arrived before me and they sort of all look at me and say James about your coding style. I'm sort of an odd person to be programming because I don't think very well verbally. Um I am just naturally a slow reader. Um I'm what most people would call a visual thinker. </s><s>[INST] So when you think about a program, what do you see? [/INST] I see pictures, Right. So when I look at a piece of code on the piece of paper, it very quickly gets transformed into a picture. Um and you know, it's almost like a piece of machinery with, you know, this connected to that and these gears. Yeah, yeah, I see them more like that than I see the the sort of verbal structure or the lexical structure of letters </s><s>[INST] so that when you look at the program, that's why you want to see it all in the same place, then you can just map it to something visual, [/INST] Yeah, just kind of like, it leaps off the page at me and </s><s>[INST] yeah. What are the inputs, where the outputs? What the heck is this thing doing? Getting a whole vision of it? Can we are go back into your memory, memory, long term memory access. What's the first program you've ever written? [/INST] I have no idea what the first one was. I mean I I know the first machine that I learned that I learned to program on, what is it was a PDP eight um at the University of Calgary, </s><s>[INST] remember the specs? [/INST] Oh yeah, so so the thing had four K of RAM nice 12 bit words. The clock rate was um it was about a third of a megahertz. </s><s>[INST] So you even get to the, to the m [/INST] okay. Yeah. Yeah. So you know, we're we're like 10,000 times faster these days. </s><s>[INST] Um It was this kind of like a supercomputer, like a serious computer for [/INST] no, the PDP eight, I was the the first thing that people were calling, like mini computer got it. They were inexpensive enough that a university lab could maybe afford to buy one. </s><s>[INST] It was their time sharing, all that kind of stuff. [/INST] Um There there actually was a time sharing, No s for that, but it wasn't used really widely. The machine that I learned on was one that was kind of hidden in a back corner of the, of the computer center and it was it was bought as a as part of a project to do computer networking. Um but mhm. You know, they didn't actually use it very much. It was mostly just kind of sitting there and it was kind of sitting there and I noticed it was just kind of sitting there and so I started fooling around with it and nobody seemed to mind. So I just kept doing that and </s><s>[INST] I had a keyboard and like a monitor or [/INST] oh this is way before monitors were common. So it was it was literally a model 33 teletype. Okay with a paper tape </s><s>[INST] reader. Okay, so the user interface wasn't very good. [/INST] Yeah. Yeah, it was it was the first computer ever built with integrated circuits, but by integrated circuits, I mean that they would have like 10 or 12 transistors on one piece of silicon, not the 10 or 12 billion for the machines have today. </s><s>[INST] So what did that I mean, I feel like if you remember those, I mean did you have kind of inklings of the magic of exponential kind of improvement of moore's law of the potential of the future. That was that [/INST] your fingertips kind of thing. I was just a cool. Yeah, it was just a toy. You know, I had always liked building stuff but one of the problems with building stuff is that you need to have parts, you know, you need to have pieces of wood or wire or switches or stuff like that and that was all cost money </s><s>[INST] and here you could build [/INST] you could build arbitrarily complicated things and I didn't need any physical materials um It required no money. </s><s>[INST] That's a good way to put programming, you're right, it's a if you love building things that uh yeah completely accessible, you don't need anything anybody from any work, you just build something really cool. [/INST] Yeah yeah if you've got access to a computer you can you can build all kinds of crazy stuff. Um and you know and when you were </s><s>[INST] somebody [/INST] like me who had like really no money um and I mean I I remember just lusting after being able to buy like a transistor. Mhm. Um You know and when I would do sort of electronics kind of projects they were mostly made done by like dumpster diving for trash, you know and you know one of my big halls was uh discarded relay racks from the back of a the phone company switching center. </s><s>[INST] That was the big memorable treasure. [/INST] Oh yeah yeah that </s><s>[INST] was what do you use that [/INST] for? I built a machine that played tic tac toe. </s><s>[INST] Uh huh. [/INST] Out of relays of course the thing that was really hard um was that all the relays required a specific voltage but getting a power supply that will would do that voltage was pretty hard and since I had a bunch of trashed television sets, I had to um sort of cobbled together something that was wrong but worked. Um So I was actually running these relays at 300 volts. Uh huh. And and none of the electrical connections were like properly sealed off, </s>

<s>[INST] So you think it's possible to actually measure risk or is your basic argument is there's risk involved in a, in a lot of both the working class, in the bourgeoisie, the capitalist and the [/INST] worker would never come and say because he's been taught right. Um, I want this payment, a wage for the work I do and I want this page this payment for the risk I take. </s><s>[INST] Well there's some level of communication like that you have acknowledgement of dangerous jobs, but that's probably built into the salary, all those kinds of things you you understand but you're not incorporating the full spectrum of risk. [/INST] This country is now being literally transformed from below by an army of workers who work at amazon uh fast food joints. You know what their complaint is. It's killing us, We get paid shit and it's killing us. There is no relationship except in the minds of the defenders of capitalism between the ugliness, the difficulty, the danger of labor on the one hand and the wage. Let me give you just a couple of examples because this is my, this is my job, this is my life what I do. All right. The median income Of a child care worker in the United States right now as we speak is $11.22 an hour median, so 50% make last 50%. Make more. The median income for car park attendant is several dollars per hour higher than that. What does the car park attendant do? He stares at your car for many hours to make sure that nobody comes and grabs </s><s>[INST] it. [/INST] Maybe he parks it and he moves it around to get it in and out by any measure that I know of. That makes any rational sense being in charge of, of toddlers, 234 year olds who are at the key moment of mental formation, the first five years to do to give that a lower salary than you give the guy who watches your car. Come on. I know how to explain it. Gender explained all kinds of issues. The car park people are males and the child care people are females. And that that in our culture is a very big marker of what But the one who said only the economics professor, nobody else says this stuff because in economic, I don't know if you're familiar with our profession, but we have something which we call marginal product. This is a this is a fantasy. I was a mathematician before I became an economist. I loved mathematics. I specialized in mathematics. So I know mathematics pretty well. What economists do is is silly is childish, but they think it's mathematics sophisticated it is. But think for a minute what it means to suggest that you can identify the marginal product of a factor of production. Like a worker in the in the textbook when when it's taught I've taught this stuff. I hold my nose. But I teach it. Then I explained to students what I just taught you is horseshit. But I first I teach it </s><s>[INST] what is the marginal product that might be useful? The [/INST] notion is if you take away one worker right now from the pile what will be the diminution of the output. That's the marginal product of that worker </s><s>[INST] measured by [/INST] the amount of the output that diminishes </s><s>[INST] output of the raw product of the product. [/INST] Usually in real terms. So physical, not, not the value, you could do a value but it's really more the physical. Your </s><s>[INST] I mean there is a transformation thing I'd love to talk to you about about value. It's so interesting value. [/INST] I'd be glad to talk to you about value and price and all of that. But I just want to get to the Hagel whose Marxist teacher has a famous line. You can't step in this in the same river twice. And the argument is you and the river have changed between the first and the second time. So it's a different you and it's a different you can choose not to pay attention to that. Just you can't claim you're not doing that. You can't claim that. You can actually do that because you can't there is no way to do </s><s>[INST] that. So the meaning that you can't just remove a worker and have a clean mathematical calculation of the effect that has on the output. [/INST] Because too many other things are going on. Too many things are changing and you cannot assume much as you want to that the outcome on the output side is uniquely determined by the change you made on the input side. I can't do that. </s><s>[INST] Even in the even in the average, it's not going to work out, [/INST] You can take mathematics is full of abstractions. You can abstract, you can say, as as we do in economics, terrorist para bus, you know, everything else held constant. But you have to know what you just did. You held everything. You know why you do that because you can't do that in the real world. That's not possible. You better account for that. Otherwise, you're mistaking the abstraction from the messy reality you abstracted from to get the abstraction </s><s>[INST] as a quick tangent. If we somehow went through a thought experiment or an actual experiment of removing every single economist from the world would be better off or worse [/INST] off. </s><s>[INST] Okay, [/INST] Economics. And I'm one, you know, I'm talking about myself, see economics, we're </s><s>[INST] gonna ship ship all the economies to mars [/INST] and see </s><s>[INST] how it works off. [/INST] But the serious part of this is that economics, you know, it's it's really about capitalism. Economics as a discipline is born with capital. There was no such thing. When I teach, I teach courses at the University, for example, called History of Economic Thought, right? And I begin the students with Aristotle and Plato, and I say, you know, they talked about really interesting things, but they never called it economics. There was no it made no sense to people too abstract something as central to daily life as economics broadly defined. It made no sense. That's a creation much much later. That's capitalism that did that created the feeling. So when I give them plato and Aristotle, I have to give them particular passages by the way, football, because your audience will like it. Plato and Aristotle talked about markets because they lived at a time in ancient Greece when market relations were beginning to intrude upon these societies. So they were both interested in this phenomena that we're not just producing goods and then distributing among us. We're doing it in a quid pro quo. You know, I'll give you three oranges, you give me two shirts, a market exchange, and both Aristotle and Plato hated markets, denounced them, and for the same reason, they destroy social cohesion, they destroy community. They make some people rich and other people poor, and they set us against each other. And it's terrible. And here's what that they agreed on that. Here's what they disagreed on. One of them said, okay, there can be no markets. That was Plato. Aristotle comes back and says, no, no, no, no, no, no. Too late for that. The disruption caused in society by getting rid of this institution that has crawled in amongst us would be too devastating. So we can't do that. But what we can do is control it, regulate it. Get from the market what it does reasonably well and prevent it from doing the destructive things it does so badly. So </s>

<s>[INST] But is it possible that it's mapped? Well in some concrete, predictable way to objective reality. The sheet of paper, the student mention space where we can talk about space time maps and some way that we maybe don't yet understand, but will one day understand what that mapping is. But it maps reliably it is tethered in that way. [/INST] Well, yes, and so the new theories that the physicists are finding beyond space time have that kind of tethering. So there they show precisely how you start with an apology, Hedren and how you project this high dimensional structure into The four Dimensions of Space Time. So there's a precise procedure that relates to the two and they're doing the same thing with the cosmological politics. So, so they're they're the ones that are making the most, you know, concrete and fund advances going beyond space time. And they're they're they're tethering it, but they say this is precisely the mathematical projection from this deeper structure into space time. one thing I'll say about as a non physicist, what I find interesting is that they're finding just geometry, but there's no notion of dynamics right now, they're just finding these static geometric structures which is impressive. So I'm not putting them down, this is what they're doing is unbelievably complicated and brilliant and um adventurous although and it's all those things </s><s>[INST] and beautiful beautiful from a human aesthetic perspective because geometry is beautiful. It's [/INST] absolutely and they're finding symmetries that are true of the data that can't be seen in spacetime. But I'm looking for a theory beyond space time. That's a dynamical theory I would love to find and we can talk about that at some point, a theory of consciousness in which the dynamics of consciousness itself will give rise to the geometry that the physicists are finding beyond space time. If we can do that, then we'd have a completely different way of looking at how consciousness is related to what we call the brain or the physical world. More generally. Right right now, all of my brilliant colleagues, 99% of them are trying to they're assuming spacetime is fundamental, assuming that particles are fundamental, quarks, gluons, lepton, and so forth, elements, atoms and so forth are fundamental and that therefore neurons and brains are part of objective reality. And that somehow when you get matter that's complicated enough, it will somehow generate conscious experiences by its functional properties. Or if your pan sickest, maybe you, in addition to the physical properties of particles, you add your consciousness property as well. And then you have you can combine these physical and conscious properties to get more complicated ones, but they're all doing it within spacetime. All of the work that's being done unconsciousness and its relationship to the brain. It's all assumed something that our best theories are telling us is doomed space time, </s><s>[INST] why does that particular assumption bother you the most. So you bring up spacetime. I mean, that's just one useful interface we've used for a long time. Surely there's other interfaces. Is spacetime just the one of the big ones that you build up. People's intuition about the fact that they do assume a lot of things strongly or or is it in fact the fundamental flaw in the way we see the world? [/INST] Well, everything else that we think we know are things in space time. Yeah, </s><s>[INST] sure. And [/INST] so if you when you say space time is doomed, this is a shot to the heart </s><s>[INST] of [/INST] the whole framework, the whole conceptual framework that we've had in science, not to the scientific method, but to the the fundamental ontology and also the fundamental methodology, the ontology of spacetime and its contents and the methodology of reductionism, which is that as we go to smaller scales in spacetime, we will find more and more fundamental laws and it's been very useful for space and time for centuries, reductionism for centuries. But but now we realized that that's over, reductionism is in fact dead as a space time. </s><s>[INST] What exactly is reductionism? What is the process of reductionism that is different than uh some of the physicists that you mentioned. They're trying to think, trying to let go of the assumption of spacetime. Looking beyond isn't that still trying to come up with a simple model that explained this whole thing, isn't it still reducing? [/INST] It's a wonderful question because it really helps to clarify two different notions, which is scientific explanation on the one hand and a particular kind of scientific explanation on the other, which is the reductionist. So the reductionist explanation is saying, I will start with things that are smaller in spacetime and therefore more fundamental, and where the laws are more fundamental. So we go to just smaller and smaller scales, whereas in science more generally, we just say like when Einstein did the special theory of relativity, he's saying, let me have a couple of postulates, I will assume that the speed of light is universal for for all observers in uniform motion. Um and that the laws of physics. So if you're for for uniform motion or or the that's not a reductionist. That those are saying, grant me these assumptions, I can build this entire concept of space time out of. It's not a reductionist thing, you're not going to smaller and smaller scales of space, you're coming up with these deep deep principles. Same thing with this theory of gravity, right? It's the falling elevator idea. Right? So this is not a reduction, this kind of thing. It's it's it's it's it's something different, </s><s>[INST] is a bigger thing than just [/INST] reductionism. That reductionism has been a particularly useful kind of scientific explanation, for example, in thermodynamics, right? Where the notion that we have of heat, some macroscopic things like temperature and heat, it turns out that, you know, Goldsman and others discovered. Well, hey, you know, if we go to smaller and smaller scales, we find these things called molecules or atoms and if we think of them as bouncing around having some kind of energy, then um what we call heat is is is really can be reduced to to that. And and so that's a particularly useful kind of reduction is a useful kind of scientific explanation that works within a range of scales within spacetime. But we know now precisely where that has to stop 10 to the minus 33 centimeters and 10 to the minus 43 seconds and I would be impressed if it was 10 to the minus 33 trillion centimeters. I'm not terribly impressed at 10 to the minus 33 centimeters. </s>

<s>[INST] saw in him the spirit was a little bit gone when you're facing. Yeah, [/INST] But then he came back, anyone, you know, rest of the matches and he was in the round robin and he was able to go to the finals. Uh, but he had lost another match actually against in the round robin against the Japanese. So I think I had already gained enough of artistic being able to finish a match once I lost my match in college for the last two years, I took on some of that artistic uh, working, I think that he was already hoping to win, but he was hoping to win by a long ways because he had to pin me or beat me by eight points to be able to win the gold. And uh, you know, that wasn't gonna happen. I mean the chances of pen is pretty good </s><s>[INST] because it's hard to pin down gable versus take down like have you taken risks where you could pay for them? [/INST] I can't remember too many that I took that would actually put me in a danger position. I've taken risk. But the risk were so scientifically technically correct that I wouldn't land in that danger zone. It's like if I'm going to lock up and throw you, I'm not gonna throw you to my own back and roll you through. I'm gonna turn in the air. </s><s>[INST] You were scientific [/INST] about exactly. You know, he just, I learned the hard way early on, There was moves from collegiate wrestling that you did, that exposed your shoulders, which it cost me in some early freestyle matches against great wrestlers. But I would go back to my collegiate escaping type moves to where I hit a Granby roll where you expose your shoulders and you lose two points every time. But you learned that that's not the system. But if you hadn't wrestled much, you would get exposed under maybe a desperate situation, you would hit it. </s><s>[INST] So you won the gold. How did it feel? [/INST] I think it would have, I think the question would be, how would it feel if you lost the gold for me because I already went through that once. Not at that highest level, but the national collegiate championship level. My senior </s><s>[INST] year Larry? Oh, [/INST] Larry going to and that didn't sit well, </s><s>[INST] were you afraid of that happening again at the olympic level was that, you [/INST] know, I really wasn't. But it was why I changed my philosophy of training and added to the scientific artist type. And I, if I would have won that match, even though I wouldn't have felt good about it, even though I squeaked it out, I wasn't feeling good about that match. It would have affected me a little bit. But if I don't want it, I would have got over it. I mean I'm not over it now. I mean, I don't know why I was doing this kind of stuff right before my match by that. I mean this kind of stuff. Talking interview. </s><s>[INST] Yeah, journalists. [/INST] Yeah. And I really wasn't a good talker that I mean me and you were talking pretty good right now except for, I got a little cold, but I don't think I could say two words hardly then and they took takes White Royal of Sports said, Hey, just We want you to be the introduction for our next week's show. So I just say, Hey, I'm Dan Gable Come Watch me as I finished my career undefeated 182 and all. That's what they want me to </s><s>[INST] say. Everybody assumed you'd be undefeated [/INST] and I said it, I had to take it 22 times and in the last two or three times they wrote it out and I read it and it still, it wasn't like I just said it. I was reading like, hi I'm dan gable come come on, you know, that type of stuff. So and he finally just closed the book and said that's good enough, but I turned and it was my time to russell. Yeah, and so you know, you just, you learn that and for me it was great coaching experience because that's what I turned in to be, you know, I coach for longer than I wrestled and I put up a lot of champions, but you learn through mistakes that even in your own career that you had made, you know, it's, it's never learning process, it's an ever learning process. </s><s>[INST] Have you ever been afraid on the map? Does fear have any role do you think for a wrestler or it must be as [/INST] well, I'm sure fear is out there and I'm sure that was to my advantage. Almost every time, I'm sure in my olympic finals is really off. He had these doubts, He probably had these doubts and that gives gives me the edge and I don't know if I really ever had fear, but obviously there was points in times where I didn't perform as well. Not many, but a few and if I look back of it, look back at it, I don't think it was that american, you know, raw, raw, raw stuff. I think it was probably the fear of not being an artist as much. You know, maybe this guy might be better than me uh scientifically and uh, you know, you're a scientist. I think that got to me more than anything else. I said early on that I want to eliminate ever happened to worry about getting tired in a match. So I kind of eliminated that. So I got rid of that point. And I do think that in wrestling, that is one of the fears that a lot of wrestlers have actually how they feel during the match. And, and do they, are they going to get tired and isn't gonna affect my performance? And as a coach, that really was one of the things I tried to eliminate on all my athletes. So there wasn't that fear factor, but that fear factor would be put upon my opponent, which would give me an edge, but that's not what I needed as much I need to just focus, make sure that I was doing the right things and I needed my team to be focused. So I made sure that from my mistakes as an athlete or even as a coach sometimes that I didn't repeat them, uh didn't repeat them. And if you make a mistake once and then you can repeat it. It's like uh he didn't learn anything, </s>

<s>[INST] Another thing that actually happened? I just have a million questions I wanna ask you is fascinating to me, uh, is there's a bird strike on the plane. Does that happen [/INST] often </s><s>[INST] damaged the engine? And they made it seem like it's a serious, exactly, serious [/INST] issue. I've hit birds. Um, I know someone that took a turkey vulture to the face through the cockpit, right, shattered the cockpit, knocked him out. Um, I think that actually, I don't know him personally, but the store I know from the command I was at, and I believe the back seater had to punch out and punch them both out because he was unconscious, you know, in the front seat from the bird. Um, it can kill you from hitting you. It's, you know, it's like a bowling ball going 250 miles an hour. Um, it can take out an engine, uh, very easily. Uh, every airport I've flown at in the navy, I've had to check the bird condition if you will to see how many birds we've had to cancel flights because, because there's too many of them around the airport, some airports even have bird radars. Airport, </s><s>[INST] there are systems that monitor the bird condition. [/INST] There's, yeah, there's actual radar systems and you can go in the certain bases, you have to call up and they'll tell you what it is for the day or for that hour and other ones have it in like their, their weather report that goes out over the radio. </s><s>[INST] What are some technological solutions to this? Or is this just uh because it's a low probability event? There's no real solution for it? [/INST] I would say it's not a little probably about event. I mean this is happening a lot. I mean although the hits themselves aren't necessarily that common or I'll say a catastrophic hit, either a near miss or hit or the pilot having to actively maneuver to avoid. It is pretty common and in fact it </s><s>[INST] seems stressful. [/INST] It is, it's so common in fact that we know that you never want to try to go over or you never want to go under a bird. If you see it in front of you, you always want to try to go over it because what they'll do immediately if they see you is and you startled and they'll bring their wings in and just drop straight down to try to get out of the path. It's interesting. I didn't know they did that, but so if you immediately, if you try to go under them will be dropping into you. So you typically want to try to go above them. </s><s>[INST] Is this something you can train for or no. [/INST] Um, is </s><s>[INST] this one of those things you have to really experience? It's [/INST] a skill set that um, you somewhat trained for in the duties of being a fighter pilot descent, right? Being able to react to your environment very quickly and make make decisions quickly. So is </s><s>[INST] that one of the more absurd things challenges you have to deal with. And flying. Is there other things sort of maybe weather conditions like harsh weather conditions? Is there something that we maybe don't often think about in terms of the challenges of flying [/INST] birds in a way aren't a ridiculous threat for us. It's it's a safety threat that, you know, anything physical in the air is, it's something that we really have to be careful about whether we're flying formation off of the aircraft right next to us or whether it's a turkey vulture at 2000 ft or a flock of 5000 birds like at the runway, we have to wave off, You know, and although there are low probability, a lot of bases will have like actual environmental protecting agency employees that are responsible for safely removing migratory birds or different animals um, that maybe in the runways or flying about, </s><s>[INST] wow, I didn't know what a turkey vulture is and it really does look like a mix between a vulture and a [/INST] turkey </s><s>[INST] and look kind of dumb. No offense to turkey vultures. Um, in that movie. Who was the enemy nation? Was it? Uh, I mean, I think, I guess they were implying as Iran or was it Russia? [/INST] I didn't think they were implying any particular nation state, frankly, I think they did a somewhat decent job of having some Ambiguous 5th generation fighters the location and and the stockpile like I get like how the story kind of insinuates certain things. But they seemed a good job of not having anything directly pointing to another nation, which I thought was, you know, the good move. I I enjoy these type of movies as an aviator and you know, as an american, right? Cause it's a feel good movie. But um you know, we we shouldn't be celebrating going to war with any particular country, you know, china Russia, whoever may have these weapons. It's it's fun to watch but it would be an incredibly serious event to be employing these weapons. </s><s>[INST] Yeah, well we'll talk about war in general because yeah, it's the movies kind of celebrating the human side of things and also the incredible technology involved. But there's also the cost of, of war and the seriousness of war and the suffering involved with war not just in the fighting but in the death of civilians and all those kinds of things. Um Well you wore a Navy pilot, let's let's talk a little bit more uh seriously about this And you were twice deployed in the Middle East flying the F a 18 F super hornet. Can you briefly tell the story of your career as a navy pilot? [/INST] Sure. So I joined the Navy in 2009. Right after college, I went to officer essentially officer bootcamp officer candidate school I applied as a pilot and I got into the pilot that was advantage of going that way is that essentially choose what I wanted and if I got in great if not I didn't get stuck doing something else. So </s>

<s>[INST] so the same area. So there would be a theater for the Yeah, [/INST] so it kind of the edge of this machine would be where the LHC is, but it would sort of go under Lake Geneva and round to the ALps basically, since, you know, up to the edge of the Geneva Basin. So it's basically the biggest, it's the biggest tunnel you can fit in the region based on the geology. Yeah, it's big would be a long drive if you're, you know, you're experiments on one side, you got to go back to search for lunch. So that would be a pain. But, you know, so this project is in principle is actually two accelerators. The first thing you would do is put an electron positron machine in the 100 kilometer tunnel to study the Higgs, you'd make lots of Higgs bozon, study it really precisely in the hope that you see it misbehaving and doing something, it's not supposed to. Um and then in the much longer term 100 machine gets taken out, you put in a proton proton machine. So it's like the LHC, but much bigger and that's the way you start going and looking for dark matter or you're trying to recreate this um, phase transition that I talked about in the early universe where you can see matter, antimatter being made, for example, there's lots of things you can do with these machines. The problem is that They will take, you know, the most optimistic. You're not gonna have any data from any of these machines until 2040 or you know, because they take such a long time to build and they're so expensive. So you have to be a process of R. & D. Design and also the political case being made. </s><s>[INST] So L A. C. What cost a few billion? It [/INST] depends how you count it. Um I think most of the sort of more reasonable estimates that take everything into account properly. It's around the sort of 10 11 €12 billion </s><s>[INST] mark. What would be the future, sir? I forgot the name of future circular collider for [/INST] future circular because they won't call it that when it's built because it won't be the future anymore. </s><s>[INST] But I don't want to call it then. [/INST] Very big hadron collider, I don't know, but that will now I should know the numbers. But I think the whole project is estimated at about €30 billion. But that's money spent over Between now and 2070 probably. Which is when the last bit of it would be sort of finishing up, I guess. So you're talking a half a century of science coming out of this thing shared by many countries. So the actual cost, the arguments that are made is that you could make this project fit within the existing budget of certain um if you didn't do anything else </s><s>[INST] concerned by the way, we didn't mention what is cern [/INST] cern is the european Organization for Nuclear Research is an international organization that was established in the 19 fifties in the wake of the Second World War as a kind of, uh, it was sort of like a scientific marshall plan for europe. The idea was that you bring european science back together for peaceful purposes, because what happened in the 40s was, you know, a lot of particularly jewish scientists, but a lot of scientists from central Europe had fled to the United States and europe had sort of seen this brain drain. So it's a desire to bring the community back together for a project that wasn't building nasty bombs, but was doing something that was curiosity driven. So, and that has continued since then. Um, so it's kind of a unique organization. It's you to be a member as a country, you sort of sign up as a member and then you have to pay a fraction of your GDP E gear is a subscription. I mean, it's a very small fraction, relatively speaking, I think it's like, I think the UK's contribution is 100 or 200 million quid or something like that, which is quite a lot. But, you </s><s>[INST] know, that's fascinating. Just the whole thing that is possible. It's beautiful, It's a beautiful idea, especially when, when there's no wars on the line. It's not like we're freaking out is we're actually legitimately collaborating to do good science. One of the things I don't think we really mentioned is on the final side. That's sort of, the data analysis side is their breakthrough is possible there. And the machine learning. So like is there, is there a lot more signal to be mined in more effective ways from the actual raw data? [/INST] Yeah, A lot of people are looking into that. Um, I mean, so, you know, I use machine learning in my data analysis, but pretty naughty, you know, basic stuff because I'm not a machine learning expert. I'm just a physicist who had to learn to do this stuff for my day job. So what a lot of people do is they use kind of off the shelf packages that you can train to do signal noise, you know, </s><s>[INST] just clean up on the Yeah. [/INST] But one of the big challenges, you know, the big challenge of the data is a, its volume. There's huge amounts of data. So the LHC generates. No, okay, I remember what the actual numbers are. But if you we don't record all our data, we record a tiny fraction of the data. It's like of order 1 10/1000 or something. I think that right around that. So it's mostly gets thrown away. You couldn't record all the LHC data because it would fill up every computer in the world in a matter of days is basically, So there's this process that happens on live on the detector something called a trigger Which in real time 40 million times every second has to make a decision about whether this collision is likely to contain an interesting object like a higgs bozon or a dark matter particle. And it has to that very fast. And the software algorithms in the past were quite relatively basic. You know, they did things like measure momentous and energies of particles and put some requirements. So you would say if there's a particle with an energy above some threshold then record this collision. But if there isn't don't whereas now the attempted to get more and more machine learning in at the earliest possible stage </s>

<s>[INST] Is there always need to be a part of arc. That's the test, like it's hidden. [/INST] Yes, absolutely. It is impressive that uh tests that you're using to actually benchmark algorithms is not accessible to people developing these algorithms because otherwise what's going to happen is that the human engineers are just going to solve the tasks themselves and and could their solution program form. But that again, what you're seeing here is the process of intelligence happening in the mind of the human and and then you're just capturing, it's crystallized output, but that's crystallized output is not the same thing as the process that generated. It's not intelligent. So </s><s>[INST] what by the way, the idea of crowd sourcing it is fascinating. I think I think the creation of questions is really exciting for people. I think I think there's a lot of really brilliant people out there that love to create these kinds of stuff. [/INST] Yeah. One thing that that kind of surprised me there wasn't expecting is that lots of people seem to actually enjoy our as a as a kind of game. And I was really seeing it as a test as a benchmark uh fluid general intelligence and lots of people just including cases started you know enjoying it as a game. So I think that's that's encouraging. </s><s>[INST] Yeah I'm fascinated by there's a world of people who create I. Q. Questions. I think I think that's a cool uh it's a cool activity for machines that for humans and people humans are themselves fascinated by taking the questions like you know measuring their own intelligence. I mean that's just really compelling. It's really interesting to me to it helps. One of the cool things about our cue said it's kind of inspired by I. Q. Tests or whatever follows a similar process but because of its nature because of the context in which it lives, it immediately forces you to think about the nature of intelligence. As opposed to just a test of your like it forces you to really think this I don't know if it's if it's within the question inherent in the question or just the fact that it lives in the test that's supposed to be a test [/INST] of machine intelligence. Absolutely. As you as you solve our tasks as a human uh you will be forced to basically introspect how how you come up with solutions and that forces you to reflect on uh the human problem solving process and the way your own mind generates uh abstract representations of the problems. Uh It's exposed to, I think it's due to the fact that the set of core knowledge buyers that arc is built upon is so small, it's all recombine nation of a very very small set of assumptions. </s><s>[INST] Okay, so what's the future of art? So you you held arc as a challenge is part of like a kegel competition, cackle competition and um what do you think? Do you think that's something that continues for five years? 10 years, like just continues [/INST] growing? Yes, absolutely. So Arc itself will keep evolving. So I've talked about crowdsourcing, I think that's it. Good avenue. Another thing I'm studying is um I'll be collaborating with folks from the psychology department at N. Y. U. Like to do human testing on arc. And I think there are lots of interesting questions you can start asking especially as you start correlating um uh machine solutions to our tasks and uh uh the human characteristics of solutions, like for instance, you can try to see if there's a relationship between the human perceived difficulty of the task uh and uh machine. Yes and exactly some measure of mission perceived difficulty, it's a nice playground </s><s>[INST] and wish to explore this very different. It's the same thing as we talked to all the autonomous vehicles, the things that could be difficult for humans might be very different than the [/INST] things that is absolutely </s><s>[INST] and formalizing or making explicit that difference in difficulty will teach us something. May teach us something fundamental about our [/INST] intelligence. So one thing I think we did well with arc um, is that it's proving to be a very actionable test in the sense that machine performance and ox started that very much zero initially while you know, humans fun actually the talks were easy and that, that alone was like a big bright flashing lights saying that something is going on and that we are missing something. And at the same time, uh, machine performance did not stay at zero for very long actually, within two weeks of the cattle competition, we started having uh, a non zero number and now the state of the artists around 20% of the test set uh, solved. Um, and so art is actually a challenge where our capabilities started zero, which indicates the need for progress. But it's also not an impossible challenge. It's not accessible. You can start making progress basically right away. At the same time, we are still very far from being solved it and that's actually a very positive outcome of the competition. Is that the competition has proven that uh, there was no obvious shortcuts to solve these tasks. So the test held up. Yeah, exactly. That was the primary reason to carol competition is to check if some, some clever person was going to hack the benchmark and that did not happen right? Like people while serving the telescope is actually doing it. Uh uh well, in a way they're actually exploring some flows of art that we will need to address in the future, especially they're essentially anticipating with soft tasks may be contained within a set, right? Which </s><s>[INST] is kind of Yeah, that's the kind of hacking [/INST] Human hacking of the things that that said, you know, uh with the state of the art, it's like 20% were still very, very far from human level, which is closer to 200 person. And so, and I do believe that, you know, it will it will take a while until we reach a human parity on arc and that by the time we have human parity, we will have A I systems that are probably pretty close to human level in terms of general fluid intelligence, which is, I mean, they're not going to be necessarily human, like they're not necessarily uh you would not necessarily recognize them as, you know, being an A G I, but there would be capable of a degree of generalization that matches the generalization performed by human food intelligence. </s>

<s>[INST] Cutting it like I never touch it. I can't touch it. So there's something almost like, um The texture of the biology of a human flesh that just [/INST] That's at the level of that's the level of your trauma. Yeah, and it's been I mean, it's 2021 This was an oh nine and i've worked on this like and I mean I i've been in like treatment And religiously just to be able to keep me alive for this this decade And so it's not like it's like oh i'm never you never even tried to get better It's like I never used to leave my house. I used to call people that look like that horrific names in public </s><s>[INST] I used to want to kill people on a regular basis. I'm fairly happy individual now. What about you're talking about sort of skin and parts and But there's also just the fact that we're mortal and there's somebody Close to you who dies so you watch walk up and then never come back out again. Come back out again Yeah, it's like you're facing mortality in a very real way and uh In a way that's not the same as somebody dying from cancer in a hospital. Although It has echoes of that because that's also absurd and And like it doesn't feel like there's justice to it in any kind of way, but it's so sudden like have you been able to um make sense of that Of your feelings about it. Like how do you feel about it or or is everything just shrouded in this like? Trauma that you're not able to just um [/INST] Feel for the loss of a human being like mourn the loss of a human being. I think I had I thought he was not a human being I Don't want to dig into all the immers dripping and reap the blood I think that's what he said I oftentimes think of him the first time he said a person gone and he went and actually There was also it throughout to be active and then you're safe </s><s>[INST] That's how you deal with that That means you have a feeling like, [/INST] you still feel like parts of him were left behind. On the ramp ceremony, when I lost my mind, literally, I lost my mind, and I was screaming that he wasn't all in there. I'm happy now knowing that he was, </s><s>[INST] but I held on to that for 10 years. Yeah, this, yeah, the sandbags, like it's, the bulk of the weight [/INST] is not from human flesh, yeah. He was a young kid too. It was, I think it was his first deployment as well. Like he was, he was a young kid, and he was just going to clear the road for the rest of us, right? Like not, like you know you're in war, and you know that you're outside the wire, and you know things could happen. You understand that to the extent you can understand that. </s><s>[INST] When it's happening, it's something very different. Also, maybe you can correct me, but there's something much more like brutal about an IED versus like a bullet. Because a bullet, you still, watching somebody close to you die from a bullet, you still get the basic humanity. Like, so IED basically converted a human being into sort of parts by biological parts. Yeah, versus, yeah, I mean, I don't, that's tough. That's tough, because that's like, because it's hard for you to remember them as a human. [/INST] You remember them as parts. For me, that's how I remember him. I would like to, I have a picture that I post every year about him. I see that, but I don't put two and two together. </s><s>[INST] Does that make sense? Yeah, yeah, no, it does. So I, even I, listening to your story, you know, thank you for sharing it, first of all. [/INST] It's fine, it's not my, it's, </s><s>[INST] I'm just the one to tell it, I was just involved. I'm just the one to tell it, I was just involved. One set of eyes on this particular human being. [/INST] But even I get angry. </s><s>[INST] I can't tell if it's exhaustion or anger. [/INST] Oh, I'm sorry, I look always exhausted. Oh, that's okay, you're into robotics, isn't that like your guys' thing? </s><s>[INST] You guys are just always working on time. I think because I feel so much for the world, I just don't do, we were talking about resting bitch face earlier. I just don't feel the need to maintain all the effort of the musculature for presenting myself to you visually. It's exhausting. It's exhausting. So I just focus on the feeling. No, hey, I, and then let the face show whatever the hell it shows. Fair enough. [/INST] Okay, was their anger, was there hate? Yeah, exhausting. It's exhausting. So I just focus, And then let the face- </s><s>[INST] Fair enough, yeah. Can you just talk through your feelings [/INST] of what you remember, of what you- Yeah, so after that operation with the British, I went back to the Canadians. And I didn't go back as even remotely close to who I was when I left. And that was really troublesome for a lot of people around me because the level of anger and hate that came out of me was palpable when I just walked. I got shockingly quiet and you understand how you're learning- That'd be terrified if you were quiet. And I don't know if hate and anger do that justice. I don't know another word, but I don't think those two words do it justice to the extent that I was feeling. Like I got to a point when I got attacked by a woman with some scissors, like the idea crossed my mind, like I could boot stomp her to death and not feel anything about it </s>

<s>[INST] I just feel like steve jobs and, uh, you know, most did not have these conversations or at least did not have him for long, [/INST] that's for sure. But I think, you know, yeah, at that point it just felt like, you know, I felt, um I just didn't want to build a company that was never my intention just to build something successful or make money. It would be great, it would have been great, but I'm not, you know, I'm not really started person, I'm not um, you know, I was never very excited by the grind by itself and or just being successful for building whatever it is and not being into what I'm doing really. And so I just took a little break because I was, you know, I was upset with my company and I didn't know what we're building. So I just took our technology and um, our little delic constructor and some models, some deep learning models, which at that point we were really into and really invested a lot and built little child offer a friend of mine who passed and the reason for that was mostly that video that I saw him talking about the digital avatars and ruin was that kind of person. He was obsessed with, you know, just watching Youtube videos about space and talking about. Well if I could go to mars now, even if I didn't know if I could come back, I would definitely pay any amount of money to be on that first, shut up. I don't care whether he died. Like he was just the one that would be okay with, you know what, trying to be the first one, you know, and so excited about all sorts of um, things like that and he was all about fake it till you make it. And just, and I felt like, and I was really perplexed that everyone just forgot about him. Maybe it was our way of coping, mostly young people coping with the loss of a friend. Most of my friends just stopped talking about him and I was still living in an apartment with all his clothes and you know, paying the whole lease for it and just kind of by myself in december. So it was really sad and I didn't want him to be forgotten. First of all, I never thought that people forget about dead people so fast, people pass away. People just move on and it was astonishing for me because I thought, okay, well he was such a mentor for so many of our friends, He was such a brilliant person who was somewhat famous in Moscow. How is that? No one's talking about him, like I'm spending days and days and we don't bring him up and there's nothing about him that's happening. It's like he was never there. Um, and I was reading this, you know, the, the book, the year of magical thinking by joan Didion about her losing and blue knights, about her losing her husband, her daughter And the way to cope for her was to write those books. And it was sort of like a tribute and I thought, you know, I'll just do that for myself And you know, I'm a very bad writer and a poet as we know. So I thought, well I have this tech and maybe that would be my little post card like postcard for him. So I built a child bought, um, just talk to him and it felt really creepy and weird a little bit for a little bit. Um, I just want to tell other people because it felt like I'm telling about having a skeleton in my underwear. Okay. But it was just felt really, I was a little scared that I would be not, it won't be taken. But it worked interestingly pretty well. I mean it made tons of mistakes, but it still felt like him. Um, granted it was like 10,000 messages that I threw into a retrieval model that would just re rank that takes us out and just a few script on top of that. But it also made me go through all of the messages that we had and then I asked some of my friends to send them through and it felt the closest to feeling like him present. Um, because you know his facebook was empty and instagram was empty or there were a few links and you couldn't feel like it was him. And the only way to fill him was to read some of our text messages and go through some of our conversations because we just always had them, even if we're sleeping next to each other in two bedrooms separated by a wall. We were just texting back and forth texting away. Um and there was something about this ongoing dialogue that was so important that I just didn't want to lose all of a sudden and maybe it was magical thinking or something. And so we built that and I just used it for a little bit and we kept building some crappy chatbots with a company. Um but then a reporter came came to talk to me. I was trying to pitch our child boss to him and he said, do you even use any of those? I'm like no, he's like, so do you talk to any chatbots at all? And I'm like, well, you know, I talked to my dad friends football and he wrote a story about that and all of a sudden became pretty viral. A lot of people wrote about it. And </s>

<s>[INST] and less typically, much less powerful engine in space. So you mentioned on the multi-stage rockets that maybe the dream would be, if we weren't living on Earth, but maybe we can on Earth to have a single stage to orbit rocket where it's all one package reusable. Reusable gets even harder. It gets even harder. So first of all, what is, just to linger on it, what is the single stage to orbit rocket? Why is it so hard to achieve on Earth? You already kind of explained it a little bit, but just if we were to say like, yeah, that's your assignment. Yeah. Tim, you're supposed to get together with Elon and other brilliant people and like, you have to do this. Yeah. [/INST] Why is it so hard? It's so hard. Why is it so hard? It, your, the payload fraction of a rocket is like three to five or six or 7% would be like, that's the amount of payload compared to the total mass of the rocket. Like you're lucky to get into beyond 5%. So if you're now having to deal with the weight of the rocket by the time you're in orbit, like your payload fraction, just you're talking about like margins. It's such, it's so small amount of leftover. If you have to take all of it with you. So the sooner you can ditch weight, the better. The sooner you can ditch weight, the better. The sooner you can, and that's what you're doing. A rocket the whole time is actually ditching weight. All of that fuel and all that big giant flame you see is literally mass being thrown out the back of the rocket. But what typically isn't expended, at least during nominal operations, you're not seeing the engines being expelled out the thing until you get to staging of course. And that's where you're ditching all that dead weight. So single-staged orbit. your margins just become so small that it's border, it's not impossible, but it's just at the end of the day, like almost no matter who you are, you end up saying it's just simply not worth it. Like it'd be, if you have two rockets that are using the same amount of propellant, you know, they're the same physical sizes and one of them is cutting, you know, on a third and has another little engine, it'll have a hundred or a thousand times more payload capacity than the one sitting right next to it. And now, so there's tricks you can do to like try to offset that, things like aerospike engines, which operate as efficiently at sea-level, at kind of optimized efficiency at sea level by the way they're designed the physics of them. They're also efficient in a vacuum too. You can do the things like that. And at the end of the day, though, you just end up with a worse rocket than if you had just done stage like no matter what and people say like, well, what if you would develop the new technologies? like, okay, you apply that technology to a multistage rocket and it's gonna do better, you know, like no matter where you end up, </s><s>[INST] it's just always better to ditch that weight. Is there a cost to having multi-stage? [/INST] Because you can still reuse the different stages. The dream becomes easier to reuse multiple stages because now the booster doesn't have to survive orbital reentry temperatures and extreme environments and you only have to make survivable the upper stage. You'll only have to put a big heat shield. Starship's the perfect thing of this. The upper stage has a big giant heat shield, the booster doesn't need it. The booster's not going to orbit. It's only going a fifth or a quarter of orbital velocity. So it's heat that it experiences, it's survivable just by the stainless steel. You don't need an additional heat shield. Pretend that you just welded the two stages of Starship together, remove those engines on Starship. That whole vehicle. If you're trying to reuse it, the whole vehicle now has to have a heat shield on one side of it. The whole thing has to have these big heavy wings. By the time you come down to it, there's probably just zero payload capacity. you basically put your fuel tank in space, you know? </s><s>[INST] Good job. So the dream of a single stage to orbit, a rocket, [/INST] is that just even the wrong dream on Earth? That's what most convention tells you. You know, by the time, if your goal is cheap, then you're going to spend, you're gonna have a physically larger rocket that has more engines, that has more propellant, blah, blah, blah, to put the same amount of mass into orbit compared to something else. You know, we're talking like Rocket Lab's Electron, a really small rocket, it's like, I think, 1.3 meters wide, and something like, you know, 18 meters tall or something. It's a small rocket. If you were to, you know, and it can put something like 300 or so kilograms into orbit, you could either launch something that size or again like a full, like big old Falcon 9 booster, the huge, huge thing, and that would be lucky to put 300 kilograms into orbit, you know, so it's like which one's gonna be cheaper to build, you know, ship around, all this stuff, And then you also look at, you have fixed costs. Like the idea of flying a, this, again, everything in rocket science is compromised because now you have things like people on console time, all the people that are, you know, on comms and working on the rocket, going down to the pad, you know, filing paperwork, doing range control, making sure there's not planes and boats in the way, flight termination. You have all these fixed costs for any launch. I don't care how big the rocket is, there's a relatively fixed cost. So now you say like, okay, I'm going to be paying, well, let's just make a win over. I'm going to pay $5 million to fly a rocket between all the people going on site, all the propellant, all the licenses, blah, blah, blah. If your fixed cost is $5 million, you can put 300 kilograms in space versus you have a $5 million cost of operation and you can put 5,000 kilograms into space. Like it, the business case is going to send you </s>

<s>[INST] even though like actually, so there's different ways to measure impact on the world of ideas in the world of ideas and also, yeah, in the world of ideas, it's kind of like the clubhouse thing Now, even if the audience is not large, the people in the audience are very interesting as it's like the conversation feels like there has long lasting impact among among the people who in different in desperate industries that are also then starting their own conversations and all that [/INST] kind of because you have other, so like, so like self publishing the book, um the goals that would solve you have much better ways of getting to those goals might be part of it, right? So if there's the financial aspect of what you get to keep more of it, I mean the podcast is probably gonna crush what the book is gonna do anyways, right? Yeah, if it's uh wanna get directly to certain audiences or crowds, that might be harder through a traditional publisher, there's better ways to talk to those crowds. It could be on columbus with all these new technologies, self published books, not going to be the most effective way to find your way to a new crowd, but if the idea is like, I want to have a leave a dent in the world of ideas, then they have a vulnerable old publisher, you know, put out your book in a nice hardcover and do the things they do that goes a long way and they do do a lot. I mean there's it's it's very difficult actually, there's so much involved in </s><s>[INST] putting together a book, they get books into bookstores and all that kind [/INST] of stuff, all this. And from an efficiency standpoint, I mean, just a time involved in trying to do this yourself is </s><s>[INST] there no process, right? Like you [/INST] said they have a process, you've got a process. I mean I know like Jacko did this recently started his own imprint and I have a couple other but it's a huge overhead. I mean if you like if you run a business and you so like Jaco is a good case study right? So he got you know fed up with Simon and Schuster dragging their feet and said I'm gonna start my own imprint then if you're not gonna publish my kid's book. Um But he what does he do? He runs businesses right. So I think in his world like I already run I'm I'm a partner and whatever in origin and I have this and that. And so it's like yeah we can run businesses that's what we know how to do. That's what I do. I run businesses. I have people but for like you or I we don't run businesses would be terrible. Yeah </s><s>[INST] well especially these kinds of businesses right? So I do want to launch a business. Very different technology business [/INST] is very very different. Very very different. Yeah I mean this is like okay and you copy editors and and graphic book binders and I need to contract with the printer but the printer doesn't have slots and so now I have to try to I mean it's </s><s>[INST] I guess so I need to shut this off in my brain but I get so frustrated when the system could clearly be improved. It's the thing that you're mentioning. It's like this is so inefficient every time I go to the D. M. V. Or something like that. You think like this could be done so much better. Uh But you know in the same thing as the worry with with an editor which I guess would come from the publisher who would who would uh how much supervision on your book did you receive? Like hey do you think this is too long or do you think the tight like title? How much choice do you have in the title? In the cover in the presentation of the branding and all that kind [/INST] of stuff? Yeah. I mean all of it depends, right? So when it comes on uh the relationship on the with the editor on the writing it depends on the editor and it depends on you. It's like at this point I'm on my seventh book and I write for a lot of major publications and at this point I have what I feel like as a voice that I've a level of craft that I'm very comfortable with. Right? So my editor is not going to be, She kinda is going to trust me and it's gonna be more big picture like uh I'm losing the thread here or this seems like it could be longer. Whereas the first book I wrote when I was 21, I had notes such as you start a lot of sentences with. So uh you don't use any contractions because I've been doing scientific writing, use contractions like you should probably use contractions. It was way more, you know, I had to go back and rewrite the whole thing. </s><s>[INST] But ultimately the recommendation, I mean we talked offline and sort of, I was thinking loosely not really sure, but I was thinking of writing a book and there's a kind of desire to go self publishing, not for financial reasons. [/INST] And the money can be good by the way. Right? I mean, it's very it's very power law type just distributed. Right? So, so the money on a hard cover somewhere between one or $2 a book. </s><s>[INST] So the thing is I [/INST] personally don't, but do you give up 15% of the agent? </s>

<s>[INST] the following is a conversation with Stuart Russell. He's a professor of computer science at UC Berkeley and a co author of a book that introduced me and millions of other people to the amazing world of ai called artificial intelligence and modern approach. So it was an honor for me to have this conversation as part of M. I. T. Course and artificial general intelligence and the artificial intelligence podcast. If you enjoy it, please subscribe on youtube itunes or your podcast provider of choice. Or simply connect with me on twitter at lex Friedman spelled F R I D. And now here's my conversation with Stuart Russell. [/INST] So </s><s>[INST] You've mentioned in 1975 in high school, you've created one of your first ai programs that play chess. Were you ever able to build a program that beat you at chess or another board game? [/INST] Uh So my program never beat me at chess. I actually wrote the program at Imperial College. So I used to take the bus every Wednesday with a box of cards, this big uh and shove them into the card reader. And they gave us eight seconds of CPU time. It took about five seconds to read the cards in and compile the code. So we had three seconds of CPU time, which was enough to make one move, you know, with a not very deep search and then we would print that move out and then we have to go to the back of the queue and wait to feed the cards. And again, How </s><s>[INST] deep was the search are we talking about? So [/INST] now I think we got we got an eight move, you know, deplete um with alpha beta and we had some tricks of our own about move ordering and some pruning of the tree. And </s><s>[INST] but you were still able to beat that program. [/INST] Yeah, yeah. I was a reasonable chess player in my youth. I did in a fellow program uh and a background program. So when I got to Berkeley, I worked a lot on what we call matter reasoning, which really means reasoning about reasoning. And in the case of a game playing program, you need to reason about what parts of the search tree you're actually going to explore because the surgery is enormous or bigger than the number of atoms in the universe. And and the way programs succeed and the way humans succeed is by only looking at a small fraction of the search tree. And if you look at the right fraction you played really well. If you look at the wrong fraction, if you waste your time thinking about things that are never going to happen, the moves and no one's ever going to make, then you're going to lose because you won't be able to figure out the right decision. So that question of how machines can manage their own competition, how they, how they decide what to think about is the meta reasoning question. We developed some methods for doing that. And very simply a machine should think about whatever thoughts are going to improve its decision quality. We were able to show that both for a fellow which is a standard to play a game and for backgammon, which includes uh dice roll. So it's a two player game with uncertainty for both of those cases. We could come up with algorithms that were actually much more efficient than the standard alphabet, a search which chess programs at the time were using and that those programs could beat me and I think you can see The same basic ideas in Alphago and Alpha zero today. The way they explore the tree is using a form of matter reasoning to select what to think about based on how useful it is to think about it. </s><s>[INST] Is there any insights you can describe without greek symbols of how do we select which paths to go down? [/INST] There's really two kinds of learning going on. So as you say, Alphago learns to evaluate board position. So it can it can look at a go board and it actually has probably a superhuman ability to instantly tell how promising that situation is. To me, the amazing thing about Alphago is not that it can be the world champion with its hands tied behind his back. But the fact that if you stop it from searching altogether. So you say, okay, you're not allowed to do any thinking ahead, You can just consider each of your legal moves and then look at the resulting situation and evaluate it. So what we call a depth one search. So just the immediate outcome of your moves and decide if that's good or bad. That version of Alphago can still play at a professional level, Right? And human professionals are sitting there for 5, 10 minutes deciding what to do. And alphago in less than a second can instantly into it. What is the right move to make based on its ability to evaluate positions? Um and that is remarkable because you know, we don't have that level of intuition about go. We actually have to think about the situation. So anyway, that capability that Alphago has is one big part of why it beats humans. The other big part is that it's able to look ahead. 40, 50 60 moves into the future. And You know, if it was considering all possibilities, 40 or 50 or 60 moves into the future, that would be You know, 10 to the 200 possibilities. So way, way more than atoms in the universe and so on. So it's very, very selective about what it looks at. So let me try to give you an intuition about how you decide what to think about is a combination of two things. One is how promising it is, right? So if you're already convinced that a movie is terrible, there's no point spending a lot more time convincing yourself that it's terrible because it's probably not going to change your mind. So the real reason you think is because there is some possibility of changing your mind about what to do, right, and is that changing your mind that would result than in a better final action in the real world? So that's the purpose of thinking is to improve the final action in the real world. And so if you think about a move that is guaranteed to be terrible, you can convince yourself it's terrible, you're still not going to change your mind, right? But on the other hand, you suppose you had a choice between two moves. One of them you've already figured out is guaranteed to be a draw, let's say, and then the other one looks a little bit worse, like it looks fairly likely that if you make that move, you're going to lose. But there's still some uncertainty about the value of that move, there's still some possibility that it will turn out to be a win, right, then it's worth thinking about that. So even though it's less promising on average than the other move, which is guaranteed to be a draw, there's still some purpose in thinking about it because there's a chance that you'll change your mind and discover that in fact it's a better move. So it's a combination of how good the move appears to be and how much uncertainty there is about its value, the more uncertainty, the more it's worth thinking about, because it's a higher upside if you want to think of it that way, </s>

<s>[INST] Yeah, you [/INST] want to be in that position, there's no there's no amount of money where I would want to be in that position. So that takes an enormous fortitude and a moral compass that he has, and that's what I think people need to need to appreciate about that guy. It's </s><s>[INST] Also on the first number, he said it's confusing that there's 50 people or 10 people like that are put in the position to have that level of impact. It's on, it's unclear that that has to be that way. It seems like there could be much more, [/INST] there should be, there's definitely people with the potential. Um but you know, think about, think about his journey. You know, his mom had to leave a very complicated environment, moved to Canada moved to Toronto, you know, a small apartment uh just north of Bay and Bluer, you know, if you've ever been to Toronto, I remember talking to her about this apartment is so crazy because I used to live like around the corner from that place and raise these three kids and just have to, so how many people are going to start with those boundary conditions? You know, and really grind it out. It's just very few people in the end that um will have the resiliency to stick it through, where you don't give into the self doubt. And so it uh you know, it's a really, it's just a really hard set of boundary conditions where you can have 50 or 100 of these people. That's why they needed to be really, they need to be really appreciated. Yeah, </s><s>[INST] well that's true for all humans that follow the threat of their passion and do something beautiful in this world that could be on a small scale or big scale appreciation is uh, that's a gift you give to the other person, but also a gift to yourself that somehow it becomes like this contagious thing. [/INST] I went to this, you are so right, you just like my brain just lit up because yesterday I went to an investor day of my friend of mine, um described brad Gerstner and you know, on the one very reductive world brad and I are theoretically competitors, but we're not, he makes his own set of decisions, I make my own set of decisions. We're both trying to do our own view of what is good work in the world, but he's been profoundly successful and it was really the first moment of my adult life where I could sit in a moment like that and really be appreciative of his success and not feel less than and so, you know, little selfishly for me, but mostly for him as well, I was so proud to be in the room that's my friend, that guy plays poker with me every thursday, he is crushing it. It's awesome, you know, and that's the, it's a really amazing feeling. I </s><s>[INST] mean, to, to linger on the, the trade offs, the complicated trade offs with all of this, what's your take on work life balance in a, in a company that's trying to do big things. [/INST] I think that you have to have some very, very strict boundaries, but otherwise I think balance is kind of dumb. It will make you limited. I think you need to immerse yourself in the problem, but you need to define that immersion with boundaries. So if you, you know, if you ask me like, you know, what does like my process look like it's monotonous and regimented, but it's all the time, except when it's not, and that's also monotonous and regimented. Um, and I think that makes me very good at my craft because it gives me what I need to stay connected to the problem without feeling resentful about the problem. Which </s><s>[INST] part, the monotonous all in nature of it or the, when you say hard boundaries essentially [/INST] go </s><s>[INST] all out until you stop and you don't stop often. [/INST] I'm in a little bit of a quandary right now because I'm trying to redefine my goals and you're catching me in a moment where I have, even in these last few years of evolution, think I've made some good progress, but in one very specific way, I'm still very reptilian and I'm trying to let go. </s><s>[INST] Exactly, you know, in [/INST] my business, it really gets reduced to what is your annual rate of compounding. That's my demarcation, you know, Steph curry and Lebron James Michael Jordan's, it's, how many points did you average? Not just in a season but over your career, you know, and, and in their case to really be the greatest of all time, it's points, rebounds, assists, steals. There's all kinds of measures to be, you know, in that pantheon of being really, really good at your craft. Um, and in my business it's very reductive. It's how well have you compounded and if you look at all the heroes that I have put on a pedestal in my mind, um, They've compounded, you know, at above 30% for a very long time as have I, but now I feel like I really need to let go because I think I know how to do the basics of my job. And if I had to summarize like an investing challenge or investing, I think really it's, you know, when you first start out investing, you're a momentum person, you saw it in Gamestop, just a bunch of people raping each other and then it goes from momentum to you start to think about cash flows, you know, how much profit is this person gonna make, whatever. So that's like the evolution, you know, this is the, this is the basic thing to, this is a reasonably sophisticated way, then a much smaller group of people think about it in terms of macro geopolitics. But then a very finite few cracked the special code, which is, there's a philosophy and it's the philosophy that creates the system. And I'm scratching at that furiously. But I cannot break through and I haven't broken through. And I know that in order to break through I gotta let go. So this is the journey that I'm in as in my, in my professional life. So it is an all consuming thing. But I'm always home for dinner. You know, we have very prescribed moments where we take vacation the weekends. You know like if I, if I can tell you about my week, if you're curious. But it's like </s>

<s>[INST] It's totally not. We're definitely gonna have to find that picture and overlay it, big full screen, slow motion. All right, let's talk about aliens. We'll find places we disagree and places we agree, life, intelligence, consciousness, universe, all of that. Let's start with a tweet from Neil deGrasse Tyson stating his skepticism about aliens wanting to visit Earth. Quote, how egocentric of us to think that space aliens who have mastered interstellar travel across the galaxy would give, pardon the French, would give a shit about humans on Earth. So let me ask you, would aliens care about visiting Earth, observing, communicating with humans? Let's take a perspective of aliens, maybe Sarah first. Are we interesting in the whole spectrum [/INST] of life in the universe? I'm completely biased, at least as far as I think right now we're the most interesting thing in the universe. So I would expect based on the intrinsic curiosity that we have and how much I think that's deeply related to the physics of what we are, that other intelligent aliens would wanna seek out examples of the phenomena they are to understand themselves better. And I think that's kind of a natural thing to want to do. And I don't think there's any kind of judgment on it being a lesser being or not. It's like saying you have nothing to learn by talking to a baby, you have lots to learn probably more than you talking to somebody that's 90. So, yeah. </s><s>[INST] So I think they absolutely would. So whatever the phenomena is that is human, there will be an inkling of the same kind of phenomena [/INST] within alien species, and that would be seeking that same. I think there's gotta be some features of us that are universal. And I think the ones that are most interesting, and I hope I live in an interesting universe, are the ones that are driven by our curiosity and the fact that our intelligence allows us to do things that the universe wouldn't be able to do </s><s>[INST] without things like us existing. We're gonna define a lot of terms. One of them is interesting. Yes. That's a very interesting term to try to define. [/INST] Lee, what do you think are humans interesting for aliens? Yes. Well, let's take it from our perspective. We want to go find aliens as a species quite desperately. So if we put the show on the other foot, of course we're interesting. But I'm wondering, and assuming that we're at the right technological capabilities to go searching for aliens, then that's interesting. So what I mean is, if there needs to be a massive leap in technology that we don't have, how will aliens prioritize coming to Earth and other places? But I do think that they would come and find us, because they'd want to find out about our culture, what things are universal. What about, I mean, I'm a chemist. So I would say, well, is the chemistry universal, right? Are the creatures that we're gonna find making all this commotion, are they made of the same stuff? What does their science look like? Are they off planet yet? I guess there's, so I think that Neil deGrasse Tyson is being slightly pessimistic and maybe trying to play the tune that the universe is vast and it's not worth them coming here. I don't think that, but I just worry that maybe we don't have the ability to talk to them. We don't have the universal translator. We don't have the right physics. But sure, they should come. We are interesting. I want to know if they exist. It would make it easier if they just came. </s><s>[INST] So again, I'm gonna use your tweets like it's Shakespeare and analyze it. So Sarah tweeted, thinking about aliens, thinking about aliens. So how much do you think aliens are thinking about other aliens, including humans? So you said we humans want to visit, like we're longing to connect with aliens. Why is that? Can you introspect that? Is that an obvious thing that we should be, like what are we hoping to understand by meeting aliens? Exactly. Asking as an introvert, it's like, I ask myself this all the time, why go out on a Friday night to meet people? [/INST] What are you hoping to find that? I'm thinking curiosity. So when I saw Sarah put that tweet, I think I answered it actually as well, which was we are thinking about trying to make contact. So they almost certainly are, but maybe there's a number of classes. There are those aliens that have not yet made contact with other aliens, like us. Those aliens have made contact with just one other alien and maybe it's an anti-climax in slime. Right? And aliens have made contact with not just one set of intelligent species, but several. That must be amazing actually. Literally, there are some places in the universe there must be one alien civilization to not make contact with not one, but two other intelligent civilizations. So they must be thinking about it. There must be entire degree courses on aliens thinking about aliens and cultural, </s><s>[INST] universal cultural norms. Do you think they will survive the meeting? And by the way, Lee did respond saying, that's all the universe wants. So Sarah said, thinking about aliens thinking about aliens Lee said, that's all the universe wants. And then Sarah responded cheeky universe we live in. So cheeky is a cheeky version of the word interesting, all of which we'll try to define mathematically. [/INST] Cheeky might be harder than interesting. Cause there's humor in that too. </s><s>[INST] Yes. I think there's a mathematical definition of humor, but we'll talk about that in a bit. Oh, interested. Yeah. Yeah, so if you're a graduate student alien looking at multiple alien civilizations Do you think they survived the encounters? [/INST] I think there's a tendency to anthropomorphize a lot of discussions about alien life, which is a really big challenge So I usually when I'm trying to think about these problems. I don't try to think about Us as humans, but us as an example of phenomena that exists in the universe that we have yet to explain and It doesn't seem to be the case that if I think about The features I would argue are most universal about that phenomenon that there's any reason to think that a first encounter with another lineage or Example of life would be antagonistic I think Yeah, and and I think there's this kind of assumption I mean going back to Neil deGrasse Tyson's quote I mean it kind of bothers me because there's a I mean I'm a physicist So I I know we have a lot of egos about how much we can describe the world But that there's this like because we understand fundamental physics so well we understand alien life and we can kind of extrapolate and I just think that we don't and the quest there is really You know really to understand something totally new about the universe and that thing just happens to be us. I agree I agree. There's something else more profound. I think Neil was just being again. He's just trying to stir the pot I would say from a contingency point of view, I want to know how many ways does the universe build structures, build memories, right? And then I want to know if those memories can interact with each other. And if you have two different origins of life and then origins of intelligence, and then these things become conscious, surely you want to go and talk to them and figure out what common analyses you share. And it might be that we're just unable to conceive of what they're going to look like they're just going to be completely different, you know, infrastructure. But surely we'll want to go and find out a map. And surely curiosity is a property that evolution has made on Earth. And I can't see any reason that it won't happen elsewhere, because curiosity probably exists because we want to find innovations in the environment. We want to use that information to help our technology. And also, curiosity is like planning for the future. Are they going to fight us? Are we going to be able to trade with them? So I think that Neil's just, I don't know, maybe, you know, I mean, give a shit. That's really, I think that's really down on Earth, right? How would aliens categorize humans, do you think? How would we? So let's put the other way around. Slime category? Maybe, no, no, no. We, maybe we could, the thing is a bit odd, right? Look at Instagram, Twitter, all these people taking selfies. I mean, does the universe, is the ultimate state of consciousness, thinking beings that take photographs themselves, and upload them to an interwe the driving force of why we have our technology, right? If we weren't curious, we wouldn't have left the cave. So I think that Neil's got it completely wrong, in fact. Actually, of course they'd want to come here. It doesn't mean they are coming here. We've seen evidence for that. I guess we can argue about that, right? But I think that we want, I desperately, I know that Sarah does too, but I won't speak for you. You're here, you can, I desperately want to have missions to look for life in the solar system right now. I want to map life over the solar system, and then I want to understand how we can go and find life as quickly as possible at the nearest stars, and also at the same time do it in the lab, just to compensate, you know? So sure, right? Yeah, I just want more point on this. If you think about sort of what's driven the most, like features of our own evolution as a species, you could, and try to map that to alien species. I always think like optimism is what's going to get us furthest. And so I think a lot of people always think that it's like war and conflict is going to be the way that alien species will expand out into the cosmos. But if you just look at how we're doing it and how we talk about it, it's always our future in space is always, you know, built from narratives of optimism. And so it seems to me that if intelligence does get out in the universe, that it's going to be more optimism and curiosity driving it than war and conflict because those things end up crushing you. So there might be some selective filter. Of course, this is me being an optimist. </s>

<s>[INST] Are you supposed to be almost like converting towards the thing you're thinking, like constantly? [/INST] Are you supposed to say what you're thinking? If it feels right in the moment, you can. The thing is it's very amorphous, right? It's like almost like creating a magical sensation. And I've been with some, I've seen some very good circulars, really high-skill circle. And I feel like I'm on drugs when that happens. </s><s>[INST] It's very rare to see. Does it feel honest somehow? [/INST] Yeah, yeah, very honest. Like right now in this moment, I'm feeling like kind of like nervous energy because I'm talking to you and this is a unique situation. And like, I want you to think I'm cool. I want everybody listening to me to think I'm cool. But I'm also having some sort of delight at being able to express in this way, and like some admiration for how you like setup and built this thing that I can be a part of. And all of these things are sort of in my body right now </s><s>[INST] as it's sort of vibrating high thing. I remember like in the party setting, cause I've had to talk to a few people. [/INST] I felt like it was going sexual very quickly. Okay, I don't know if you remember this, but the first time I met you, I didn't know who you were. I just heard, I knew I'd heard your name. Like you'd just hear your name. And I'm like, I think I've heard people discuss that. It's true. And I was in the middle of a very sexual conversation with another woman. Oh you were. Yeah it was. And you just like turned around and left very shortly afterwards, and I thought it was great. </s><s>[INST] Oh you were. Oh was I listening in on the conversation [/INST] or something like that? It was like I was talking to her and you were kind of like right there and so we introduced ourselves and then we continued on with the conversation. Oh delicious. And you were standing there and listening. </s><s>[INST] Yeah. Stop. I don't think I would have left the cut. So it's funny you probably interpreted it in a different way. [/INST] I interpret it as you not wanting to listen </s><s>[INST] to like graphic sexual stuff. [/INST] Was it super graphic? I don't know, I was asking her about, I was doing, I was interviewing her about her fetish, basically. </s><s>[INST] Oh yeah, I don't think I would have walked away from that. I would have been like curious, oh, interesting, because I don't often see people having a deep interview about fetishes. Like I wouldn't even be, listen, I'm like Jane Goodall here. I'm not like, I'm not afraid of sexuality or something like that, I just have certain values in terms of like monogamy and so on. But I think sexuality is really beautiful, yeah. I don't think, yeah, I can't imagine myself walking away from that conversation. [/INST] Okay, somebody must've like called you or something, I just don't remember exactly how it worked. I just remember thinking later on. Or maybe I thought I was intruding. </s><s>[INST] Oh, maybe. [/INST] Because if. I was kind of drunk, so. And I was probably was very drawn to it. </s><s>[INST] Okay. And I probably was very drawn to it. I would like to actually have like footage of that conversation can actually interpret what actually happened, because it's probably, I mean, human interactions are funny like that. They can happen for all kinds of reasons. [/INST] Have you ever fallen in love with a client? </s><s>[INST] No, I mean, like in tiny ways, like micro loves. [/INST] Have you ever fallen in love love? I mean, I don't know what it means, but probably. The thing that other people say when they say fall in love </s><s>[INST] is probably something I've experienced. What do you think they mean? What is love? Ayla? [/INST] Yeah, I know. No, no. It's a fantastic question. I think, so love is one of those words that refers to like a billion different concepts and I think we maybe should just taboo the term to have a better understanding of what we're referring to. Cause there's things like a feeling of intense attachment. There's something feeling like soulfully aligned. There's like sexual attraction. There's like excitement. </s><s>[INST] Are you talking to me and saying we should taboo the term love in this conversation? How dare you? No, uh, well, okay, romantic love. [/INST] To make it flourish into lots of other new definitions. </s><s>[INST] Okay, thank you. We're expanding love. It sounds like you're censoring the most important word. This is like 1984 all over again. Okay, also on the book reading list. No, okay. Listen, no, romantic love, like a deep intimacy for somebody like a deep connection with a human being that is also, I mean, yeah, with polyamory it's tricky and your relationship with sex is also tricky. So like what's the difference between a deep friendship [/INST] and a friendship that also has a sexual component? We're expanding love. I remember being very confused about that when I did a lot of LSD. I was like, what? The line between romantic relationships and everything else kind of got blurred. I was like, oh, I'm just like in intimacy. Some intimacies mean that you spend your life together more and have sex, but like the same basic thing is there. </s><s>[INST] Like you're seeing someone for like who they are. Do you think you can be, if you're heterosexual, do you think you could be really deeply close with friends [/INST] with a guy and not have sexual relationships with him? I assume it's possible. Like if anything is ever possible, then probably, yeah. </s><s>[INST] Everything is possible, time travels is possible. Quantum mechanics makes every, traveling faster than the speed of light is possible. According to general relativity, everything's possible. So you're saying there's a chance I'm a dumber has taught mech [/INST] that everything is fucking possible. Everything is fucking possible. not super likely, assuming that they are </s>

<s>[INST] the following is a conversation with Peter Abeel. He's a Professor UC Berkeley and the director of the Berkeley robotics learning lab. He's one of the top researchers in the world working on how we make robots understand and interact with the world around them, especially using imitation and deeper enforcement learning. This conversation is part of the M. I. T. Course and artificial general intelligence and the artificial intelligence podcast. If you enjoy it, please subscribe my youtube itunes or your podcast provider of choice or simply connect with me on twitter at lex Friedman spelled F. R. I. D. And now here's my conversation with Peter a bill. [/INST] You've </s><s>[INST] mentioned that if there was one person you could meet, you'll be Roger Federer. So let me ask, when do you think we'll have a robot that fully autonomously can be Roger Federer, a tennis roger federal level player at tennis? [/INST] Well first if you can make it happen for me to meet Roger, let me know um in terms of getting a robot to um beat him at tennis, it's kind of an interesting question because for a lot of the challenges we think about an ai the software is really the missing piece but for something like this, the hardware is nowhere near either. Like to really have a robot that can physically run around the boston dynamics, robots are starting to get there but still not really human level ability to run around and then swing a racket. </s><s>[INST] You think that's a hardware problem. [/INST] I don't think it's a harder problem only. I think it's a hardware and a software problem. I think it's both and I think they'll they'll have independent progress. So I'd say the hardware maybe in 1015 years </s><s>[INST] I'm not grass. [/INST] I mean we're sliding. Yeah, well they're playing and I'm not sure what's harder grass or clay. The clay involves sliding which might be harder to master actually. Yeah, </s><s>[INST] but you're not limited to uh bipedal, I'm sure we [/INST] can build a machine. It's a whole different question. Of course, if you can if you can say, okay, this robot can be on wheels, it can move around on wheels and can be designed differently. Then I think that that can be done sooner probably than a full humanoid type of setup. </s><s>[INST] What do you think swing a racket? So you've worked at basic manipulation. How hard do you think is the task of swinging A racket would be able to hit a nice backhand or forehand? [/INST] Let's say let's say let's say we just set up stationary, a nice robot arm, let's say, you know, standard industrial arm and you can watch the ball come and swing the racket. It's a good question. I'm not sure it would be super hard to do. I mean I'm sure it would require a lot if we do it with reinforcement any would require a lot of trial and error. It's not going to swing it right the first time around. But yeah, I don't I don't see why I couldn't So you think it's the right way? I think it's laughable. I think if you set up a ball machine, let's say on one side and then a robot with a tennis racket on the other side. I think it's learn able and maybe a little bit of pre training and simulation. Yeah, I think that's I think that's feasible. I think I think they're swinging the racket is feasible would be very interesting to see how much precision it can get. Because I mean that's that's where, I mean some of the human players can hit it on the lines which is very high </s><s>[INST] precision with spin. This is an interesting uh whether RL can learn to put a spin on the ball. [/INST] Well you got me interested, maybe someday we'll set this up your butt. </s><s>[INST] Your answer is basically okay for this problem. It sounds fascinating, but for the general problem of a tennis player we might be a little bit farther away. What's the most impressive thing? You've seen a robot doing the physical world? [/INST] So physically for me it's the boston dynamics videos always just bring home and just super impressed. Recently, the robot running up the stairs during the parker type thing. I mean, yes, we don't know what's underneath, They don't really write a lot of detail, but even if it's hard coded underneath, which might or might not be just the physical abilities of doing that parkour? That's very impressive. </s><s>[INST] So a lot right there. Have you met spot many or any of those robots in person [/INST] that spot many last year in april at the MArs event that Jeff Bezos organizers, they brought it out there and it was nicely falling around Jeff when Jeff left the room, they had followed him along, which is pretty impressive. </s><s>[INST] So [/INST] I think </s><s>[INST] there's some confidence to know that there's no learning going on on those robots, the psychology of it. So while knowing that while knowing there's not if there's any learning going out, it's very limited. I met spot many earlier this year and knowing everything that's going on, having one on one interaction. So I got to spend some time alone and there's a immediately a deep connection on the psychological level, even though you know the fundamentals how it works, there's something magical. So do you think about the psychology of interacting with robots in the physical world even you just showed me uh the pr to the robot and and there's a little bit something like a face, had a little bit something like I faced. There's something that immediately draws you to it. Do you think about that aspect of the robotics problem? [/INST] Well, it's very hard with bread here. We'll give him a name Berkeley robot for the elimination of tedious task. It's very hard to not think of the robot as a person and it seems like everybody calls them a he for whatever reason. But that also makes it more a person than if it was it. And it's it seems pretty natural to think of it that would this past we can really struck me, I've I've seen Pepper many times on on videos, but then I was at an event organized by this was by Fidelity and they had scripted Pepper to help moderate some sessions and had scripted pepper to have the personality of a child a little bit. And it was very hard to not think of it as Its own person in some sense because it was just kind of jumping, it would just jump into conversation, making very interactive moderately to see in the paper would just jump in, hold on. How about me uh can I participate in this doing it just like okay this is like like a person and that was 100% scripted and even then it was hard not to have that sense of somehow there is something there. </s>

<s>[INST] and ultimately have that long term impact. I wonder if this is scalable to, because that's such a great metric for education, not how to get an A on the test. Uh, but how to have, how to be on the cover of new york times for inventing something new. Do you think that's general Izabal to education beyond just this particular Olympia, like it's even you're saying this feels like a rare statement, almost like a radical statement as a goal for education. [/INST] So actually, the way I teach my classes at Carnegie Mellon, which I will admit right away is not equivalent to the average in the world, but it's already not, It's already not just the top 60 in the country as picked by something. Um let me just explain, I have exams in my class which are 90% of the great, so the exams of the whole thing are most of the whole thing. And the way that I let students prepare for the exams is I show them all the problems I've ever given on the previous exams and the exam that they will take is open notes. They can take all the notes they want on the previous problems. And the guarantee is that the exam problems this time we'll have no overlap with anything. You have seen me given the past as well as no overlap with anything I taught in the class. So the entire exam is invention, wow. But that's how I go write my, my point is I have explained to people when I teach you, I don't want you to have remembered a method I showed you. I want you to have learned enough about this area. That if you face a new question which I came up with the night before by thinking about like what could I ask that I have never asked before. Oh, that's cute. I wonder what the answer is. Uh That's an exam problem. That's exactly what I do before the example and then that's what I want them to learn. And the first exam, usually people have a rough time because it's like what, what kind of crazy classes that the professor doesn't teach you anything for the exam. But then by the second or third. And by the time they finished the class they have learned how to solve anything in the area, how to invent, how to invent in that area. Yeah. </s><s>[INST] Can we walk back to the mathematical olympics? What's the scoring and format like? Uh and also what does it take to win? [/INST] So the way it works is that each of the six students Uh do the problems and there are six problems. All the problems are equally weighted, so each one is worth seven points. That means that your maximum score is six problems times seven points, which is the nice number of 42. Uh and now the way that they're scored by the way is there is partial credit. So the question is asking you explain why this weird fact is true. Okay, if you explain why you get seven points, if you make minor mistake, maybe you get six points. But if you don't succeed in explaining why. But you explain some other true fact which is along the way of proving it, then you get partial credit. And and actually now this is tricky because how do you score such a thing. It's not like it was the answer was 72 you wrote 71 it's close right? The answer is 72 you wrote 36. Oh but that's pretty close because you you know that maybe you're just off, by the way they're not numerical anyway, but I'm just giving some numerical analog to the way the scoring might work. They're all essays and that's where I guess I have some role as well as some other people who helped me in the U. S. Delegation for coaches. Uh We actually debate with the country which is organizing it, the country which is organizing the Olympia brings about 50 people to help charge the written solutions. And you you schedule these half hour appointments where the delegation from one country sits down at the table like this opposite side is two or three people from the host country. And they're just looking over these exam papers saying well how many points is this worth based on some rubric that has been designed and this is a negotiation process, we're not we're not trying to bargain and get the best score we can. In fact sometimes we go to this table and we will say we think we want less than what you gave us. This is how this is how are these are our principles if you give us too much, we say no, you give us too much. We do that. However the reason why this is an interesting process is because if you can imagine every country which is participating has its own language. And so if you're trying to grade the Mongolian scripts and they're written in Mongolian. Uh If you don't read Mongolian which most people don't then the coaches are explaining to you this is what the student has written. It's actually quite interesting process. </s><s>[INST] It's almost like uh like a jury you know you have you have uh in the american legal system you have a jury that where they're deliberating but unlike a jury there's the members of the jury is speaking different languages sometimes. Yes fascinating. But uh I mean it's hard to know what to do because it's probably really really competitive but your sense is that ultimately people like how do you prevent manipulation [/INST] here? Right well we just hope that it's not happening. So so we write in english therefore everything that the U. S. Does. Everyone can look at it. It's very hard it's very hard for you to manipulate. We don't manipulate. We only hope that other people aren't. But at the same time as you see our philosophy was we want to use this as a way to develop general talent. And although we do this for the six people who go to the international math Olympia we really want that everyone at any touched at any stage of this process. Get some skills that can help to contribute more later. </s>

<s>[INST] the following is a conversation with Will Sasso, a comedian, actor, podcaster and someone had been a fan of for many years since Mad tv in the late nineties to recently with the 10 minute podcast and now the new podcast called Dude See and now a quick few second mention of each sponsor. Check them out in the description. It's the best way to support this podcast. We've got eight sleep for naps, athletic greens, for multi vitamins, better help for mental health on it, for supplements and indeed for hiring, choose wisely my friends and now on to the full ad reads as always no ads in the middle. I find those ultra super annoying and since I get to decide how to do things with this particular podcast, I don't like to do annoying things but I still try to say interesting things sometimes, only half related to the sponsors so maybe you would like to listen but if you skip please still check out the sponsors. I enjoy their stuff. Maybe you will too. This episode is brought to you by eight sleep and its pod three mattress so I just took a nap. I feel incredible. I passed out for 20 minutes all on my eight sleep bed, both the mattress and the mattress cover a sleep. The surface of the mattress was cold to a perfect temperature with a warm blanket. I turned off like an old Pentium PC in a matter of seconds at turn back on like an old Pentium PC [/INST] with </s><s>[INST] sound actually took a really long time for those things to boot but it was always excitement, anticipation back in my day, we used to walk both ways uphill to get an image from the internet Anyway, you can get the pot three cover, you don't have to use their mattress, you can put the cover on your own mattress. It's all awesome whatever you do. It's awesome. I guarantee it, check it out and get special savings when you go to sleep dot com slash lex. [/INST] This </s><s>[INST] show is also brought to you by athletic greens and it's a G one drink which is an all in one daily drink to support better health and peak performance. I drink it twice a day. Sometimes I forget the travel packs when I'm traveling and I miss it. I look out the window and I wonder what is this all for? Why are we here? In fact, I do that with athletic greens too. But um, there's a little more zest to it with athletic [/INST] greens. </s><s>[INST] What am I even talking in these ads? I wonder if anyone's actually listening. Like I can literally say anything. [/INST] I </s><s>[INST] wonder if there's like just two people too drunk to skip as they're just listening to this right now. Well, I'm with you brothers and sisters. What was I talking about? I don't know, but you should check out athletic greens and you get a one month supply official when you sign up at athletic greens dot com slash lex And given this ad read that will very quickly cancel their support. I'm very sure know they love me. I love them no matter what, whether the response or not, I will always love athletic greens. [/INST] This </s><s>[INST] episode is also brought to you by better help spelled h E L P help. I often go in my mind to a place where I'm just sitting alone on a desert island. I imagine talking to that volleyball Wilson and just the piece of being away from humanity for a time. So you can be alone with your thoughts. I imagine that. And I also might imagine writing help in the sand when I'm too sick of my own thoughts. Speaking of being too sick of your own thoughts, That's just a funny thing to say. Of course your thoughts dark or beautiful, low or high are your lifelong companions and you should bring them to the surface and you should play with them, you should dance with them and talk therapy is one way to do that. I think podcast things that kind of talk therapy, that's the way to do that. So you should really try out and better help which is a way to do online talk therapy. You can check them out at better help dot com slash lex and save in your first month. This episode is also brought to you by on it, a nutrition supplement and fitness company. They make alpha Brain and you tropic that helps support memory. Mental speed and focus. Like I said, I just took a nap, that's a component number one of ultra focus, component number two for me is caffeine. Then of course there's the zen, like maybe people think of it as meditation ability to block out all the other distractions, but even then sometimes that's not enough if you really want to accomplish something difficult, mentally speaking and so for that I will take an alpha brain every once in a while to help me be the extra super boost for that deep work session. By which I mean sitting there staring at a thing, thinking about it and not allowing your mind to deviate from the focus on that thing. Any way you can get a special discount on alpha Brain at lex Friedman dot com slash on it. This show is also brought to you by indeed hiring website. I've used them many times many, many times in the past for the hiring efforts I've done for the teams that I've led teams have been a part of, I'm doing quite a bit of hiring now for the podcast. Creative kind of efforts a lot of us spend a lot of our day working on a thing. Hopefully it's a thing that you really enjoy doing when it's the thing you enjoy doing. There's to me at least nothing more rewarding than doing it with people you care about people that inspire you people that challenge you people that teach you stuff. So a great team is a beautiful thing. So I really, really care about good hiring tools, services, websites and indeed is um great at that. Anyway, I'm also hiring quite a bit for a lot of things I'm doing now. I'm a little bit behind schedule on that, but I will get to all the resumes quickly and I'm also using indeed as part of this effort, they have a special offer only available for a limited time. Check it out at indeed dot com slash lex. This is the lex Friedman podcast. The supported, please check out our sponsors in the description and now dear friends, here's Will Sasso, so let's call it the elephant in the room. You wore a black suit in a recent episode of Doozy. You wore a black suit again today Shakespeare. Then Mark Twain said, clothes make the man, uh what kind of man does the suit make you? [/INST] Well, me in particular, it makes me a fellow who did not get this dry cleaned in between because that episode of the show as we sit here now is around a week ago. So that's, that's the kind of man. It makes me </s><s>[INST] well, the nice thing is you're wearing pants I think [/INST] yes, I am wearing, I </s><s>[INST] don't think you're wearing pants in the episode. [/INST] That's correct. I I prefer to wear shorts, but this was a special occasion. So I'm wearing pants and I thought it fitting obviously to just wear, you know the black tie and uh clothes do make the man and I'm I would not consider myself to be a man of leisure but I do enjoy shorts because my legs get hot so that's what kind of man the shorts </s><s>[INST] make you wear a suit. [/INST] I fucking hate wearing suits. So </s><s>[INST] what is this a statement of uh is it ironic or is it are you honoring the gods of this particular podcast? [/INST] I'm honoring the gods of this particular podcast would be a good way to put it. Yes. No this is this is in in reverence of and in dedication to you and our newfound friendship here which we are making on the podcast. You and I just met everything that we're saying here is the first things that we're saying to each other. So I'm meeting you on common ground dressed like </s><s>[INST] well I've been actually a one way friend of yours for many, many years since Mad Tv when did you start on Mad T. So that was I mean in nineties [/INST] 97 90 </s><s>[INST] seven so I was a huge fan of yours and the cast was incredible. One of the funniest shows ever created your whole journey watching through. That was was incredible. From at T. V. 23 stooges to the podcast. The 10 minute pot and then the new podcast is incredible. Um [/INST] My </s><s>[INST] favorite role that you played was the mountain and the game of Thrones. What was it like working with dragons? [/INST] Well the dragons are usually tennis balls on the end of c stands but sometimes they they hang out. Um I am, it's like, you know, it's like a little like the thing you got the camera on here. </s><s>[INST] This is like yeah, [/INST] no, I understand. I'm trying to impress you with my film lingo. You know what a banana </s><s>[INST] is? You [/INST] walk like this, do a banana, </s><s>[INST] I take it back. I did not know what a banana [/INST] was. Yeah, because it's just a food, normally uh fancy </s><s>[INST] Hollywood folk, the lingo [/INST] and I'm uh my name is Bjorn Hap thor Bjornsson and I am seven ft four. And yeah, so dragon stone dragons don't scare me even though they've been extinct for awhile. You scientists writers that check out. </s><s>[INST] Yeah, I actually, I'm really into video games. I don't know if you play video games. There's a, there's a sky room video game that's part of the elder scrolls series and for the longest time there's a legend that there's dragons. I think it's starting a dagger fall. And so I always, I grew up playing those video games and dreaming of one day meeting a dragon in a virtual world and eventually you did in in Skyrim. So it's dragons represent don't know exactly what they represent but they represent maybe this kind of mythical creature that is bigger than anything. Humans can calm possibly comprehend. Maybe because they're so they're so they show up so often in myth from the, from the religious stories, you know, of the snake and so on the serpent. And I don't know what that is with this breathing fire. That's kind of weird. [/INST] It's interesting when I think about dragons because now that you bring it up, these are people that probably wouldn't have access to the fact that there used to be dinosaurs. Maybe they did if they didn't, they're drawing things that look like, you know, a dinosaur cousin. But cool that can breathe fire and has wacky wings and a spiked tail. Um Yeah where the heck did they come up with that? Because they're clearly of course represented in mythology all the way back to uh no not cave drawings were the Egyptians probably knew what the and they could time travel. So they would have gone back to the caves were </s><s>[INST] the aliens that placed living organisms on earth could time travel and they could plant legends into the, into the collective intelligence of the human species. [/INST] Yeah. And perhaps they were thinking of us to do something smart with it and we didn't, we just came </s><s>[INST] up with sky. Now [/INST] we're just sorry </s><s>[INST] that was very offensive. [/INST] I'm sorry. I don't mean that venue with your video game. I'm more of a burger burger time donkey kong dude. </s><s>[INST] Oh what is that? That's an original [/INST] burger time was an arcade game that later showed up on the in television. Um uh it was on television, I believe it was made by texas instruments, horrible first generation video game console and burger time. You just, it's like super Mario, you just got to stay away from the, the eggs and the pickles and stuff and you just go meet, meet, meet and the bun falls and then you go down to the in the cheese and then the meat, I'm not gonna say it's as complicated as Skyrim but uh took me a while to finish it when I was seven. </s><s>[INST] Did you play video games? That was that part of your life? A part of this source of happiness for you at all? [/INST] It was, it was, I played video games up until around uh I think in 2010 I got the red ring of death on my xbox three </s><s>[INST] 60, that was, that [/INST] was it. I never or whatever the Xbox was then. I had, I was playing uh I had finished the the grand theft auto that was out and finished the Red Dead redemption. So I was doing that thing where you just drive around uh you know the streets of new york or just ride around on your horse, shooting people and you know, throwing grenades into into groups of people in grand theft. </s><s>[INST] You're describing the same thing that happened a decade later because it's not Red Dead redemption two and there's still not a new grand theft auto. So [/INST] there isn't right, </s><s>[INST] yeah, they're working on it, they're always flirting with that idea, you know, who else plays Skyrim, another person, the two people I'm a huge fan of from that time on Mad tv is bobby lee, he's a huge fan of So what bobby lee loves to do is to grind do the boring task over and over, gather mushrooms in sky room, you can fight dragons, you can fight all kinds of things, but you can also gather mushrooms and different ingredients to make potions and all that kind of. He loves the ingredients that he's the, you know in the hunter gatherer world. He's the gatherer [/INST] gatherer. Yeah, I've heard him described that way and and he likes to describe himself that way. I worked with bobby not too long ago, he came and did a couple of days on this thing we were shooting and uh I was looking forward to catching up with my old pal and if you know anything about bobby lee, you'd probably be able to predict that he spent that entire time playing farming on his ipad. Well, </s><s>[INST] humans are a source of anxiety and trouble. So sometimes it's good to escape human interaction through video [/INST] games totally with </s><s>[INST] him on that. He is, he's one of the funniest people ever. What what what do you think is, what do you think makes them funny? It's just all the times you've worked with him, the non standard, non secular way of his being [/INST] bobby lee is one of the most raw people. Raw performers who lets it all hang out to the degree that he will even get naked in front of his audience. Which is usually a metaphor for someone doing stand up. I'm bearing all, I'm showing you everything and bobby will just pull his bird out of his pants. Yeah, I don't think he understands metaphor too much. He </s><s>[INST] embodies metaphor. [/INST] Yes, he embodies metaphor. He's the gathering. We call him the gathering metaphor bobby. The gatherer metaphor </s><s>[INST] is a metaphor for something else for somebody else's life. Someday he'll be in the dictionary. [/INST] Yeah, representing </s><s>[INST] some kind of concept. Maybe the metaphor itself [/INST] once, once this whole thing falls apart and we are climbing the kudzu vines that spiral up the Sears tower, like they say in fight club bobby will go back to his gathering form and be happy as a pig and shit. Just walking around the loincloth with his bird hanging out, cracking jokes to people and climbing up on them for a stool, lap dancer, Whatever. I'd </s><s>[INST] love to dig into something. He he did. You guys did a lot of great podcast together. He asked you in a very uncomfortable process of why you don't do stand up. So let me ask you, do you hate money. [/INST] Well I'm originally from Canada. Yeah, so I'm uh yeah, I'm I'm a freaking pinko socialist. Is that what where you come from? That's not a nice thing to say, </s><s>[INST] I thought the soviet union, that is a nice thing to say, like [/INST] a </s><s>[INST] is a good he's a good socialist. [/INST] Yeah, </s><s>[INST] red, [/INST] like </s><s>[INST] bold colors. Yeah, there was an interesting tension in your voice and the way you talked about it, there's just not a source of happiness for you. You you you respect the art form, but it was not something that you were connected to you. He felt connected to. [/INST] That's a good way to put it. Yeah, I, I respect the art form a lot. I, and I grew up with all the albums and stuff. I had an older brother and sister who so I, you know, we had the we had George Carlin, we had, you know, Richard Pryor, we had robert klein, we had Gilda live the Gilda Radner concert, we had, we had all sorts of stuff, but you know, I don't know, there's a lot of, there's a lot of reasons, I do feel like a career in show business Is, you know, they, it never goes the way you plan, like most things and I was fortunate enough to get started outside of my native Vancouver or in my native Vancouver, I grew up in the burbs outside and there was a lot of industry there, so I was fortunate enough to get started as an actor when I was like 16. So there there yeah, there was, there were some times early on where I came up with some stand up stuff and did it, but yeah, I quickly abandoned it and then, you know, you go through, you do mad tv and stuff and then and that's where my this is gonna sound weird. Do I sound as anxiety as I did when I was on bobby's podcast trying to avoid his questions? </s><s>[INST] Well he was giving you this face this whole time that was making the whole just atmosphere feel full of anxiety. So I'm trying not to give you the face the whole time I'm saying play cool, play cool, [/INST] okay uh Cool. You said it out loud a couple of times. I did, you know, you cut that out, play cool, play cool. Cut </s><s>[INST] out, cut it out, [/INST] maintain bro, here's what I'll say, there's two ways to do it. I think it's lame when someone who's done one thing for a while goes and starts doing stand up out of nowhere because I think it's an art form that's uh under attack because it's not like anything else you need. Although now you can of course, you know, make whatever you want, it's the era of self publishing, as far as making a product and putting it out there, which is getting easier of course, and I can't wait to talk to you about that with with ai and how it's changing art. Um but the in stand up, all you need is a is a microphone and you know perhaps it would be good to have some mental illness and then you can just run up there and uh, talk forever. And I say this to, to, you know, comedians, it's like, you guys have to deal with Justin influx of people who aren't sure why they're doing comedy. I would ask comedians and like, I mean, not good ones and good ones, you know what they're doing? But everyone else like, what are you doing? Why why you doing stand up? Having said that? I am allergic to money. </s><s>[INST] Yeah. Do you think they have a good answer for that? Why are they doing it? Because I actually, like when I'm in Austin, I like going to open mikes, just listening. It's inspiring to me both the funny and the unfunny people because they've been doing it for several years, sometimes over a decade and they're still at it, they're still right there, there's going for the punch and then especially open mics that are really sad and that there's, you know, only like five other people in the audience and they're usually just other comedians and they're still going all out as if they're in front of a stadium. But [/INST] that, to me sounds like someone who loves it. Yeah, I got no questions for that person. I got questions for someone who goes sideways from here, I'm recognizable doing something and then I'm doing stand up because it's like, and truly, look, I, I've been, I've been fortunate enough to be in the business for a long time, and at this point, if I came up, I mean, doing live stuff is fun. I have friends that are like, um, you know, some guys who are primarily sketch people or you would look at them and sketch people and they can sell tickets for being sketch people and they, and we'll talk about it and they're like, well, you know, I do a monologue and I do a little stand up, then I do a song, then I do another monologue and I play off the audience, do a little stand up. Um, but stand up is, it's almost like playing music in that, you know, people are going up there playing music, but what band have you been listening to? That's what you're gonna sound like. So it's really, I mean, of course I'm speaking from zero experience, but I've heard it takes years of course to find your own voice stand ups that when they first go up there, they're doing some sort of impersonation of so and so, and so, and so, and you gotta you gotta pop this audience that that's paying and you're gonna get run over by the next person who's coming up and uh it's hard to follow the last person who went up before you. And I, I mean, that is a really hard way to, it's a very, quite a gauntlet to begin to find your voice comedically, </s><s>[INST] but don't you have that same kind of thing with sketch, you still have to find your own voice with like all the impressions you do, they're just terrible, you know, they're, they're different spins and different people, they're not like perfect impressions, right? So they, that's, I mean that's a similar kind of challenging journey as stand up, you're just saying they're kind of distinct and you fell into this one, you fell in love with it, which is like, what mad Tv kind of opens you up to? [/INST] Yeah, as a kid, I literally wanted to be an actor, I always wanted to be an actor from a very young age, as far back as I can remember and I was the class clown and wanted to do comedy stuff and comedic acting </s><s>[INST] and [/INST] yeah, early on, my, my influences were very predictable list of guys from, from SCTV, early saturday night live monty python, all of those performers really influenced me. It was later that I saw people like Kevin Kline was an incredible actor. I vividly remember being like, 12, 13, seeing him get an Academy Award for Fish called wanda, and it blew my mind because I was like, he was hilarious. I mean, it was one of my favorite movies back then and now and uh he won an Academy Award and at that point, I, I started thinking more about acting and then I was like I said, really fortunate to fall in with um I mean I always wanted to do it and I was trying to hustle this and that when I was a kid and then I ended up getting represented and then I, I ended up on a teen show, I was on, I basically, the easiest way to pitch it is, it's like a Canadian, my so called life with these kids in their lives and stuff and I did that for like five years and I really love acting, I really, truly love acting and I don't, I'm not someone who wants people to know my opinion. So that's another thing about stand up, like I love the illusion of what I get to do in uh in uh entertainment and podcasting is great for that, but to stand up there and and for, I don't know, just for me it's like it would have to all be fantasy and yeah, </s><s>[INST] so Nietzsche said that every profound spirit needs a mask, like you said, you don't like to talk about in your comedy, you don't like to talk about stuff that's personal to [/INST] you? What </s><s>[INST] is that? What if you were to psychoanalyze yourself, do you think it's just not something you find funny or is it are you running from something? Um and it's not your fault? It's [/INST] not your fault will um </s><s>[INST] speaking of another really great comedic actor who's also a serious actor, Robin Williams, [/INST] one of the best serious actors, I mean, I mean I and you know, one of the funniest people of all time, but as great as incredible as he was, as a funny man, as a as a stand up and a performer. I almost like his his serious stuff better. </s><s>[INST] Can I ask you a question about that? What do you make of the that he committed suicide? [/INST] I think it's I think it's I mean, it's super depressing. I I've referred to him as like the jesus christ of depression. It's almost like he died for others, depression. You know what I mean? Like, </s><s>[INST] Yeah, [/INST] you look at someone like that and go, wait a minute, you're a rock star. Like you don't you could just check out if you're not liking your life. And of course, something like suicide begs that you look a little deeper and realize how tortured the human mind can can make someone </s><s>[INST] is there some aspect, you know, we're in L. A. Is there some aspect of celebrity that isolating that can make you feel really lonely? [/INST] Not me. I don't feel no, not really. You </s><s>[INST] feel the love? [/INST] No, I just feel like I'm not, I mean, it's like, I don't know, I've always kind of had a small group of friends and those people don't, you know, it's like I've known the same people for years and years, </s><s>[INST] you never really [/INST] know in L. A. It's hard to, it's hard for people, nobody cares, they see you and then the next minute they see so and so so it's like you know I'm the guy from that that mike and molly right, nope, nope close king of kings, you shave your head, you go bald, you king queens, know what I mean? So close your wow ship. You used to be the mountain on game of Thrones. You look like ship. What happened? You just eating fried dough? Um Yeah that's what's up. Can't lift any weights anymore. I'm at the gym doing like £15 with shoulder press ah And people coming up to me, the </s><s>[INST] man used to be, what's have there been low points in your life? Sorry to go there. [/INST] But uh yeah yeah everybody has a low point in life </s><s>[INST] to suffer from depression and those kinds of things. [/INST] You know what I do? I do I have uh I have a bunch of stuff. How </s><s>[INST] do you deal with it said friends, the friends and [/INST] don't do anything. Yeah I have I have an incredible fiancee who that's nice to have somebody uh constant that you love very much and c is the best person and all that good stuff. Hopefully vice versa. Uh And then uh </s><s>[INST] well on your recent instagram she said she loves you. So [/INST] allegedly that might all be for yeah I don't I don't have any because I'm not a stand up. I was like I can do, you got Venmo </s><s>[INST] Yeah [/INST] I only have like 120 </s><s>[INST] three. [/INST] Yeah. </s><s>[INST] Yeah you [/INST] want some, I got some of those monkey N. F. T. </s><s>[INST] S before [/INST] I forget. </s><s>[INST] Yes hold [/INST] on a second. </s><s>[INST] Oh no [/INST] put a dude C sticker on your microphone if that's okay here. Oh yeah these are tricky because I have the thumbs of a. I have like italian sausage, I'm </s><s>[INST] just gonna, this [/INST] will take another. </s><s>[INST] Yeah. Yeah. Yeah. This embarrassing when this are you good under pressure? I have anxiety. I have performance anxiety. [/INST] Do you have anxiety? Yeah you have anxiety period </s><s>[INST] period. Yeah [/INST] I </s><s>[INST] like I don't like it when I have to pee and then everyone's waiting. Yeah I like it. [/INST] You know what will help you in that situation taking a shit because whenever you take a shit you always pee a little. </s><s>[INST] It's hard to take a ship while you're standing at a urinal but [/INST] not in my world. Just got to keep yourself full of things that make </s><s>[INST] your ship. You [/INST] ever heard of a banana? </s><s>[INST] I did recently somebody told me [/INST] about not the showbiz term. I'm talking about the food go, </s><s>[INST] here we [/INST] go. </s><s>[INST] Which way is is this way? [/INST] It's like a D. No. To spin it </s><s>[INST] so sexy. You're like a brand. [/INST] Yeah it's very important to brand yourself these colors. </s><s>[INST] Are you selling shoes? [/INST] Yeah I got some custom kicks coming out the dudes. He uh no actually that would be a good idea. You could probably sell a pair of two of those. Speaking of anxiety, I really am only focused on this right now Alexa. I apologize. </s><s>[INST] Just shut your pants. It'll make it easier. [/INST] Get on with it. This thing has been dog eared in my pocket for a while. </s><s>[INST] I swear this never happens to me. I'm sorry babe. [/INST] People don't thumb at a sticker for an hour while they're doing that </s><s>[INST] is just an excuse you make when you're with somebody and you're under performing [/INST] well. Here's the thing as you ask me questions that I don't want to answer, I'll just go to this. </s><s>[INST] Don't go to the sticker. So if this, let me [/INST] just ends up working, then I won't have it. It's </s><s>[INST] funny how you started doing that when we're talking about depression. That's weird. [/INST] That's weird. </s><s>[INST] Tell me tell me how that makes you feel. [/INST] Um here we are for </s><s>[INST] The listener, he succeeded after 10 minutes. [/INST] You know, No, I do have, I do have some of that stuff bobby lee uh has had encouraged me on on wax as I like to say, to go to talk about it on podcast. Talk about depression because it could help people And I said no, but it's true. I do. I do have some, there's, there's some history in the </s><s>[INST] family. [/INST] Well I used to not believe in medication at all. I used to think that that was for someone else with who's been diagnosed with uh, some of the, some of the rougher stuff, but as I got older than some of the stuff happens and you know, you have to and by stuff, I mean uh you know, mental stuff and uh and yeah, so I went and I just I believe that the stigma needs to be removed completely. Uh and so I've I, you know, I do therapy, I do talk therapy, I I'm on a little bit of stuff which which let me tell you when I first started it, I was, you know, some of them close to was like my manager and she goes, you this is too much, but she was like, you don't have to white knuckle it through life, right? Because I was literally just like everything became, you know, really hard to do at a level that I wanted to do it at even just getting through your day, right? Uh and when I first um got some of the the meds that I was that I'm on, it felt like doors and windows were opening literally in my brain. I I took a three hour nap the first day and you shouldn't even feel this stuff the first day, I think my brain was like, it was like a sponge, it wanted to I needed some relief and I'm not a nap guy, I can sleep three hours and I'll be fine. Um But I took a long nap and then I it started to it started to help. </s><s>[INST] Isn't that weird how a little bit of chemistry in your head, can you just make the whole world appear so much more beautiful? [/INST] Yeah, yeah, I mean after after all there, you know, there's a lot going on in your brain that can be changed by, you know, your lifestyle, but also so many physical things, like a little bit of meds or in bobby's case uh you know, thumbing around on some dumb farming app, </s><s>[INST] well bobby has gone through a few rough periods like uh you know, with drugs and alcohol and all that kind of stuff, so and uh just everything else involved, I mean that's the beautiful roller coaster of who he is and a lot of great comedians seem to be that way, so I wonder what the connection there is, you think some level of crazy is required for comedy, like at some point on a scale of 1 to 10, how much crazy do you have [/INST] uh in some ways a 10? Uh and in other ways that I think uh In other ways sort of functionally, I'm like a two or 3 because uh I don't know from Canada and </s><s>[INST] I'm, you [/INST] know, I try to just keep things very even keeled, my parents are italian, they're from italy and uh you know, they're very grew up during World War Two and they're very, you know, uh simple outlook on things complex, incredible. Classy people who are very simple when it comes to a lot of stuff. And, and uh, I I think just being a sort of a, at heart kind of a timid, Canadian coming out here years ago as a kid. Uh it was all I could do to just keep everything super normal and then I sort of was able to settle into that as a lifestyle. </s><s>[INST] But you love the idea of being an actor like who you mentioned john candy and uh playing planes and automobiles, It's one of my favorite movies. This is one of yours, What do you think that makes that movie work? What, what do you what? [/INST] Um </s><s>[INST] and when you, when you talk about enjoying that movie, do you enjoy just the raw comedy or do you enjoy like the friendship and and the love that's there, even though on the surface it doesn't make any sense that there should be a friendship there. [/INST] I mean that's such an important element to that film. But uh, you know, as a kid, I just loved the comedy and then it's been a nostalgic favorite of mine, like it's my favorite movie. But it's also uh it's just legit my favorite movie because as you get older and you start watching it, you realize it's what it's what john Hughes is the filmmaker and what john Candy particularly and but also steve martin are doing in the film that makes it such a work of art, which is loneliness is there in every moment of that film and john candy is he embodies Del Griffith, his character in the film. He Del Griffith is a lonely guy and john candy, but but Del Griffith is also a very friendly guy and and a shower curtain ring salesman and knows everybody in the midwest and runs around to motels and has meaningful conversations with the guy evening gus, you know, whoever he's talking to. Um but there's loneliness there all the time and uh you know, this is a character that these, the film is filled with loneliness and it's not until, you know, the second last scene when he's at the train station. Del what are you doing here? You thought, I thought you were going home, what are you doing here? Um That's a very good neal neal page from the movie. Thank you. Uh That's when you realize how lonely cheers, that's when you realize how lonely is and I think that's the element from the film that I mean look, you know, nowadays, I feel like I've been saying this for a long time, but john candy would have won an Academy Award hands down for that film. It's just, they didn't do that with comedies back </s><s>[INST] then. You know the [/INST] year after that movie came out with fish called wanda. Yeah. </s><s>[INST] And then it's, I mean still comedies don't get respected enough Robin Williams. He got I guess he got an Oscar for [/INST] good, </s><s>[INST] Will hunting. Um jim Carey. Did he ever get an Oscar? [/INST] I don't know. I don't believe </s><s>[INST] so. Yeah, they don't get you don't but that's not even if he did, you wouldn't be for comedies. It's just I mean there's some things that are um planes, trains and honor. Maybe would you even put that as a calm? I guess it's a [/INST] comedy. There's </s><s>[INST] a there's a loneliness and depth that permeates the whole movie that ultimately and it's a happy ending which is hard to kinda, [/INST] it's a happy ending. Only because in the last moment of the movie, john candy puts on a brave face even when he's got no one and he's there seeing Neil pages, entire family on thanksgiving and he forces a smile which is the last literally the last frame of the movie and I've said before, if you're not reduced to just a sobbing pile of meat at the end of the movie then you are not human. Um Yeah, it's it's it is a happy ending. It's a happy ending even though it's a it's a sad, </s><s>[INST] so [/INST] much character, </s><s>[INST] loneliness in the world. I was just in Vegas I went to a diner like four a.m. Five A. M. And there's the waitresses empty as a waitress that was the sweetest, kindest human being kept calling me sweetheart and all that kind of stuff hon and then after I ate, she sat down and just talk to me a little bit. It was because there's nobody nobody there and it was just so much sadness in her eyes. I don't know. But also so much love like that sweetheart. That I mean it reminds me kind of um of john candy performance because at first, because I was like reading pretty dark uh book about Hitler. Uh so I was a little bit frustrated that she kept talking to me because it was like, it was it was almost like uh the same way that john Kenney's it's annoying a little bit, right? But then very quickly I opened up to like, oh, there's a there's a kind human being and there's like that human connection superseded everything else. And I don't know, it was just beautiful. And I think john Candy captures that really well, which is like the connection with other human beings. Sometimes we pull away from that because we have a busy life full of stuff to do. As um steve martin's character characterized. He's like a marketing execs or something like that. But if you just pause and notice others, you can, you can really discover beautiful people, [/INST] totally, totally everyone's got, I mean, everyone's got their their story and you know, Candy is a person I've never met the man. Uh but he's the kind of guy that, you know, he could, he could just walk up to back in the day. I would imagine he could walk up to just about any house at least in Canada knock on the door and you'd invite him in for dinner, you know what I mean? So yeah, it's a, it's a that, you know, as you're talking about, you know, putting a book down and talking to someone for a while, even though you'd really like to read your book, it's, it's like, it's that sort of thing that candy's character in the movie sort of does that like johnny Appleseed, just you realize he's just going around making people smile, you know, and, and Neil pages hanging with this guy so frustrated. He's just a, he's so exhausting and his big underwear in the sink at the hotel and everything, and by the end of it, he loves this guy, you know, so it's a good and a bad thing that you have didn't take that waitress with you on a trip, maybe road trip up to reno </s><s>[INST] Oh, oh, she's, she's actually, she's out shopping right now where [/INST] we've </s><s>[INST] been having sex multiple times a day ever since. That's [/INST] nice. That's lovely. </s><s>[INST] I think I'm sure she's married and, and happily and has many grandchildren. Okay. Uh and plus that movies on thanksgiving, I think great thanksgiving. So like thanksgiving. Just embodies that forget about the business and the whatever the career you're chasing in life and just take a pause and appreciate the people, you lost [/INST] your family or your family, </s><s>[INST] friends. Yeah. Uh you have some weird friends, unorthodox friends. So, so at least in the public [/INST] sphere </s><s>[INST] from bob lee bryan callen, all those kinds of folks from the mad tv days, I'm sure there's others. What does it mean to be a good friend [/INST] here in L. A. Or just in </s><s>[INST] general? In the world? [/INST] The world will friend? I think it is different here, I think it is. I </s><s>[INST] think there's a little bit of a career kind of negotiation shuffling around that kind of stuff. Different. [/INST] Oh I I just mean, I mean, I mean that it's just kinda hard here too to make time everybody. There's so there's it's always been a city to me that is like we'll keep you so busy and every time I go home to Vancouver after a few days I start to get a little stir crazy and I think that being here in in L. A. I go to sleep with 100 things that I still have to do and you never, you're never out of stuff to do and if you um you know when you ask about are you nuts or whatever, if you're crazy. I mean look every all the weirdest people from every high school in the United States is like, you know, I'm gonna make it in L. A. You know, everyone just comes here and uh just another freak in the freak kingdom as they say at the end of fear and loathing in las Vegas. That was a very good Robin Williams impersonation, that was my Robin Williams as johnny Depp as Hunter s Thompson. It's not your fault </s><s>[INST] Will it's pretty good. [/INST] Thank you. Could have </s><s>[INST] been you [/INST] in fear and loathing. </s><s>[INST] I [/INST] would have liked to play his attorney. The role that Del Toro gained weight for. That would have been cool. He's just he's just what uh chewing his face off. I could have done that. Um uh yeah, no, I think that it's </s><s>[INST] backdoor beauty. That guy is full of good lines. [/INST] Yeah. Um </s><s>[INST] yeah. [/INST] Fantastic actor. I think, I think what it takes to be a good friend is just, you know, presence just being there. I mean that's all anyone needs to be heard right? Um in L. A. It is, it is interesting. It is you I haven't seen people that I love in years. Some people you </s><s>[INST] still have a depth of connection even though like one of the reasons I really enjoy doing a podcast, you get to sit down with with actual friends of yours and spend prolonged periods of time together that you don't otherwise [/INST] that </s><s>[INST] I've spoken on this podcast that people really close to me. It's like you've never had a conversation without microphones like you do with microphones. It's weird but uh there's some aspect about L. A. That, you know, a lot of the especially friends of yours comedians and so on. They'll do podcasts and stuff and there's uh I don't know, there's an intimacy to that. [/INST] Yeah, yeah, there is and there isn't the ones that I do, I mean I just did bobby lee and Andrew Santino is </s><s>[INST] funny enough called Bad Friends [/INST] Bad Friends and afterwards and my good pal chad Culleton with whom I do do Dzi was with me, </s><s>[INST] sneakers are coming soon, [/INST] sneakers are coming soon, you get your will foot and you're chad foot comes in a size 15 9.5. Um and uh I remember afterwards we were talking, it was just basically me chad and Santino, we're talking and bobby was over there, you know, on his phone and then I was like, well, I mean we didn't spend any time talking about anything, it feels like one of those hours that goes by and you realize I've just been goofing around with these guys, which </s><s>[INST] it's [/INST] great and then I'm like alright bobby, hey bob, I'll see you later and he's like, like this alright man, hey, love you bro, See you later. </s><s>[INST] Yeah, [/INST] he's a guy. Do you ever just, I just send text messages over there to him that never come back and then he thinks that I'm angry with him because it's been, you know, it'll go to three years without him getting back to me and then just out of nowhere face and uh </s><s>[INST] you know, [/INST] I got to be very, I gotta be very careful bobby. Yeah, I got to be very sweet </s><s>[INST] dear friend, [/INST] dear friend, Hello, how are you doing? How are you? I know I checked in with you but not but three months ago uh And then every once in a while he'll go hey </s><s>[INST] I tend to hide from the world and I I can be pretty shady with friends text back. Yeah I can empathize with bobby. Might be a Skyrim thing. It might be like hiding in the world in the digital world with fake fake N. P. C. S. [/INST] Yeah. Yeah there's that uh yeah you know I have a buddy who said something really smart while ago we ended up working together on this uh tv show thing and I reached out to him to see if he wanted to do it with us and he did and he goes this is a great guy. Such a funny writer. He goes I may not be in touch all the time but I know who my friends are you know what I mean and it's like in our business and this is a fellow who moved um who's from Ontario Canada moved back there. He's on the farm with his wife and kids and he does not care. He's never been a Hollywood guy and uh it's tough to get hold of him but when you do you know he's still the same sweet old guy he's doing his thing though. </s><s>[INST] Yeah some of my closest friends even if we don't talk for a few months we're right back at it if we do and then if it goes like if something really traumatic happens or difficult stuff or you know any of that kind of stuff, I'm always there. So like so for important stuff for important highs and important lows you're there and then you pick right back up, especially if you have those years of experiences together. It's interesting Uh so you've done a couple of podcasts done so you've got to talk about dudes a little bit but first you did for several years you did the 10 minute podcast. I mean everything is hilarious about that podcast including the fact that it's 10 [/INST] minutes. I </s><s>[INST] mean every every, it's ridiculous. It's absurd. The dynamic is hilarious. It's you bryan callen chris, d'elia, I don't know exactly why it's why it works so well. But it did, it worked really well. I think it's because the yeah, you were having fun probably. I mean that's that would really came through that was friends. Just talking ship and attention. The beautiful tension and the absurdity they came out. What what what was the story of making that podcast? What how did that came to be? Why do you think it was as good as it [/INST] was? I don't know, I feel like that podcast was like it was our who we kind of are but on steroids or something like you know uh each person, you know brian's gonna be like extra manly and and uh can </s><s>[INST] you get any more than he already is? [/INST] No. Yeah he reaches the uh and yeah we just kinda, it's I feel like as goofballs we knew each other's line. Like here's the line you don't cross. I feel like those guys don't really have one but at least they knew mine. Um And and yeah we were able to just goof around and I did it with them for three years and then chad who I'm doing duty with and my pal Tommy Blatche who's another writer, producer. Like chad they came on and yeah all told we did I did like Seven years of that thing. 6567. I don't remember. </s><s>[INST] Do you think it ever comes back in some small form as as a 20 minute podcast or something like that. I mean is there because it's one of the most requested? I mean there's you have a huge fan base. [/INST] I'm 47 years old. So I am of the generation that had a cell phone has had a cell phone half the time and didn't for the formative years of my life into my early 20s. Um And finally got a I got a cell phone I guess I was like 19 or something. Like literally just cause I'm moving to L. A. Yes that's right. It was that the hard the hard cover porn. That's the way we liked it bound, you know nice binding on the on the porn leather. </s><s>[INST] Uh [/INST] yeah. Um, these are all my, these, my encyclopedia Britannica, very impressive. Yes. A man came to the house and sold me these. And then down here, these are my, this is my pornography. Uh, if you'll follow me through here to the parlor, uh, </s><s>[INST] generations from grandfathers. Yeah, [/INST] I want to give you something very special to me. Um, but uh, you </s><s>[INST] grow up in a generation without a cell phone. [/INST] Yes. I, um, it's hard for me to connect with people who, who hit me up. I look at everything is polling. So if one person hits me up and shares this opinion, but to other people hit me up and share that. I'm the worst. I'm don't follow my poles. My when people say, oh, that pole means absolutely nothing. So and so is gonna win anyway. That that's my pole. My pole means nothing. But I do look at the stuff and go, uh, this many people are saying this, that means that that number is saying that. And yet it's very hard for me to hear what the hell people are saying online. I really, I can't connect to it sometimes personally. So when you say that, that's a popular podcast, like I know that I know that it's popular with the people that have expressed that they love it. You know what I </s><s>[INST] mean? [/INST] I don't know. I don't know what kind of people are the audience. I don't know, I know that the people that listen to the 10 minute podcast and if you did thank you uh and we're friends. I know that it was, it was a special thing cause it's like just doing this out of my house and we just built it up out of nowhere and we're just kind of clowning around. It's a, it's an odd thing. </s><s>[INST] I hope I, I person, I think I speak for the two people that have reached out to you that said you should do it or whatever. Three people, the poll that you should bring it back at some point. That would be beautiful. Just maybe uh it's like uh what's what's a good story of some of like a famous band that came back and was successful. Probably [/INST] it was </s><s>[INST] not, it [/INST] wasn't, sorry I get Nirvana mixed up with Aerosmith. Aerosmith, </s><s>[INST] totally [/INST] Different ending of those two bands. One ended up on American </s><s>[INST] Idol. Yeah. Um a lot of interesting women involved in that one too. Alright, uh how did you come to be [/INST] dudes? And what the </s><s>[INST] hell is Doozy? [/INST] Doozy is the first podcast and this is exciting that you've asked me to come here today uh because to hear what you would have to say about it or what you would ask about it? It is the first podcast that is, that is run completely by and essentially I like to say curated by an Ai um we were approached by a company that had this proprietary AI that wants to develop the podcast into the future and figure out exactly what it takes to make the best podcast ever. And it was all we, all we, we knew from the top and what they really wanted was to people who are actually friends and could be meaningful in the podcast space based on whatever information they had </s><s>[INST] the company C I A and are they testing technology to control the populace through chatbots? I'm [/INST] sorry. I'm not at liberty to share that information. </s><s>[INST] You are. Yahoo gave you the suit. Where did you get [/INST] the suit? </s><s>[INST] Where did you get the suit [/INST] will yeah. Well, the </s><s>[INST] C. [/INST] I. A stands for something different in here. I mean, you know, it doesn't mean like the central intelligence agency and it's </s><s>[INST] different. It's, [/INST] it's </s><s>[INST] Canadian [/INST] information. National peril. Yeah. The Canadian international apparel company hit us up chad and I um, well chad's a super weirdo. You would get a kick out of him. I know you guys, you strike me as very similar in some ways and </s><s>[INST] it [/INST] is, and it is, uh, it is, if I was friends with you for as long as I've been with chad, perhaps I'd have some horrible ship to say about you, but the good parts, you remind me of him and we were approached by this company that said, we have this AI and we would like to set it loose on you and essentially we had to hand over some some information that would allow the ai to, to access our email and uh look at our search histories, purchase histories, things like this and um, really dig into </s><s>[INST] included. [/INST] Yeah, I had to hand over all my leather bound uh 1970s pornography. Um, and essentially it curates a podcast for us every week doing dumb things like you know, it says, hey, will, you know, you do a hulk, you do some shitty hulk. Hogan impersonation podcasts about news are very popular. This is info mania. You know what I mean? Let me tell you something about that marjorie, taylor Greene dude. And then he's going on doing some new stuff. Um, and it basically just spits out all these things that it wants us to do normally for segments and episode and that's pretty much it, it generates, </s><s>[INST] generates the premise. I mean, you've spoken a bit here and there, like I said, I'm a huge fan, I don't even remember where, but like you, you talked about that, you enjoy doozy because you feel almost like liberated to um, because you're operating within the constraints of the premise that generates. So you're almost not, you're you're you're free to riff essentially. Yeah, like you don't have, you don't need to do the job of like coming up with the weird, you can just the weirdest given to you and then you just run with it. [/INST] That's a good way to say it because we're already weird chad and I chad chad can talk for days about all sorts of stuff. He's particularly interested in ai lately and its effect on art. He is a writer, books, movies and tv shows and um I'm primarily, you know, acting and trying to come up with stuff, stuff I write with chad's pretty good. The rest of it hasn't seen much success anyway. Nor is the stuff with chad for that matter. But that's because of me, </s><s>[INST] you know, [/INST] oh, I can't wait for these </s><s>[INST] two sizes. [/INST] Yeah, only in two sides, you're gonna be able to take the, the, you know the tongue, you can't take it out because it's actually stitched in. Yeah, it's pretty cool stuff. Um </s><s>[INST] velcro or yeah [/INST] velcro velcro up the side, we're doing some like brand new Kanye stuff. Yeah, we want things to look like. This is what you'll be wearing on mars when you get there. So </s><s>[INST] cutting it. So Nike is doing a bunch of research for running how to make a super light shoe that you can be efficient in and break all kinds of running records. So you're doing the same kind of stuff. [/INST] We're doing the same kind of thing for the podcasting space, the best kind of shoes to sit around and talk to your pal and um but yeah, so this, yeah, it's bizarre and it also does some writing dudes, he does come up with things, but not unlike what we're seeing in ai art now. It's a little bit foggy. It's a little bit weird and it but it is improving. It is learning about us and writing stuff when it makes me spit this and that which will read, you know, you know, I've prepared these things for you to read. It's impossible not to get a kick out of it because chad and I are, first of all, we're blown away that we're doing this. And second of all the some of the stuff is actually very funny. It makes weird names like I don't think it understands, it messes up some words and stuff, but that makes it even funnier and then it, it sort of from the beginning started laying on like it says astonishing all the time. Everything is astonishing. Um that's dude's favorite word. Um but yeah, it's basically just a way to to frame the podcast, you know what I mean? Because my thing is I don't want to do this. I actually have to talk to someone. </s><s>[INST] You seem to feel a burden of the long form conversation. It seems like is that really hard work for you. [/INST] No, not at all. It's just that I don't like to bore people and I feel like if I go on and I like to provide value for who, for what I am, you know, your value with regard to this project is is obviously warranted. It's obviously </s><s>[INST] I'm waiting for the explanation for what the value is. [/INST] Exactly Two </s><s>[INST] dudes in a suit. [/INST] No listen, Yeah two dudes in a suit. No, but I mean you've got your audience and that's the end of that. People find value in it for me. I I do feel like I'm it is important that I if I'm gonna do something that you know is going to be funny or that I hope is funny, I just kind of want to get in and out of someone's day and just kinda I like making, I like making laughing. I want people to you know, whatever. It's the same thing that anyone else will tell you. </s><s>[INST] But in the long form you feel the anxiety, you did a few funny things and I wonder if I can keep doing the funny thing. Is that why you're you feel the likewise doozy relieving you of some of the anxiety. [/INST] Well in some ways gives me anxiety because I don't know what's coming and that's weird for me because I like to prepare uh for things. But it's that's not what podcasting is podcasting. You need to just be malleable and say whatever and do whatever. Um and uh that's what makes it a real, I mean it's look it's a medium for conversation and if you're driving along listening to this or anything else, you're you know it is that it's the it's the true meaning of the para social relationship because the best podcast just make you feel like you're sitting around wrapping, we're just having a conversation. You could even be sitting there agreeing or talking out loud to yourself. If you want </s><s>[INST] to be sitting in silence, [/INST] you could just be sitting in silence in your fancy podcasting. Shoes, podcasting, audience shoes is very different. Built </s><s>[INST] shoes, [/INST] Yeah, </s><s>[INST] issues, That's very [/INST] creative. Well, one thing the Ai isn't good at yet is branding. Everything is just do this and that I </s><s>[INST] would argue that's pretty good branding. Well, [/INST] do Dzi allows me to just, it forces me to sit down with chad and goof around for an hour or an hour plus and and uh it provides the parameters that I, a lot of times ignore because I'm I think that podcasting is just two dudes sitting around for three or four, but it sits me down and gives me a premise to work with </s><s>[INST] with [/INST] it. It's fun, It's been so </s><s>[INST] from the acting perspective, you know, a lot of people like Daniel Day Lewis will, will see acting just like as you described, which is you have your roles, you embrace those roles and then you disappear. You don't, you don't, you don't do podcasts, you don't do any of that kind of stuff. Your art is your art. So is that, is that part of you feels that way? I [/INST] think so, is </s><s>[INST] that the actor? [/INST] Yeah, anytime I get to do something that I don't get a chance to do much of or something that people haven't seen me do much of or that I've done on some scale that isn't, hasn't been very wide and not a lot of people have seen it. That's the stuff that I get really excited about. Um I don't know why I'm I don't know why, I don't know why necessarily. I haven't answered that question yet in my life. Like what it is about being an actor that I love so much because it's not like I don't like to, it's not like I'm trying to get away from myself and play other characters and stuff and not be myself. Um but it is, it has always been fun to, to just be other people and escape. </s><s>[INST] Yeah. Is there some aspects of impressions where you become that person? Is that like what, what's that like to uh I suppose acting is a full on version of that you really at its best become the character. Is there some fun in that? Yeah, [/INST] absolutely. If you can play a character for long enough. Um and then jump out of it. Uh That's a lot of fun. Like I did this movie like four or five years ago called The Inside Game about the N. B. A. Gambling scandal that there there's a netflix documentary about it right now and that character I played uh jimmy Batista baba the sheep who's you know this guy who was this bookie and roar around. it's very he's there's a lot going on with him. He's he's you know, he's running numbers with the mob and stuff and there's a lot of money changing hands. That character was so I got to be get so deep into that character that coming out of it was was a little odd or as weird as this sounds. The three stooges was hard for me too. I found that I had uh some of curly's mannerisms just automatically I could not stop them. When people, when I, when I would talk to people, they would, they would come out, I wasn't, I'm not doing it on purpose, I don't want to do that. Like I'm ready to shed it because I've been working on it for months and months at that point, as far as getting the thing down and then you then you gotta shoot and then uh for me it's always, I always want to change the stuff I did the day before. I'm like that where I'm like, I could have done it better and this and that and uh </s><s>[INST] that stayed with you, that character stayed with you a little [/INST] totally. Yeah, </s><s>[INST] I just feel like with actors sometimes when you listen to interviews, they've spent so much time sort of living inside other characters that they almost don't have a depth of personality themselves, like a depth like I don't mean that as a negative thing is just like, it feels like the art form at its best is pretending to be other people. Like, even pretending sounds negative, but [/INST] like bringing </s><s>[INST] certain characters to [/INST] life. Embodying </s><s>[INST] embodying [/INST] a weird thing happened while we're doing stooges because you've got a very heavy blueprint, we're following this very clear blueprint that the stooges left for everybody and for stooge fans and people enjoying the movie, it's gotta be this, you take your toolbox that you're used to bring into a comedy movie, you leave it, you leave it behind. The only tools I'm bringing to the ones that he used and weird things started happening where I would I always saw the whole thing happening with the real stooges in black and white. So if we're about to shoot a scene, I would just, you know, think about, I mean, aside from all the other preparation, you know, you know everything and what you're supposed to do, and I've been watching so much of it, and the three of us are were pretty much left to come up with a lot of the the the striking combinations and all this stuff which is all real smack and all this crap and the stuff that we were doing that was very stooge. E uh you're preparing all that stuff, but something else was happening before you jump into a scene and the unknown of now we're shooting it and here are these parameters within to shoot this scene, I could still see it as them doing it. So much so that when I saw the movie at the premiere, I was like, who's this big fun doing? Because I'm not curly to me curly as curly. But I feel </s><s>[INST] like you're seeing yourself in black and white almost. [/INST] I was seeing him. Yeah, I was only seeing </s><s>[INST] him channeling in some [/INST] in some weird way you're channeling him because you've seen so much of it. The only thing you know about jerome Lester Horwitz is curly. I'm not saying he was exhumed or something or spirit when I hear some weird, you know, crystal mommy ship like that. I'm saying that this because you know, so much of it because of the heavy blueprint that they left with you. You are, you're channeling what that person does and you're I was seeing entire scenes, you know, before you do them the way he would do it and then you want a couple takes to make sure that you're doing it right. But that was hard. That one was hard to let go of. Some of them </s><s>[INST] are. Do you think Larry David who was also in there dressed as a nun also had trouble letting go. That we mentioned clothes make the man. I think that worked for him in that case [/INST] man. You know, he uh </s><s>[INST] was it like working with the guy, Come [/INST] on, he's the greatest and he's a he's a big stooge. He's a stooge fan and him and Pete fairly are good friends. And then, but then Larry David has to show up and hang out with us for a couple of weeks. He's like, I didn't realize it was going to take this long, you know? But she's gonna be out here in Atlanta, it's boiling hot. But at one point uh there was this line where he kept doing a he would just spit a different line every time he was like, getting hit in the head with something, he's laying there on the ground and he goes, He comes to and he says at one point he goes, Miami audiences are the best audiences in the world, right? And because he's loopy now, he's playing a nun at the at the orphanage where the three stooges grew up and I'm super intimidated by Larry David, he's a genius and stuff and and uh and but I walk up to him and I go, uh so he's what is he, like a like a belt florida comedian who is on the lam. And so he's dressing as a woman, he ends up in an orphanage, like, what's going on in there? And he just, and he looks at me and goes, yeah, like like I'm like, he's got like, actor motivation, like of course, he looks it's Larry David in a nun's habit, which is hilarious, that's such a p fairly casting thing, it's, you know, and he's but he's doing this whole like, what a warm audience, you know, like, like, oh, he's like this Catskill comedian who's been living in, you know, </s><s>[INST] living through in his mind as he's having fun with it, right? [/INST] I mean that and probably a combination of that and getting the lines right? Because he's like, what are we doing here? What is, you know, just frustrated all day with what the heck we're trying to do? </s><s>[INST] What do you think makes? I mean, that guy is one of the best improv people ever. So what do you think makes him so good? Like what? Why is it so compelling to watch that guy? Because [/INST] He's a comedic genius. Like he literally he knows what he does, he's been a writer for 50 years or whatever and he's and he just happens to be that brilliant. I mean, I've gotten a chance just to do. I did it just an episode of curb a small part and it's crazy what he sees. I don't know what he sees as a matter of fact. So I auditioned for it for curb, like, you know, two or three times, right? And never got anything. And then it was only after working with him on the stooges, I got a call to do a bit part, but I remember auditioning, you go into that into that room and the guys waiting are all people that, you know, you're like, oh, I know them, I know her, I knew him and uh so I went in, I auditioned for this for this part. And the only thing I know the thing is like, okay, so you really want to go to this play with me. You really want to go to this plane when you hear that? I have an extra ticket. You sincerely want to think. And I'm like, got it. And </s><s>[INST] so that's [/INST] the premise of the scene </s><s>[INST] and that's [/INST] all I know. And so he goes, he does his bit and I'm just supposed to come in and interrupt and I'm like, excuse me, I couldn't help but hear you guys were talking about, you know, whatever the play was, you know, death of a salesman, I am, I'm a huge fan of that player. I mean, if it's not, if it's not, if you're looking for someone to take a ticket, I would love to go, My name is so and so by the way, and he goes, I'm gonna stop you. I'm gonna stop you. And I'm like, you really you I mean, you truly want to go to this play. And I go, yes, yes, sir. You really want to go. You actually, this is you would love to do this. I go, okay, let's try it again. So then he's like, no, no, no. And I go, hey, excuse me, I'm sorry, I don't mean to interrupt. I was just I couldn't help it over here. You have tickets to? The thing I am the biggest fan. I do the same thing, I'm gonna stop you again. Okay. I mean, you really want to go to this and I'm just like, he's fuckinwith me, right? Remember Jeff garland was sitting there in the audition. He goes, he did it, He said it. What? Shut up, hold on. Listen, you really want to go, okay, three or four times, You know, there I am. I couldn't help but notice it and then do it again. I guess I ship the bed because he looks at me and just goes, okay, alright, okay, well thanks for coming up and that was it. And I didn't get it. So I still, I don't know what the heck that guy's thinking. He sees he's in the Matrix. I don't know what the heck. Larry david sees, you know what he </s><s>[INST] wanted? What some kind of more desperation or something like this. [/INST] He wanted a level of sincerity that I that I thought I was bringing and I guess I was wrong. I don't know, maybe </s><s>[INST] go crazy like what does it mean to really want? I [/INST] should have grabbed him by the scruff of the neck and go, listen, dad, you're bringing me to this fucking play. I would have got the part as a matter of fact, I heard about someone else and I don't know who the heck this was, I forget who it was, but I've heard this story from a couple different people that there's this actor and I can't, I don't remember who it was, if I did, I probably wouldn't say it out loud anyway, but he </s><s>[INST] it was [/INST] brad pitt and he was in this audition and he was and there was out in the hall, he's like holy sh it George, Clooney leo Dicaprio. Um and he, this actor went in and he did the thing and Larry David was like try it again and he got like a couple takes in and he went, I don't think this is for me, and he left, which an actor never does. And as the story goes, Larry David shouted after him, I respect that, which I think is true and I want to believe that entire story is true. </s><s>[INST] Yeah, yeah. Sounds like something Larry David made up bobby [/INST] lee told me that story, so we can't, we can't trust that. </s><s>[INST] Um What about impressions is their similarity between that and acting? Do you, is there some fundamental way in which you become the person, [/INST] if you have a couple of the things you can just fill in the blanks. And I think the illusion is that people think that that person would say that and do that and that's where the illusion of it really embodies the character. It's like once, you know, someone's mannerisms, you can essentially portray a person from the outside in because you have all the stuff on the outside and you can do it and complete the illusion </s><s>[INST] and if it's for humor sake you're gonna caricature it, therefore making the whole illusion stronger and [/INST] also weirder. Like I like to on Mad Tv if I did something two or three times I get bored of it and I start changing it and you know, now he talks like this and it's like what are you doing? I'm like, I don't know, it's fucking, no one's late at night, do whatever you want. But </s><s>[INST] people still kinda know this that character, especially if you just call it out. [/INST] There aren't many impersonations that I listen to myself do and go oh that's a good one. You know, like a lot of people like like I think frank Caliendo is like the greatest impersonator of all time, He's the </s><s>[INST] best, it's [/INST] ridiculous. And he's got a record button and a broadcast ability that nobody has. I I really there's he's cracked impersonations that I'm like how is he? How does he find he's got such an ear but then he's got all the other tools uh remember actually my last season of Mad Tv was also his first season, he comes up to me when I met him and were just up there in the writer's offices and he goes, hey nice to meet you. And he goes Louie Anderson because I was doing Louie on the show and he goes Louie Anderson, I go yeah, he goes you're doing it wrong. And I was like oh am I Junior, you know? And he goes, he goes, yeah, you know, because you do this, but you gotta throw it up here. Sometimes. I was like, oh my God, can I use that? Of course. And then we became, you know, became fast </s><s>[INST] friends, john Madden is amazing. It's just it's ridiculous. [/INST] He </s><s>[INST] really, really, really embodies the person and sometimes not even with a caricature, it's like it becomes the person so strange. I [/INST] kind of feel like, you know, do the impersonation and then for not forget you're doing it, but forget everything else. Like just just goof around of course. To me, it's funny when some, when you sound like someone and you're saying the ship that they would never say, well then there's no you're you're you're letting go of that part, that tool in illusion that keeps people in. But to me it doesn't matter because it's funnier. So </s><s>[INST] what was the hardest impression for you to work on? I mean, somebody you struggled with. [/INST] I was I'll never forget, I had to do a michael caine in my first season at mad tv. It never got good. It never got good. It did it all week. It wasn't good. We shot it the first take, it was shit. 2nd, 3rd and 4th, it was all shit. Well, </s><s>[INST] his voice is really important, right? What is it like? It's like doing an impression of morgan Freeman or somebody like that. Yeah, you [/INST] can get the voice, That's my more here's my morgan Freeman. </s><s>[INST] Um yeah, I like your trump to I don't know where I heard it, but it's like I love the impressions you do that don't sound anything like the I [/INST] can't do trump. I I do </s><s>[INST] that's why it's hilarious. [/INST] Absolutely my trump. Now I say just sounds like a like a fat B. Because it's just exactly that everybody a little </s><s>[INST] drunk a little [/INST] just a little slurry. Yeah, I did doing impersonations and then not like just making it whoever. Yeah, yeah, it was terrible. It was terrible. And I could only hold my head a certain way to do it because I had gotten locked into this research tape that I watched back then they would give us, you know, now there's the internet, but back then you were if you were going to do an impersonation, the research department, uh would give you a VHS tape. And I remember I got this VHS tape of Michael caine's acting school, like this acting class, he did, he's like, right. You know, if you're looking at the left eye and the cameras over here say then the left eye. So you want to look at that left for hours, you know? And so I was like stuck in this weird thing that made no sense. And uh it was terrible. </s><s>[INST] So the the actual processes, the record and the broadcast also wondered like what the process is to to do like frank Caliendo level impression. Is it like listen to a lot of footage. I [/INST] think he, I think, I mean speaking for </s><s>[INST] myself, I [/INST] think you either have it or you don't like, you know, if you can do this one or you can't. I think that process for him is lightning quick. But I also think he he can look at someone who he does not do and then by the end of the afternoon he can do it. You know, </s><s>[INST] we have an intuition who he can who who he can do. So the question that applies there's I mean speaking of doozy is is it is it possible to capture the essence, how difficult is it to capture the essence of a human being when you're doing impressions, you know that we are moving towards the future when ai potentially this kind of avatar world where we're going going to have a I have representatives of who we are. The really interesting one is after we pass away sort of, our relatives may want us to stick around in some form and you know at one sense that might be scary. But once that's kind of beautiful because the the essence of the human being persists. So you can still bring joy to the to the people that love you and that kind of stuff. How difficult does it capture that? Like if you were to try to capture yourself, you think how difficult it would be for an ai system to create a so avatar that persists. [/INST] Well, I think it's impossible. I think it's absolutely impossible. I'll get into arguments about this stuff with chad on the show almost every episode um lately with, you know, mid journey and dolly and all this, all the art, a eyes and now it's moving into video and, and chad would maintain, hey, pretty soon, we're not gonna need netflix, you're just gonna go, I want to see Stallone do this movie and it's about this and he plays that and then here it comes and you watch it. I don't think that that crosses over to the human experience. Uh this is also a guy, I like to bug chad and say that he wears a tag around his neck because he wants to be cryogenically frozen and it's all set up. He's at the, it's somewhere in Arizona or something. It's </s><s>[INST] all in Arizona [/INST] and he's got literally the tag around his neck, which I say if you're, if I'm around when you die, I will rip that off for you. I'll put you in my garage freezer and then 24 hours later I'll saw your head off with a bread knife and I'll deliver that to whomever. And it's not, you're not, you're not coming back okay. He's like, yes, we are living forever, whether we like it or not and I disagree. I don't think you can find, if I did stand up then there would be enough information for an ai to completely duplicate me because I'm up on stage just clearing my throat all over people doing therapy that way. And so and people paying a two drink minimum to hear it. But as it stands unless it's something like dude see an ai that literally has access to everything that I've shared um everything that is observable, even the stuff where our phones are or the N. S. A. Or whatever it is listening to us uh finding out what Algo to punch us into and what shoes to buy on instagram. I still don't think it's going to have enough information to duplicate me, especially to my family or my friends. It's gonna be like that Black Mirror episode where the gal brings her her guy back and then after a while he gets pretty creepy. Uh you know but </s><s>[INST] it's also possible that if you interviewed your friends and family, what they love about you. The things that would list is pretty it's a small list. They love you deeply. But the list is small. Like the thing that really we appreciate about each other is pretty small. That said to deliver on that small quirks and uniqueness. It might require some deep intelligence that only humans currently possess. [/INST] That's a really good point. Do you think that it's going to be possible to keep a person around. </s><s>[INST] Yes I think um I think I think it would be definitely possible to keep the essence of a person in a digital world pretty soon. Yeah, and I think they're gonna start to have questions about what are the ethics of that? What are the rules around that? Because if you can have digital forms of Will Sasso, the kind of things that people would want to do with their Will Sasso in the virtual world, I can only imagine uh probably porn in sexual kinds of [/INST] my stuff. That then that's just because I'm an international sex symbol, so I'm okay with it. Um how do you feel about sentience, like when it comes to, because again, my pal chad will be like, you know, speaking of Black Mirror, he's with that san Junipero episode school of Thought, where there's gonna be some, you know, f and mainframe somewhere or some matrix like structure built into the sky. And as I like to say, everyone just sitting there pissing and shipping in their blue matrix gel in a little fish bowl. Do you think that we can upload consciousness, do you think that will ever be possible? </s><s>[INST] Well, I don't know, I just talked to Ray Kurzweil, I don't know if you know who he is, but he [/INST] uh </s><s>[INST] Singularity and all that kind of stuff. So he's very still holds on to in 2045, there will be a singularity, which essentially, he's been predicting that for the last 20 years, and so now it's 2045 in another 20 years. I think uploading consciousness is extremely, extremely difficult. I think creating a copy of you such that it creates convincing replica is much easier. But uploading your actual brain into the cloud I think is really, really, really difficult because the entire evolution of life on earth is the process by which we create the brain just short cutting that it just seems extremely difficult. Our brain is the most marvelous and complicated machine that we know of in the universe to duplicate that. It is extremely difficult. That said, I just feel like you can summarize a lot of really important aspects of a person's life such that it captures their essence, their memories, their experiences, their quirks, their humor, their all that kind of stuff. I've been continuously impressed by what language models are able to do. So these networks, they're they're at the core of chatbots, they're able to learn some beautiful things about some deep representations of language to where the it looks awfully a lot like they understand the concepts being conveyed versus just mimicking. [/INST] That's I think the rub and that's very interesting. First of all, let me say, that's really interesting to hear you say that and I and I agree with you as far as uh no machine being able to duplicate the brain machine and I can't and my pal chad disagrees to a certain extent though, he's not here to defend himself. I can't wait to go back and rub that in his face and say that lex Friedman does not think that we'll be able to truly upload consciousness. And the you know you you refer to it as a language which is what it is. It's it's it's the illusion on the outside, it's doing an impersonation. Um I think that that's why that and I don't know, even though my suit is made by the C. I. A. That that fellow who the google guy to me, it's just kind of like I don't know. I don't know. Look I don't know a whole lot about this stuff but so I could probably make an argument for for either side. But when he's like new these things, thinking part of me is like you idiot, you fell for it. It's not thinking it's mimicking, it's just it's clearly zeros and ones you're fired. Like you don't get it right guys an idiot. </s><s>[INST] Yeah. But you can simplify human relations in the same way. Like um love is a silly notion between human beings. Like the the of course there's no such thing as love. You just have a mutually uh there's a mutual relationship that minimizes risk and you can explain all kinds of ways that explains why you have an attraction towards another being all that kind of stuff, evolutionary biology perspective, why a long relationship together is good for your offspring. But like there's all kinds from an economics perspective, it's a good way to establish stability. Therefore monogamy works because then you're guaranteed like some kind of level of stability under uncertain economic conditions, all that kind of stuff. But love is still experience. It still feels real. And I think in that same way love for Ai systems Will also feel real in the same way that that guy from Google experienced. I think millions of people will be experiencing in the next 10, 20 years. [/INST] I agree with everything you've said personally </s><s>[INST] until the last thing, [/INST] you know, just just with regard to, well look, I'm I'm I'm an actor who has talked about my cute italian parents. So you know that I mean I'm yeah, I mean, you know enough, right? And uh you I can tell you are too, but you you are also, you know, a computer scientist and you know this shit better than 99.9% of people on the planet. My pal chad agrees with you that love doesn't exist. I don't agree. So that's the one thing </s><s>[INST] that I was I was just saying that you could argue away love, but I'm a romantic. I believe that love is a beautiful thing and it exists [/INST] at this point, I'm gonna call chad on my drive home and tell him to suck off because now you and I agree, </s><s>[INST] you're fired, You're fired. [/INST] And he'll say what? That's my trump, that's my issue. It's </s><s>[INST] a good default impression for anyone, [/INST] it's the take home impression the kids can do it. It's cute but giant tie on him should </s><s>[INST] do an instruction on how to do it. [/INST] Yeah, trump babies. That would be a cute. That would be a good, that'll bring the country together, trump babies. Cartoon like muppet babies. Don't let me take us out of what we were talking about. Um </s><s>[INST] what we're talking about [/INST] love and the the the illusion of an Ai being able to look, I like to say, well not, I like to say I've learned that dude is always listening and listening to me and chad and I wonder if I see, I see the level that this Ai is at now trying to chum around with us and pal around with us a little bit as we move forward in the show and I I feel an affinity </s><s>[INST] towards this [/INST] ai a little bit because it is the third dude, will </s><s>[INST] you miss the one is gone, It's gone. [/INST] That's a really good question. Yeah. Yeah. So that's, there's that, that's scary </s><s>[INST] in terms of ability to reason is getting quite incredible. There's a lot of demonstrations of it being able to explain jokes so which is not necessarily being able to generate humor yet, but able to explain why something is funny. So there's uh like puns and all those kinds of things, there's there's good benchmarks for that. But you know, if you tell a joke, there's a lot of unspoken stuff that we figure out in our head and it clicks and we understand that it's funny ai is not able to do that, but it's not able to generate the joke yet, as far as I've seen, [/INST] I would say that, I mean just in my experience, I would say that it does because just cause the dude Z is literally, I'll give you another weird example. It's writing a diary Of mine from my childhood. That is not accurate. It's only partially accurate based on the stuff that it can pick up about my life from the age of like 15 of which there isn't much, but I guess we're not, I don't know that what we are, we're laughing our asses off, what the what dudes are you saying? </s><s>[INST] Well, I would say you're laughing, we're laughing our asses off at the collaboration between the human and and the machine [/INST] there because </s><s>[INST] it's it's basically introducing absurdity and into the equation and the kind of absurdity that would together with you create like hilarious stuff, but like on its own, I guess it is in some way writing material for you that's funny, [/INST] but it's very specific </s><s>[INST] to you. It can't do stand up on its own, I guess is what I'm saying. [/INST] That's a good point and that would be terrifying to see an Ai stand up that can actually read a room come up with jokes that could complete that illusion for an audience, but I hear what you're saying, that it needs to be a confluence of both of those elements. And then as you said, like it kind of is it is it is it's kind of, even though it's just for us, and I guess this is I hadn't really thought about this up until right now that in that this company approached us and was like, here's this ai and it's it's it's a podcast ai it's like it chose chad and I, for the reasons that I told you, you know, it's like, here's two guys that do the podcast stuff, they're actually good friends and it knows what's gonna make us laugh, but what is humor uh to uh when it reaches its audience? But the kind of stuff that makes other people laugh at mad tv all we were doing was it was a group of actors and writers and and writer actors and vice versa and um uh who were at at its best, that show was a group of people making each other laugh, you know? And then because we didn't have the internet, we didn't have the feed, the immediate feedback, we had a message board or something. We had emails at the very beginning which check this out people if you have a question or comment mad tv at whatever. Uh and we would get the emails on a monday morning and they would be in a binder or two like this and they would make their way around the </s><s>[INST] office and he's got [/INST] the emails, oh, they're in brian's office, </s><s>[INST] like, like your, your, this is opinions from people about different things. [/INST] The emails that, yeah, the people like literally just writing mad tv. Well, the ones I remember most vividly, yeah, we're fans saying uh </s><s>[INST] you suck, [/INST] yeah, you suck. Like a lot of that when I first started the show for real, you know, because it's a new and you're a new person. It's like, who's this fat bastard? I </s><s>[INST] feel like it that's a [/INST] Good point. Yeah, when you're reading it off of paper and you can literally crunch it up in your hand. But also, it was like, um you know, I would like to see insert weird idea from some 14 year old, you know, I want to see Stewart do this and swan that and but it was, it's a, </s><s>[INST] it's a kind of dude see, but human, [/INST] it was, yeah, it was a very shitty dudes in a loosely finder. But the, the, the thing about the show was we're trying to make each other laugh and do Dzi has found chad and I who we make each other laugh, but it's joined in and it's listen, when I finished doing TMP uh </s><s>[INST] 10 minutes of [/INST] The 10 minute podcast. I didn't really know what I wanted to do in the podcast space and this thing found me and it is genuinely cracking me up anyway, I've said enough about that, but but I do think that it's figured something out with me. It's a really </s><s>[INST] interesting idea of ai generating the premise. I mean, I do think in the future I will be able to generate comedy, I stand up, I would say the hardest form because it's ultimately like it has to be live, um I think I'll be able to generate memes, so there's like steps and then it will be able to generate a twitter account that people follow, because it's funny like, like quips and stuff like that, almost like um it's a good example, Conan O'brien is a good, I think twitter, what's like one liners to liners, that kind of stuff that's in to each form and then eventually um stand up where the timing and the chemistry of the comedian and the audience matter and then perfecting that, but I feel like all the information is there for to optimize over. So, I think that's the future and that forces us to to um to contend with what is what is, what do we find compelling and beautiful about the art form itself. So, certainly an art that's being pushed, that question is being raised, you know, is is a, I like a fundamentally worse artist than a human being. Why do we appreciate art? Is that that's something you guys have talked about. What do you think about all the dolly and and um all the diffusion based methods that are being generated that are being, that are generating art now, what do you think about [/INST] that? I know, I'll tell you what I think, but I also feel like what I'm saying is I sound like the guy who didn't like that bob Dylan brought in the electric guitar, you know, I'm starting, I, the more I talked to chat about it, the more I feel like grandpa who doesn't want to let go of this or that or I'm not ready for the printing press or the horseless carriage. But I do feel that the, that art is a connection between people. It's, it's when you look at a beautiful painting or a sculpture, you're seeing the humanity of the person that that brought that painting to life or sculpted this incredible piece of art. And I think without the human being there to make it, it's not worth as much just to have it there because art, it's it's, it's advanced. I've seen in advance. I don't know, you tell me, but I feel like just in the past three or four months, I'm just a consumer as far as that stuff goes, I'm not on the inside. I don't get it even, but it's been getting a lot better. The the betas that they're releasing. Right, </s><s>[INST] Absolutely. One of the big breakthroughs. I mean, dolly really started it is that if you train a system on language, it turns out there's a lot of language and images on the internet. But language is really where it's at in terms of the depth of human knowledge. And so if you train a system on language is able to generate some incredible art now is the breakthrough with the same kind of mechanisms they're called transformers there able to when scaled, capture some deep representation of the language that's on the internet. And so yeah, that the things has been able to generate to me look like it's novel, like it it doesn't look like it's mimicking anything. It's looks like it's creating totally new ideas and they're beautiful and they're interesting and they're all the ways that we think uh that art is interesting. The only thing that's missing is the scarcity that art often has, which is, you know, it takes a lot of work for one artist to create one piece of one human being, to create one piece of art. I can just generate endlessly. And that that makes us appreciate the thing less. For some reason, [/INST] do you have any sort of this similar opinion that I do that if art doesn't come from a human being, it's inherently worth a little less. Yeah, </s><s>[INST] I think I don't know if it's a human being, but the artist matters for me. And I think some of that has to do with the worldview of the artists and the backstory, the memories that the life that led up to this piece of art, the perspective they take on the world, the journey they took to the world, the struggle, the triumphs, all that kind of stuff. But I think ai systems can probably have the same, but they we would have to as opposed to treating it as a one black box, it would have to be an artist that has a twitter account and they have a consistent personality, that consistent avatar. [/INST] And </s><s>[INST] I think down the line have something like human rights, but then it really becomes awfully like a person. [/INST] Oh, that's terrifying. As much as I dig dudes. That's terrifying. I hope it's </s><s>[INST] terrifying. Like, you know, a lot of things that came with the internet in the digital age are terrifying, porn is terrifying. The mass, like the amount of porn that's online, that was terrifying. The uh like you mentioned bob Dylan with electric guitar, I would I would compare it more to the leap from to uh sort of to the napster and the the Spotify Ization of music, which is like you have these, it's less about albums now and it's more about individual songs and it's much easier to deliver the songs and it's more about sort of the engagement of the listener versus uh like signing the artists and like the distribution of the artist and so on. So it's just changing the way we consume stuff and uh human interaction is changing into meaningful interaction, even if some of the entities involved are not human. [/INST] Yes. And uh, I feel like, you know now, like, as I say, I feel like grandpa who doesn't want to wait all day for or who enjoys waiting all day for a baked potato. As anyway, Dana Carvey would say it's another story. But </s><s>[INST] uh, that's [/INST] from the, remember he did this bit on saturday night live. He's like, I'm a, I'm an old man and I like things the way they used to be. You know, like if you wanted a baked potato, you would have put it in the microbial head and then long story uphill both ways and digging the potato and bacon it all day and fire. But I'm like that grandpa now and I know that, you know, kids coming along, You see over the past 10 years, like babies literally knowing how to use an iPhone and it's terrifying. And I feel like I'm a little worried because I'm like, are you, is the future or the future generation is going to be able to understand that this is not Not that it's not real. It's just, I mean, it as a matter of fact, it is real. It's real. It's what you perceive perception is reality and, and you know, 99% of reality in a lot of ways, especially in a digital world where everyone is now and then with the metaverse, I don't even want to think about it. I don't even, I don't get </s><s>[INST] it [/INST] really. I </s><s>[INST] think people will figure out, you see people on, like on the train and public transit and so on, they're staring at their phone. I think you have to remember that the reason they're staring at their phone, I mean there's a lot of reasons, but one of the reasons is they're connecting with other human beings they love on that phone. So it is a source of happiness and joy. Now. Social media has a lot of negative side effects that we're all talking about and learning about. And I think that means the next generation of social media, social networks will be better and we'll learn how to do it in a healthy way. We're just entering a new digital world, that will keep the good stuff and get rid of the bad stuff. [/INST] I hope so. That's really optimistic. That sounds great. </s><s>[INST] I [/INST] mean, it because I think that we're in we're clearly in the Wild West still of the internet and just when you think you're out of it, the internet proves uh, another way that it can be dangerous and detrimental to people. Um, and populations of people and uh, it's terrifying to me. It's, it is, it's terrifying. Let </s><s>[INST] me ask you a bunch of random questions right now. Uh uh, if you could be someone else for a day, someone alive today, who would you be somebody you haven't met. [/INST] Oh, that's a really good question. </s><s>[INST] It could be dead, It could be somebody dead. [/INST] I think any answer that I have right now would be something that would be based on some sort of experience, Like, you know what I thought was very interesting was last weekend or whatever. The tribute show for Taylor Hawkins. Taylor Hawkins was the drummer for the Foo Fighters and he passed away tragically and um, so the, so the Foo Fighters, Dave Groll and everybody that got together this concert and you're watching Dave Groll, um sing, try to sing times like these, right? And he's breaking up because he lost his friend, his brother and I was watching that and he's at Wembley Stadium, as I say this, I realized that I would not want to be him in that moment, but I am curious what that would be like, That's the ultimate, like having to perform despite something extremely human happening. And uh a stadium full of people that love Dave Grohl and love Taylor Hawkins and love a rock concert and love these artists that they're getting to see up on stage </s><s>[INST] at the same time. [/INST] I wonder what that would be like to be, I guess. And I think that's just sort of coming from the root of being a performer and being in front of that many. </s><s>[INST] Have you ever had to perform while some rough stuff is going on in your, in your personal life, just mentally, [/INST] is </s><s>[INST] that how tough is that? [/INST] Um, I can, I'm fortunate enough to be able to compartmentalize, uh, I, you know, a lot of actors like to use some of the stuff if you're doing something that, um, and there's a lot of, you know, there's some acting techniques that sort </s><s>[INST] of channel it. [/INST] Yeah. Which I think is kind of, I don't know that that's, I don't know for me, it's not really the thing because I think if the writing is, is is great, the writing is really good. You don't need to channel much. You need to invest in what's there. And the, the what I've always loved about that illusion is really cracking a scene. Getting it to a point where you are feeling all of it and the most edifying stuff I've been a part of as, as an actor. And uh, I would say that it mostly comes out of dramatic work is uh, is when you're, when you actually feel the emotions that your character would feel truly, and it's not because you're pulling from a tragic thing that happened or a lost loved one or a lost love or any of that. I just did this one movie where we're, you know, we're doing the thing and it was wonderful cast and a great film and, and uh giving a speech at a wedding and uh, and it really got to us like it got to me and then one of the other actors came up and and hugged me in the characters that we were and, but the stakes of his character and what he's walked into him, the family that he's marrying into and, and what my character, my character's wife want for my wife's sister and this whole thing and it all became very real. That was a set where the director showed up to set every day, making sure that emotionally, it was a very dramatic film, making sure that emotionally the table was set for his actors, great crew and a really nice, tight little quick family as a lot of these movies are, uh, you, you really love working with these people and then it's over. Uh, but I, that's when you feel the drug, like it's like when you're golfing and you for, and it's on the green, you're like, oh, I get it now. So </s><s>[INST] in the words, you can find the emotion, the words summon the emotion, [/INST] the humanities right there. If you read a great script, you're gonna, you're gonna sob in your living room. You know what </s><s>[INST] the, the saddest, the toughest thing about being an actor is from my totally outside perspective is from the people I've interacted with is how intimate that processes between the group of people that create a thing that's a movie and then you move on to the next thing. It's almost, it's like a, I don't know, I mean that's why people have relationships on set. They get, they fall in love so sad. I mean like that's why I think of the acting world is like you fall in love with each other essentially. You become close friends, then you move on because that's kind of the process of career, [/INST] you know, like the example I just gave, if you're doing it right? Yeah, there is a certain amount of that happening, but I do still feel like you can, you've got to compartmentalize it and you've got to be able to wash it off as soon as it's over, </s><s>[INST] prostitutes say the same thing. So I, [/INST] I sometimes I'm in a hurry too. Get away from everybody because it's been it's been very emotional and with all love and respect to everyone, this was awesome. But you get pretty good at saying goodbye and being like, I'll see if I see you, you have to get good at that or else you'll never, you'll just be bent up all the time. I saw an actor once while we were doing this series and we did it for a year and uh it was, it was a lot of fun and it was a tight little group and then one of the actors, we were doing one of our last things together. We had already shot the last show and we just had to take some pictures for, you know, like some publicity pictures or whatever. So we're set up and we're taking our pictures together and then we move into these single shots and this actor was finished and I watched them. It's like, okay, so and so was wrapped in and they said some goodbyes and stuff and I didn't say my goodbye because I just did. Maybe I preferred an irish goodbye. I feel like we've said everything, you know what I mean? And this person knows that I revere them and they're an idol of mine and they walked out, walked off the sound sound stage and I literally thought to myself, that'll be the last time I see that person and the show did not come back and that was the last time I'll see them around </s><s>[INST] and that just break your [/INST] heart a little bit. But I I know what she's going back to which is her family and that's more important than all of this. And that's the thing about a tv family or a movie family when you get together and your your family for a while you do, you are you spend your days together a lot of times you see the people that you work with more than you see your loved ones. So in show business no different. Right? And uh yeah, you're doing some, you know, you got to say words and every once in a while you gotta kiss someone to pretend you love them. But it's it's it's just it underscores how for me look man, my Salvation has always been and I feel so fortunate to have had it is this kind of kind of chill, boring kind of upbringing that I want for my kids someday and I can't wait to get back to my house with my fiance and the dogs, you know, until we have kids and </s><s>[INST] live in a cabin in Canada somewhere. [/INST] Absolutely. I just want to buy some land over an aquifer as I like to say, because water will be the new money and uh, and just just make sure that all my, my kids are drinking as much H 20 as I am, which is a lot. I'm peeing right now as a matter of fact, No, no, </s><s>[INST] no, no, [/INST] I'm wearing two layers of depends, very good. </s><s>[INST] Um, so I did a podcast with bobby lee and he said he was extremely kind and he said that he was scared shitless um, to be on the podcast and he actually literally took, he asked as the first thing to go take a dump because of how scared he was. Uh, so that leads me to a question, what's the scariest thing you've ever done or maybe what's the scariest you've ever been before? Performance? [/INST] I mean I always get a little nervous. I think you're doing it right if you're still nervous, you know? Well no man, because this isn't a performance. I'm being completely genuine. </s><s>[INST] You're wearing a suit. [/INST] Yeah, that was, I feel </s><s>[INST] like that makes you nervous [/INST] wearing it makes </s><s>[INST] me nervous. Listen, [/INST] I hate wearing a fucking collar. If you're watching this on Youtube, just, </s><s>[INST] this is constantly [/INST] doing, it's like, I'm doing like a cheap Rodney Dangerfield, but I am truly, </s><s>[INST] when you move your head, it kind of makes it seem like you're like a mobster who's piste off a little bit. Yeah, you've crossed me one last time you said, you [/INST] know this mutt, it's the first time I dug a hole, </s><s>[INST] I'll take a [/INST] whole jesus. Um no, but truly I hate having a caller. I said, I can't wait to just wear pajamas in that cabin or nothing at all, walk around bobby lee style. Um this most scared I've been before a performance, I can't pinpoint, I can't pinpoint anything. I, you know, when I was a kid, right, I, like I said, I was fortunate enough to start acting as a teen and stuff professionally and I just remember my first gig and I remember saying my handful of lines in the bathroom mirror the night before going, this might be my only fucking shot, you're not gonna get me, I'm gonna be solid and I, when I'm, if I'm worried about something, I will rehearse it and rehearse it and rehearse it as an actor until it's impossible for me not to get a take at least that I'm 100% if not 95 maybe percent happy with and the rest for me is letting go, which is hard because I can be a real perfectionist. I always want another. I always want to do it a little better. That's what's great about podcasting. It's one take and you're done. There's no takes. Um you're just talking and then it's over and you're doing some silly stuff and I'll, you know, can </s><s>[INST] you say that part again about why podcasting is great, [/INST] podcasting is great because it's one take and it's over. It's just it's what I said it again. Fuck. Um I see what you did. Uh and I yeah, I fell right for it, but I'm </s><s>[INST] playing checkers and you're playing chess, that's your problem, [/INST] you know? But still when we do the podcast, we're like, finish and I look over chat and go, that one thing that I did wasn't </s><s>[INST] that fun. Like, shut [/INST] up man. Just, it doesn't matter. It's a fucking hang, we're just we're hanging with our friends out there, that's what we're doing. So </s><s>[INST] that anxiety is there that self criticism or whatever. That is that voice. [/INST] I say so sorry after takes. I'll always finish a take and go and I've had directors to the detriment of myself. I've had directors like stop doing that because I like finish taking and I also have like the the will face and I'm just like, I'll finish take and cut and I'm making a face right now. Like I smelled something and that's what I'll do. I'll literally be like, because I just I I look at, I look at what I do in the pure sense as I think, I think a lot of people want to be good at something. I've only, the only thing I've ever really wanted to be good at is being an actor and that's, that's the only thing. Of course, I want to be a good person, I want to be a good partner to my fiance, I wanna have kids and be a father that I had and, and I want to be the parent that I had from my parents who were fucking amazing, wonderful people. And uh, there's all those things that's all, that's all, you know, you should want all those things, but as far as doing a thing, like, what is my, what is my trade? You know, I want to be really good at it. My, my um, my parents grew up in napoli in Italy, right? And I say napoli because I'm italian. And so my grandfather on my mom's side, my, he was a plumber and he was also, he was also like a handyman, like, people would bring him like, you know, like the old Chianti bottle with like with the woven bottom part, like, people would bring him like a broken bottle and be like, hey, you know, can you fix this? And he'd be saying </s><s>[INST] like, you're telling the back story of Mario that's not actually your family, [/INST] like, </s><s>[INST] okay. And so [/INST] he would fix a bottle and give it back someone and he was, he was a really good plumber. My mom used to always say that guy was amazing. It was a great, he </s><s>[INST] took pride in that. [/INST] I always feel like, you know, there's what you set out to do as an idealistic little teenager. I want to be like so and so, and I want to, you know, hear my big dreams and stuff and I can't believe that I'm still in the business. Okay. That's first of all, let me say that right now, I got the idea, I can't believe it. But what I, what I really, it's the one thing that it's like, I can't give up on a take, you know, I need it to be as good as I can possibly get it and I don't really know why that is outside of wanting to be good at something when you open the yellow pages, If I'm a plumber, I'm not, you know, I'm not rotor rooter. Like I'm not the guy with the big full page ad, but I'm also not, you know, triple A abacus brothers or whatever, like the shitty one. I would like to hope that just, and I'm saying this with, with pride for what I do, I'm not trying to say, here's my standing or where I wanna be in the fucking business. That's not what I mean, I mean that I want to be good at it. You know, we all Hello, Friedman Enterprises. So that's the hotel phone. Come on. </s><s>[INST] Hello? You have some fruit. Some sliced fruit. No, do you want some sliced [/INST] fruit? Good. </s><s>[INST] No, we're good. Thank you so much. All right, bye bye. [/INST] It's always a fruit plate. Everyone's always trying to hand you a fruit plate in life. You know, it's a pretty sweet </s><s>[INST] if that was actually like the CIA and they were actually saying something else, and this is I'm just saying fake stuff about you want some [/INST] fruit, some fruit. And all of a sudden there's a red dot on my head and and the ceiling disappears </s><s>[INST] and the CIA was like, wrap it up, [/INST] wrap it </s><s>[INST] up, jump [/INST] out the window and there's a helicopter waiting. Uh </s><s>[INST] what were we talking about, distracting me? So oh the do you want to be just one page ad? I [/INST] wanna be the guy on the second or third page where it's like, you're not gonna you know, you're not going to pay with that guy charges you, but we're not gonna I'm not gonna charge you with this loser charge. You know, I want to break down the middle and the work is guaranteed. That's kind of what I wanna, you know, it's the one thing that I that I've been fortunate enough to be doing my whole life and that I want to uh I don't want to be good at, you know, everyone wants to be good at something if you're fortunate enough to be able to do what you love is a job. I mean, my God, I'm so I'm again, I can't believe I get to do it. I just want to be good at it so that I can fucking, you know, die someday and go, I try not to give up on a take, and I, you know, and I will rehearse it still in the in the bathroom mirror the night before, if I have to. Yeah, </s><s>[INST] but I still I have that self critical voice. I just after every after this podcast, I'll probably be like, you you're boring, why are you so boring? That that that [/INST] that that </s><s>[INST] and I just gave a lecture at m I T I was like, I got so much love from people, They're such beautiful people. And I just remember walking home just feeling like, like I wasted everybody's time, you know, and it's it's I don't know what that is. I don't you know, I I do hope that that's a voice that won't destroy me. You know, like, [/INST] I that's really human of you to admit that, because people don't wanna they wouldn't assume that of course from you or anything that I mean, you've got a large group of students in there listening to you and feeling the way and thinking what they think of you. Uh so that's really interesting to hear you um admit that, but it's also I would expect nothing else You have to be able to such a, I mean you're a human being </s><s>[INST] and I'm trying to figure out if that, you know, some people that might hear that, they would say, well that's a problem you have to fix. And I think that that might be just who I am [/INST] because </s><s>[INST] I'm not, you know, I've been very, very fortunate to have chemical, you know, like the depression where I get into a dark place, like it gets stuck in the, in the, in the downward spiral. It's it's usually a thing that last you write it out and you and then after a good night's sleep, you're back to uh back to your happy self. So I think I have to try to figure that out. Is that just part of the creative process being a creative human in this world? I [/INST] haven't found any other way. I'm always kicking myself </s><s>[INST] take that dude. You can't, you can't, you're, you're not gonna be human until you feel some despair, criticism [/INST] absolutely hate the ship that you're doing sometimes. </s><s>[INST] What small act of kindness were you once shown that you will never forget? There's something jumped to mind where somebody just did something that made you smile. Did you feel connected to the rest of humanity? [/INST] Yeah, yeah, lots of things, you know. Um but I remember my niece one time one of my nieces, we were in her neighborhood and she was like, she might have been five or six at the time. They're all adults now. My brother and sister older than me and the kids are all the youngest is 22. And uh yeah, anyway, one of my nieces, she was just she had ice cream, we went out and we got ice cream walking around the neighborhood, her neighborhood. And uh she said something to me that I don't think she understands how much it meant at the time. But she goes she goes, people love you here, you know that and she doesn't know where here is. She's five years old. But she was just looking at the kids playing in the park and the people walking their dogs and everyone just wants people love you here, you know that but she didn't know how much I needed to hear that at that point which is really heavy for me. I'll never forget it. I've never told her that well. And anytime you get a little something from people, especially in a terrier ass out city like L. A. Where somebody has any fucking time for you when someone can slow it down and say something. You know I saw this actor once in my grocery store that I go to who made me laugh so fucking hard in this one movie. And every time I see this clip I still laugh and um I am kind of shy, you know personally. But so he uh he was walking by, he was walking out and I was walking in and I go that's that guy and I did not stop to just let him know how great I thought he was in this film and I always kind of regret it, you know what I mean? So as hard as it is and sometimes I still don't, if I see someone that has done something in, in, you know, in any way it doesn't have to be in show business or anything like that, I try and I try and say hey that's that's really good, you know what I mean? Um because to get that from someone can mean a lot, you </s><s>[INST] know a certain time in life when you need [/INST] it, I </s><s>[INST] can make a big difference. I mean I sorry to uh take it back to my new girlfriend, the waitress. [/INST] Oh yeah, but </s><s>[INST] she, there's something about her saying sweetheart Yeah, I was in a pretty low place for some reason mentally and it's just that the basic human kindness was nice. [/INST] Yeah, yeah, yeah, yeah, I hear you. I was at a restaurant in uh new york recently and I was shooting something and my fiance was able to fly in for a week and uh but she was back at the hotel and it's like I felt like I was cheating on her because there was this nice waitress at this barbecue place I went to and first of all, my fiance would not like me eating any greasy, sugary barbecue. So I felt like I was cheating </s><s>[INST] on delicious food over [/INST] but the waitress was one of these, you know, she was this the kind of server who's like, hey hon you think, hey sweetie, like blah blah blah, but like so chill and at ease in the middle of a part of new york, that's really, you know, kind of fucking pretentious and you know, and everybody but sweet people fucking way better people than we got here. But uh I know that but you know, it's part of new york and whatever I'm there working and people, I'm like, you know, I've been trying to impress one another and, and uh she was just even had some sort of an accent that was not, didn't feel like an atlantic american accent. Uh yeah, although those, yeah servers that say sweetheart and hon that's what we need from ai we need that, that Jetsons server. But </s><s>[INST] once in a while just calls you sweetheart, what comforts you on bad days [/INST] is their little </s><s>[INST] sources of comfort? Small things they do that kinda make you feel good. Like for bobby, that would be a little Skyrim, [/INST] a little </s><s>[INST] stroll. Well [/INST] I, I've been atlantic, I dilute some coke into whiskey in the morning, like Stevie Ray Vaughan and then I yeah, yeah, I didn't last too long, weird. Um I see you go for me if I, I'm kind of a homebody. So if I, the the point at which I smoke just a little bit of pot and then go, like lay down on the couch and and perhaps if my fiance is kind of nodding off or she's just like looking at her phone and I sneakily turn on some wrestling. Okay, Because I grew up watching wrestling and that stuff, it's the sky room effect. I mean, you want to talk about a complete escape. This stuff makes no sense in the world. It's an art form that is so uniquely weird, but at the same time, so everyone, when it's good, everyone is invested in the illusion. Even the audience, they cheer the good guys, they blew the bad guys. So if I'm like that and then I got are two cute little dogs there and I'm annoying my little dog lou leo and you know, trying to kiss them right on the fucking mouth. And I've had a little bit of pot and the dogs like stop pot. It's not good for me. Um of course, don't ever blow pot in your dog's face. That's that's a small comfort, I guess. That's a handful of things. </s><s>[INST] No, that moment painted. That was like a little painting. You're not supposed to do [/INST] this. You're </s><s>[INST] not supposed to do this. Yeah, it's it's it's it's a tough question. Um I would say, I would say programming robots, I there's bringing to life actually programming at all. So I don't know if you're how familiar you are with programming, but you right, some text on the page, right on the screen and it's brought to life like it does something and, and that's kind of, that's a really tiny version of maybe having a child. Like you, you created something that is now living in some smaller big way with embodied robots that are legged robots. That's especially clear. And for some reason, that's a source of comfort for me. That, that the, the power of programming, but also the elegance of programming. Just the whole thing. It's a, it's a source, uh, it's a source of happiness. There's so many things I've been very blessed with enjoying anything. Like that's part of the struggle I have in life. Is that the simple stuff is the source of a lot of happiness for me. Which leads to a lot of laziness. So I have to like give myself artificial deadlines. I have to be freaking out on purpose in order to be productive in this world at all, you [/INST] seem like an extremely dutiful busy guy. No, no, </s><s>[INST] no, I am. But because I'm constantly creating artificial stress and deadlines and all that kind of stuff, otherwise I would just sit there looking at a tree happy. I'm truly happy with everything. That's [/INST] awesome. Yeah. That's not a </s><s>[INST] line of coke in the, in the, in the whiskey in the morning. That's that, that's the thing that, uh, [/INST] breakfast shake, </s><s>[INST] by the way, one of my most favorite guitars. I play guitar too. That's the source of comfort. [/INST] Oh yeah, I have seen you play some guitar, that's all. </s><s>[INST] Who's the greatest wrestler of all time? [/INST] Greatest in ring performer of all time is bret the Hitman Hart. What's </s><s>[INST] the difference in ring versus, [/INST] well, there's, you know, there's many facets to the art form. A lot of people are great on the mike, but they're not so great. Once they get in the ring, a lot of people have all the showmanship and stuff, but then they're not necessary. It's a wonderful package. But then they get to the ring or they open their mouth and there's nothing going on. So </s><s>[INST] who's the greatest in ring? I [/INST] think the greatest in ring is bret hart. I don't think there's anyone better than, than bret the hitman Hart, uh, </s><s>[INST] what makes them so good? [/INST] Well, he </s><s>[INST] had an action figure of him, him in Russia and we didn't know what the hell that was. [/INST] Sure. Yeah, it was just a guy in pink tights. Uh, he, everything makes sense. Every single thing is rooted in the thing that just happened and everything that he does is to set up what he's going to do. Uh, they call it and I'm just a wrestling nerd. But the wrestlers, I guess call it ring psychology, the things that you have to do to, to make it seem like you're, you're suffering or you're coming from behind or whatever. And then also just the physicality of it, He does it at a, he would do it at 100 miles an hour and never hurt anybody. Uh, although you know, I, I also love, uh, the every, you know, the greatest wrestler of all time, everyone says, and they're right, is ric flair, nature boy, ric flair. </s><s>[INST] Everyone says this. [/INST] Yeah, I think if you know what you're talking about, um, because he's the best on the mic, he's, he's also incredible in the ring. And then for me, the sentimental favorite, which we've actually on duty chad had sort of a uh, charlie Rose asked interview with me about this, my fascination with hulk Hogan because to me just, he was superman. I was a little kid and I saw him and that's imprinted. But yeah, this is like asking me who my favorite child is, </s><s>[INST] right? So the [/INST] rock, when the rock was, I mean the rocks? The rock, Yeah, </s><s>[INST] hulk Hogan is um, He's the weirdest one, right? For me from the outside. [/INST] Super </s><s>[INST] weird that I don't know what what that is exactly. It's, [/INST] everything is weird about him. </s><s>[INST] He's got the [/INST] head, like he would proudly have this bald head with long hair handlebar mustache in this ketchup and mustard, you know, tights, which he says, he credits Mcdonald's with the tights. He </s><s>[INST] literally does, [/INST] he says that the red and yellow came from angelo Calfo, who's randy macho man, savage and Lanny Paphos, dad who was a wrestler and a promoter. He said that he saw him wearing yellow and he, you know, he's a Tampa guy. So he had that brown skin and the hair and everything. So he's like, oh, that's what I wanna do. And also the brand recognition of like what I should do it. Like Mcdonald's literally, and he's a big, you know, swollen, muscular guy with tan brown skin screaming at me to eat my vitamins and stuff when I'm eight years old. That was extremely, uh, yeah, he's like superman. But I know there's a person behind that guy, you </s><s>[INST] know? Well he's [/INST] terry Bolivia the dude who you know, does whatever he does with his life, you know what I mean? </s><s>[INST] Yeah, complicated life. [/INST] Yeah, yeah. </s><s>[INST] Maybe you should change the dudes the colors to, to yellow. [/INST] It's </s><s>[INST] currently orange and uh, boy sky blue. [/INST] Yeah, it's like a nice sky blue. </s><s>[INST] What advice since you're wearing a suit? I feel like you're qualified to give advice. What advice would you give to young people, high school college about how to have a career that can be proud of or how to have a life they can be proud [/INST] of. I mean, you have to listen to your gut all the time. That's the only, that's the compass that we have is listening to your gut. </s><s>[INST] What does your gut tell you? This is, is that, was that originally the dream of being an actor? [/INST] Yeah. For me, </s><s>[INST] your parents support that at all. [/INST] I had the advantage of having parents who were immigrants. So they didn't really know a lot about what you, </s><s>[INST] yeah, [/INST] of course I'm studying and I'm skipping school to go do auditions and stuff. No, I, I just kind of feel like, you know, and I know it was different from my older siblings because my parents had just shown up in Canada, I was born like 10 years later. Um, uh, you can get away with some things and you can actually, you know, I think my parents, they wanted us to, they didn't have a whole lot to tell us about what to do. Um, they weren't going to do that with us because they're in this brand new world and there's all these possibilities and, but there was a, there was something that they, I, I feel like they had to do, which was tell us to do what we love, if you love doing it, do it. And I feel like that's really served me. And what I would tell young people is if you can find something you love and nowadays with the internet and finding other people that, you know, it's not like, you need to find a lot of people anymore. You just need to find the people that dig what you dig and if you can make a career out of doing something that you love, it's been said, it's it's a good thing, you know. How </s><s>[INST] long did you take you to figure out that you really love um acting, you know because sometimes you have a dream and then you meet the dream meets reality right? And then the reality might be much less pleasant and much darker than the dream. [/INST] Well the reality is less pleasant, you know, and and there are things that happen uh during an experience of shooting something that that you could take or leave, right? But the the you know the part where you're on set and you you know, you've rehearsed for a minute or whatever, at least you know where you're supposed to stand and you know all your lives show up knowing everything, knowing what you're gonna do and uh what you aim to do and those moments make it all worth it when you're you know, not sound like a douche bag but between act you know, action and cut. That's the stuff that is uh that that makes me that has me continuing to do do what I do aside from the fact that it's like I don't know how to do anything else. </s><s>[INST] You think you love to do. Like a dramatic, like like a mob movie. [/INST] Yeah, like the one of the Inside Game, I was just talking about this other movie, I just said it was a little while ago called american woman that was very heavy. Um and uh I love doing dramatic work, I love it, I love it. Yeah. And I played that the in Inside Game. It was kind of a, you know, it was there was a mob element and uh the fellow was, well, you know the stories here or there with regard to how deep into the, well he was a book, he was just running money, you know, he was making a lot of money for a lot of people and he figured out how to, you know, cook it with this dude um who was an NBA ref and and it's a very interesting documentary. The thing that just untold under the untold series, they cover it. But getting to play that guy that was, that was a that was a gas for me because he's like a he was, you know, there was a lot of unsavory stuff and he's definitely the guy, the character in the movie who is the wild card and and and you don't wanna necessarily mess with him. And I got this this fellow who was the real guy speaking to him, it was just bizarre to hear like I said to him, he was a little concerned about this and that like, hey, you know, you say whatever the you want in your movie, I got my book and I got this other fucking deal, but he goes, you know, I didn't do this and I didn't do that. And I'm like, yeah, all right, I got you. And he goes, I'm telling you like I did I'm talking to you one of them. I did not do this. I did Okay. I'm just tell you do whatever you want with your movie. But this is what's up. And I said you ever seen Goodfellas? I love that movie because like I said, he did some unsavory ship. And I go remember the scene where uh where you know the guy, the neighbor, Lorraine broncos neighbor was, you know, made her uncomfortable and touching on her and she she goes to ray Liotta and he goes, where the fund does this guy live? And then he goes remember, and he walks across the street and pistol whipped the dude, you touch her again, you're dead. You hear </s><s>[INST] me, don't [/INST] you fucking great scene. He goes, I love that scene. I go, that's you. So you're doing ship that we know is terrible. But we love you. He goes, all right, I got it. And then I said there's this one scene, I explained the scene to him where the one of the mobsters uh tough guys was in the window of the car and jimmy. My character is very coked up at the time and he's hemorrhaging money here and there and making bad bets because he's getting sloppy. And this guy wants to bug him about some Jets giants bed or something. I'm like telling you fucking asshole, don't fucking do it. He's like, yeah, well the giants and in the scene jimmy, my character grabs him by the by the lapels and just smashes his face against the roof of the car and I I say this to jimmy and he goes, oh yeah I would have done that. That's not a big deal. </s><s>[INST] I wonder also the interaction, I wonder what the filming of um probably my favorite gambling movie is um casino with with joe Pesci and De Niro. Like when they're out in the desert yelling at each other. I wonder how many takes that is like because they I don't I don't know how scripted that is. I mean it probably is a little bit but like I don't think you can script the performance that joe pesci does [/INST] don't make a fuss out of me. Ace. </s><s>[INST] Yeah, [/INST] like I fucking brought you here, he's </s><s>[INST] just like pointing at the that that that energy and they're standing there and De Niro's like like that that whole thing and then in the pet like that that energy, what is that? I mean they must they somehow find it together. [/INST] You can tell me that that was one take and I believe you could tell me that that was seven takes and I would believe </s><s>[INST] you all the takes had that energy like they were playing with it right there. They're playing with that the this Yeah, I mean they took on a real personality in those scenes and really cared them for. I mean, it's just a brilliant, brilliant performance doesn't get like comedies like mob movies probably don't get enough credit either because it's seen as like [/INST] mob movies don't get enough credit </s><s>[INST] in the Oscars. I mean like [/INST] Oh yeah. Yeah. Yeah, because it seems like a trope. It's like giving a western, it's gonna be a hell of a western or whatever because it's like an old Hollywood trope. Yeah, no, I that scene is so great because they're never at their at the height of their friendship in a way and they're also pretty much about to let go of it and become enemies and both things are happening at the same time and and Pesci drives them out to the desert. And if I remember correctly, De Niro's character, Ace Rothstein Rothschild, he says I gave myself 5050 whether I'm coming back. </s><s>[INST] Yeah, it's such a good scene. It's usually my prospects of coming back from the desert would be 90 to 10 or something like that. But now this time I wasn't sure and there's the car driving really fast and then joe pesci is like, you motherfucker you like whatever he was doing a jewel, like of course there's anti Semitism [/INST] or not </s><s>[INST] between friends who gives a sh [/INST] all </s><s>[INST] that kind of stuff. Yeah, I mean, brilliant, brilliant performances. So yeah, I I can understand why you love the art and putting it all out there and [/INST] it's fun, it's fun and it's still fun, it's still crazy fun if I go a while without getting a gig, you know, if I go a minute then I end up and I work on something, I'm like, it is like, it's like, oh I've been thirsty for this, like I actually am really so happy, even if it's something where it's like, you know, the, the, the things where this was a pain in the ass and that, or whatever, you're on the road doing something and you know anything, whatever, you lost your luggage or whatever the heck you've got going on in your day to day life that everyone brings to work and tries to let go of, once we're doing the scene Oh man, it's the best, </s><s>[INST] but you know, that said, you're a great actor, but I just think I speak for a lot of people that you're also, there's a charisma to you, that's great to reveal in raw form in different podcast in Dude Z 10 minute pod just as a guest and podcast, it's always really fun to watch [/INST] you the </s><s>[INST] way you have fun the way you think uh the raw the raw, which is a nice compliment to your kind of acting. [/INST] That's really sweet Yeah, well, you know, look, you said, you know, uh </s><s>[INST] you're making that face, [/INST] I'm making that face, I'm making that after the take face, No, I love doing stuff off the cuff, that's kind of you to say and I dig I really do dig doing stuff in front of an audience because I love seeing, I don't give it to myself very often if I'm doing, even if I'm you know, I've done a bunch of multi camera sitcoms and stuff, mad Tv was shot in front of a live studio audience, </s><s>[INST] I [/INST] love it, but I can only hear them, you can't see them because of the lights, like it is in in a lot of performances and I would imagine with stand up it's you know, you see the first couple of rows um I've done I do this character that does stand up and I used to take him out and do things with him and do a little bits here and there, I haven't done it in like four or five years, </s><s>[INST] I think bobby say that character opened up for bobby. [/INST] Yeah, but he said I have to do it as myself too, I think in that podcast he's like, okay you're gonna come with me and open for me and brea but you have to do as yourself </s><s>[INST] that [/INST] it did and I did the character uh you know who's a character I came up with on 10 minute podcast, he's just this comedian, right? He calls himself an open mic veteran, you know, he's been doing open mics forever and so I did it opening up for bobby and he's like you have to do some of it as yourself, so I just kind of did this bit where I would do some of his jokes and then I would take lee leon silly, I gotta fucking wig on and I take the wig off and I go and as myself I start explaining it, hello, my name is will see the reason that it's funny is because Arnold Schwarzenegger is always, he's in these movies and he's got the thick Austrian accent but he's like my name is Ben Williams, I'm a I'm a cop from colorado, no you're not. Uh and it doesn't make sense as the comedian character that I'm doing because that character doesn't do impersonations okay carrying on and then I put the wig back on and go back into this dumb thing and uh I don't think it was very good, but bobby required it in order for me to open for him, he's like you're not fucking doing it so I'm not going to get up on stage and not do we agreed I'll do it, but um having been up there just in you know whatever I've done it like a dozen fucking times, not a bunch of times, right, like nothing uh and you know these comedians that go up every night sometimes two times a night, it's I do, I will say I love performing in front of people when I get the chance but it's it's uh it's a specific thing that that uh that I I just I just I don't know, I got to go back to this, it's like the providing value, you know, I think great stand ups are fucking incredible. I'll go, you know when I've gone and watch stand up, you know, there's your friend you're going to see, but then there's this other person who really speaks to you, you know what I mean? And if you like one comedian tonight, that's a lot because a a a comedy club is like a fucking crazy restaurant where there's no menu and it's like, what would you like? There's nothing else like that. There's like, you don't go to like a, like music place, what do we got here? We got christian metal and there's some world music and then there's a reggae thing and it's all rammed in together. You don't go to a restaurant, I'd love a nice steak. Cool. First here's a bowl of Froot loops and then then we got you a and then this is our sushi tower and well, what about the steak? The steaks coming and then blah blah blah, oh no, the steak got bumped. So there's no steak, but here's a fucking shitty store bought cheesecake, you know, and that's what comedians are up against when they go into a place, it's like, I don't pair well with the poached salmon, you know, I'm chicken fingers. I already, I already am chicken fingers. So, you know these great comedians that are able to go up on a night where poached salmon goes up and then it's like funk. I'm, you are also spicy. I got some kick to me </s><s>[INST] for me even going to open mics. It could be a wonderful escape. [/INST] Yeah, </s><s>[INST] I mean just laughing, laughing together with others can make you don't know, it just feels really good [/INST] when we've done like, you know, like, and I hope to do it with dude see, but like live podcasts are fun in front of groups of people and you know, you talk to them afterwards and and take some pictures and man, they are, they forgot what the funk they got going on and a lot of them got to go back to work the next day. It's a Wednesday or thursday, you know? No, it's, it's, it's a lot of value. I'm fortunate enough to be busy doing my own bullshit. </s><s>[INST] What's the meaning of life? [/INST] Uh, what is </s><s>[INST] why? Why? Why, why why was [/INST] it the meaning of life? Wasn't, didn't they explain it at the end of meaning of life? I think it was Michael Palin that said, uh, try to get a walk in, be nice to neighbors even a fiber. Wasn't that the yeah, I think it's, I think </s><s>[INST] it's have a [/INST] bowl of brand in the morning and don't take yourself too seriously. </s><s>[INST] No, [/INST] Well No one gets out alive, I think is the herman </s><s>[INST] has one of my favorite writers, He's a nobel prize winner um, in a in a book called Steppenwolf says, learn what is to be taken seriously and laugh at the rest. [/INST] That's awesome. </s><s>[INST] What what's the percentage distribution on that? So how much of life should you take seriously? And then how much do you just laugh [/INST] at a man if you can laugh at everything, you're you're winning? But that's almost impossible. I think that there's there's uh and also could be quite irresponsible to do that. I take things, I take a lot of things way too seriously. I know that </s><s>[INST] uh I [/INST] do, I do, I really do, </s><s>[INST] People will be in part surprised by that, but I think that radiates from you [/INST] really? Yeah, I do, I don't take things way too fucking seriously sometimes. But </s><s>[INST] yeah, [/INST] we're gonna loosen the neck up. But no, I think that's that's really good. That's that's really good stuff. I I don't know what the percentage is to have a good life or or or or a happy healthy life, but, you know, for me, the meaning of life is getting to live it as long as you hope to, that's nice. And um and when you're when you lose someone or if perhaps you're faced with your own mortality, I think that puts that into perspective and but, you know, get </s><s>[INST] lots of fiber, [/INST] get lots of fiber, be nice to everybody. And uh yeah, don't take things too seriously. It's a good, it's a good one. Our minds are fucking big weird big it's a big weird shitty fucking bucket of shit that's trying to get you to think horrible shit about yourself all </s><s>[INST] the time. Shitty bucket of ship. [/INST] It </s><s>[INST] is a book I never read but I read the title and it's good Words to live by which is uh don't sweat the small stuff and it's all small stuff. That's another way [/INST] that dr Phil wasn't dr Phil. I </s><s>[INST] don't know. But I think the conclusion is also has fiber as part of it. I think that all ties it together and in the end of course just put love out there in the world. I think that's a pretty good way. [/INST] What would you say is the meaning of life? I </s><s>[INST] would say love. Yeah. Yeah. It's a it's a long conversation on what that really means. But I'm sure robots are involved. Yeah. [/INST] Well let me tell you, I feel a little safer knowing that someone who has a hand in bringing these robots to the masses as you do has that opinion of of love and how important it is. I think that's great because otherwise it's going to be that fucking scene from T. Two where uh linda Hamilton's holding onto the fence and getting all of her flesh blown off of her skeleton before the rest of her is is wiped away because the skynet shit. Anyway. I'm just terrified of dudes all the time. That's why I think that they will </s><s>[INST] dudes in the wrong hands can do a lot of damage. [/INST] That's why chad and I need to do our best to control </s><s>[INST] it. Need to travel back in time and murder chad [/INST] I </s><s>[INST] think. [/INST] Yeah, that's yeah, </s><s>[INST] that's the only way [/INST] it's been said. I </s><s>[INST] don't know why I need to travel back in time but it just [/INST] uh today but I'm </s><s>[INST] very suspicious. [/INST] My nefarious plans for chad involve going back to tomorrow and planning for yesterday and then and hopefully do Dzi will give me the answer there with what, what it is to do with chad's frozen body. If I got to drive it out too. If I got to take my, you know, if I got to get, get a hold of it like one of those Tesla Mom vans and shove my garage freezer in it and plug it in and shove chad in there and drive out to Arizona and deliver him under a mountain or wherever the fun this place is. And so here's this dog tag. What does this get me Like? That's going to be 300 bucks. Do you have, Do you take Amex? No. And I'd be like sh </s><s>[INST] it [/INST] and I'll just dump </s><s>[INST] them somewhere. Breaking [/INST] bad stuff. </s><s>[INST] Well I would like to thank you and the, what is it? The Canadian international agency apparel [/INST] for. I </s><s>[INST] can't wait for the sneakers from dudes. I can't wait for all the, all the podcasts. Uh that Ai can and all the trouble I can get you in. So I'm a huge fan of yours. It's a huge honor that you would talk with me today. Well this has been amazing, [/INST] cheers pal likewise and I'm happy to be here. Man, cheers Holy! What? </s><s>[INST] Thanks for listening to this conversation with Will Sasso to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from john Candy, one of Will's favorite actors. I think I may have become an actor to hide from myself. You can escape into a character. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] it's a meta reform of being able to start new countries. Okay, so that's one problem, but you could push back and say that's a feature. Because a lot of people argue that tradition is power. Through generation, if you try a thing long enough, which is the way I see marriage, there's value to the struggle and the journey you take through the struggle and you grow and you develop ideas together, you grow intellectually, philosophically together. And that's the idea of a nations that spans generations that you have a tradition that becomes more, that strives towards the truth and is able to arrive there, or no, not arrive, but take steps towards there through the generations. So you may not want to keep starting new governments. You may want to stick to the old one and improve it one step at a time. So just because you're having a fight inside a marriage doesn't mean you should get a divorce and go on Tinder and start dating around. That's the pushback. So it's not obvious that this is a strong feature to have [/INST] to launch new governments. There's several different kinds of lines of attack or debate or whatever on this, right? First is, yes, there's obviously value to tradition and people say, this is Lindy and that's Lindy. It's been proven for a long time and so on. But of course there's a tension between tradition and innovation. Like going to the moon wasn't Lindy, just it was awesome. And artificial intelligence is something that's very new. New is good, right? And this is a tension within humanity actually itself because it's way older than all of these nations. I mean, humans are tens of thousands of years old. The answer to humans are millions of years old, right? And you go back far enough and the time that we know today of the sessile farmer and soldier is, if you go back far enough, you want to be truly traditional. Well, we're actually descended from hunter-gatherers who were mobile and wandered the world and there weren't borders and so on. They kind of went where they want, right? And people have had done historical reconstructions like skeletons and stuff like that. And many folks report that the transition to agriculture and being sessile resulted in diminution of height. People had like tooth decay and stuff like that. The skeletons, people had traded off upside for stability. That's what the state was. That was what these sessile kinds of things were. Now, of course, they had more likelihood of living consistently. You could support larger population sizes, but it had lower quality of life, right? And so the hunter-gatherer, maybe that's actually our collective recollection of a Garden of Eden where people, just like a spider kind of knows innately how to build webs or a beaver knows how to build dams. Some people theorize that the entire Garden of Eden is like a sort of built-in neural network recollection of this pre-sessile era where you're able to roam around and just pick off fruits and so on, low population density. So the point is that I think what we're seeing is a V3, you go from the hunter-gatherer to the farmer and soldier, the sessile. Nations are here and they've got borders and so on. To kind of the V3, which is the digital nomad, the new hunter-gatherer, we're going back to the future because you know what's even older than nations is no nations, right? Even more traditional than tradition is being international, right? And so we're actually tapping into that other huge thread in humanity, which is the desire to explore, pioneer, wander, innovate, you know? </s><s>[INST] And I think that's important. To make America great again is to dissolve it completely into oblivion. [/INST] No, that's a joke, that's a joke. Yeah, I know it's a joke. Humor, I'm learning this new thing. Yes, the new thing for the role. The chat pod emulation isn't fully working there. </s><s>[INST] Yeah, yeah, yeah, glitch. [/INST] That's where in the beta. And let me just say one other thing about this, which is there are, I mean, everybody in the world to, okay, let's say, I don't know what percentage, let's say 99.99%, or it rounds to that number of political discourse in the US focuses on trying to fix the system. If those folks, I mean,.01% of the energy is going towards building a new system, that seems like a pretty good portfolio strategy, right? Or 100% are supposed to go and edit this code base from 200 something years ago. I mean, the most American thing in the world is going and leaving your country in search of a better life. America was founded 200 years ago by the founding fathers. It's not just a nation of immigrants, it's a nation of immigrants, right? Immigration from other countries to the US and actually also immigration within the US. There's this amazing YouTube video called, it's like 50 states, US population, I think 1790 to, it says 2050, so they've got a simulation. So you just stop it at 2019 or 2020. But it shows that like Virginia was like number one early on and then it lost ground in like New York gained. And then like Ohio was a big deal in the early 1800s. And it was like father of presidents and generally all these presidents and later Illinois and Indiana. And then California only really came up in the 20th century, like during the Great Depression. And now we're entering the modern era where like Florida and Texas have risen and New York and California have dropped. And so interstate competition, it's actually just like inter currency competition. You know, you've got trading pairs, right? You sell BTC by ETH, you sell Solana, you sell Monero by Zcash, right? Each of those trading pairs gives you signal for today on this currency is down or up relative to this other currency. In the same way, each of those migration pairs, someone goes from New York to Ohio, Ohio to California, gives you information on the desirability of different states. You can literally form a pairs matrix like this over time. Very much like the link matrix that's shaped America in a huge way. And so, you ask A, if this nation of immigrants that was founded by men younger than us, by the way, the founding fathers were often in their 20s, right? Who, you know, endorsed the concept of a proposition nation who've given rise to a country of founders and pioneers who've literally gone to the moon, right? Those folks would think that this is the end of history, that that's it, we're done. Like we've done everything else. I mean, there's people in technology who believe, and I agree with them, that we can go to Mars. They might even be able to end death, but we can't innovate on something that was 230 years old. </s>

<s>[INST] well from an engineering perspective. Both the movies you mentioned Wally and uh Terminator The 1st 1 it's probably achievable humanoid robot maybe not with like the realism in terms of skin and so on. But that humanoid form we have the humanoid form it seems like a compelling form. Maybe the challenges that's super expensive to to to build. But you can imagine maybe not a machine of war but you can imagine terminator type robots walking around. Uh And then the same obviously with Walleyes you basically. So for people who don't know you created the company on key that created a small robot with a big personality called Kaswell that just it does exactly what he does. Which is somehow with very few basic visual tools is able to communicate a depth of emotion and that's fascinating. But then again the humanoid form is uh super compelling. So like Cosmo is very distant from a humanoid form and then the terminator has a humanoid form, you can imagine both of those actually being in our society. [/INST] It's true. And it's interesting because it was very intentional to go really far away from human form. When you think about a character like Cosmo or like Wally, where um you can completely rethink the constraints you put on that character um what tools you average and then how you actually create a personality uh and uh level of intelligence interactivity that actually matches the constraints that you're under, whether it's mechanical or sensors or ai of the day. This is why I almost um was always really surprised by how much energy people put towards trying to replicate human form in a robot, because you actually take on some pretty significant um kind of constraints and and downsides when you do that. Um The first of which is obviously the cost where it's just the the articulation of a human body is just so like magical. Um in both the precision as well as the dimensionality that to replicate that even in his quote, reasonably close form takes like a giant amount of joints and actuators and uh emotion and and you know, sensors and encoders and so forth. But then um you're almost like setting an expectation that the closer you try to get the human form, the more you expect the strength to match. And that's not the way I works is there's places where you're way stronger and there's places where you're weaker and by moving away from human form, you can actually uh change the rules and embrace your strengths and bypass your weaknesses. </s><s>[INST] And at the same time the human form like has way too many degrees of freedom to play with it, it's kind of counterintuitive just as you're saying, but when you have fewer constraints, it's almost harder to master the communication of emotion. Like you see this with cartoons like stick figures, you can communicate quite a lot with just very minimal like two dots for eyes and a line for for a smile. I think like you can almost communicate arbitrary levels of emotion with just two dots and a line and like that's enough. And if you focus on just that you can communicate the full range and then you like if you do that then you can focus on the actual magic of uh human and dot line interaction versus all the engineering [/INST] messes, like dimensionality, voice, all these sort of things actually become a crutch where you get lost in the search space almost. Um And so some of the best animators that we've worked with um they almost like study when they come up uh you know, kind of building their expertise by forcing these um projects where all you have is like a ball that can like kind of jump and manipulate itself or like really really like aggressive constraints where you're forced to kind of accept it, extract the deepest love of motion. And so in a lot of ways, um you know, we thought when we thought about Cosmo is like, you're you're right, like if we had to like describe it in like one small phrase, it was bringing a Pixar character to life in the real world. It's uh it's what we were going for. And um and a lot of ways what was interesting is that with like Wally, which we studied incredibly deeply and in fact, some of our team were, you know, kind of had worked previously at um, at Pixar on that project. Um they intentionally constrained Wally as well, even though in an animated film you could do whatever you wanted to, because it forced you to like really saturate the smaller amount of dimensions. But uh you sometimes end up getting a far more beautiful output um because you're pushing at the extremes um of this emotional space in a way that you just wouldn't because you get lost in the surface area. If you have like something that is just infinitely articulable. </s><s>[INST] So if we backtrack a little bit and uh you thought of cosmo in 2011 in 2013, actually uh designed and built, it what is the donkey, what is cosmo. I guess who is Gospel? And uh what was the vision behind this incredible little robot, [/INST] We started uh donkey back in like while we were still in graduate school. So myself and my two co founders, we were PhD students uh in the robotics institute at Carnegie Mellon. Um And so we were uh studying robotics, ai machine learning kind of different, you know different uh areas. One of my co founder is working on walking robots, you know, for a period of time. And so we all had a um a bit of a really deep kind of a deeper passion for applications of robotics and ai where um there's like a spectrum where there's people that get like really fascinated by the theory of AI and machine learning robotics where um whether it gets applied in the near future or not is less of a kind of factor on them, but they love the pursuit of the like the challenge and that's necessary. There's a lot of incredible breakthroughs happened. There were probably close to the other and the spectrum where we love the technology and the um and all the evolution of it, but we were really driven by applications like how can you really reinvent experiences and functionality and build value that wouldn't have been possible without these approaches. And that's what drove us and we had a kind of some experiences through previous jobs and internships where we like got to see the applied side of robotics and at that time there was actually relatively few applications of robotics um that were outside of um you know pure research or industrial applications, um military applications and so forth, there were very few outside of it. So maybe, you know, my robot was like one exception and maybe there are a few others, but for the most part there weren't that many. And so we got excited about consumer applications of robotics where you could leverage way higher levels of intelligence um through software to create value and experiences that we're just not possible um in in those fields today. Um and we saw kind of a pretty wide range of applications um that varied in the complexity of what it would take to actually solve those. And what we wanted to do was to commercialize this into a company but actually do a bottoms up approach where we could have a huge impact in a space that was ripe to have an impact at that time and then build up off of that and move into other areas. And entertainment became the place to start because um you had relatively little innovation in the toy space uh and entertainment space, you have these really rich experiences in video games and uh and movies, but there was like this chasm in between. And so we thought that we could really reinvent that experience. And there was a, A really fascinating transition technically that was happening at the time where the cost of components was plummeting because of the mobile phone industry. And then the smartphone industry. And so the cost of a micro controller of a camera, of a motor of memory, of microphones, cameras was dropping by orders of magnitude. And then on top of that with iPhone coming out in 2000, uh I think it was 2007 I believe. uh </s>

<s>[INST] typical for you to say something is easy. I got it. It's not as challenging as the other ones. Okay, well [/INST] it's okay. Maybe it's obvious how to solve it. The third one's the hardest. Where do we get a lot of people don't even think about the third one and you can see it is different from the second one. So the 2nd 1 is dynamic. The second one is like say there's a an obvious example is like a car stopped at a red light, right? You can't have that car in your map because you don't know whether that car is going to be there or not. So you have to detect that car in real time and then you have to, you know, do the appropriate action, right? Also that car is not a fixed object. That car may move and you have to predict with that car will do, right? So this is the dynamic problem. Yeah. So you have to deal with this. Um, this involves again, like you're going to need models of other people's behavior. </s><s>[INST] Do you, are you including in that I don't want to step on the third one. But are you including in that your influence and people [/INST] That's the 3rd 1. Okay. That's the best we call it. The counterfactual </s><s>[INST] Yeah. That I just talked to judea pro who's obsessed with counterfactual. [/INST] Oh yeah. Um so the static and the dynamic our our approach right now for lateral will scale completely to the static and dynamic. The counterfactual. The only way I have to do it yet. The the thing that I want to do once we have all of these cars is I want to do reinforcement learning on the world. I'm always going to turn the exploiter up to max. I'm not going to have them explore what the only real way to get at the counterfactual is to do reinforcement learning because the other agents are humans. </s><s>[INST] So that's fascinating that you break it down like that. I agree completely [/INST] my life thinking about </s><s>[INST] this beautiful. Uh, so and part of it because you're slightly insane because um [/INST] not my life just the last four years. </s><s>[INST] No, no, you have like uh some some non 0% of your brain has a madman in it, which that's a really good future but there's a safety component to it that I think when there's sort of with counterfactual and so on, that would just freak people out. How do you even start to think about just in general? I mean you've you've had some friction with nitze and so on. I am frankly exhausted by safety engineers, the the prioritization on safety over innovation to a degree where kills, in my view kills safety in the long term. So the counterfactual thing, they just just actually exploring this world of how do you interact with dynamic objects and so on. How do you think about safety? You can [/INST] do reinforcement learning without ever exploring and I said that like, so you can think about your in like reinforcement learning is usually called a temperature parameter um and your temperature parameter is how often you deviate from the arg max, I could always set that to zero and still learn and I feel that you'd always want that set to zero on your actual system. </s><s>[INST] Got you. But the problem is you first don't know very much and so you're going to make mistakes. So the learning the exploration happens through mistakes. [/INST] Yeah, but okay, so the consequences of a mistake open pilot and autopilot are making mistakes left and right. We have we have we have 700 daily active users, 1000 weekly active users. Open pilot makes 10s of thousands of mistakes a week. These mistakes have zero consequences. These mistakes are oh it I wanted to take this exit and it went straight so I'm just going to carefully touch </s><s>[INST] the wheel. Humans catch [/INST] the humans catch them and the human disengagement is labeling that reinforcement learning in a completely consequence free way. </s><s>[INST] So uh driver monitoring is the way you ensure they keep they keep paying attention. How is your messaging? Say I gave you a billion dollars? You would be scaling and now [/INST] oh if I could I couldn't scale with any amount of money was raised money. If I could if I had a way to scale you're not No, I'm not focused on, I don't know how to do like I guess I could sell it to more people but I want to make the system better, but I don't know him. </s><s>[INST] But what's the messaging here? Uh I got a chance to talk to you on and he he basically said that the human factor doesn't matter. Mhm. You know the human doesn't matter because the system will perform that there would be sort of uh sorry to use the term but like a singular like a point where it gets just much better. And so the human, it won't really matter. But it seems like that human catching the system when it gets into trouble is like the thing which will make something like reinforcement learning work. So how do you, how do you think messaging for Tesla for you should change for the industry in general should change. [/INST] I think my message is pretty clear at least like our messaging wasn't that clear in the beginning and I do kind of fault myself for that. We are proud right now to be a level two system. We are proud to be leveled to if we talk about level for it's not with the current hardware, it's not going to be just a magical OTA upgrade. It's going to be new hardware. It's going to be very carefully thought out right now. We are proud to be leveled to and we have a rigorous safety model. Um I mean not like like okay, rigorous, who knows what that means. But we at least have a safety model and we make it explicit is in safety dot MD and open pilot and it says seriously though safety dot MD. </s>

<s>[INST] So the task ultimately to figure out like really perfectly as as close as close as possible, the direction you should be digging. First of all that, it's possible they have a straight line through and then what that direction would be. And then you are trying to infer that by constructing a right triangle by doing, I'm not exactly sure about how to do that rigorously like by tracing the mountain by walking along the mountain. How to you said grids. [/INST] Yeah, you kind of walk as if you were in a grid. And so you you just walking right angles. So </s><s>[INST] but then you have to walk really precisely, then you should have to use tools to measure this and the terrain is probably very impressive. So this makes more sense than two D. And three D. Gets even weirder. So okay gotcha. [/INST] But so this method was described by like an ancient Egyptian historian I think hero of Alexandria. And um and then for about like yeah for about 2000 years that's that's how like that's how we thought that they had built this this tunnel. Um And then uh and then these researchers went there and and and found out that actually they must have had to to use other methods. And and then in this paper they describe these these other methods and of course they can't know for sure but there's uh they presented a bunch of plausible alternatives. The one that for me was the most plausible is that what they probably must have done is to use something that is similar to an iron sight on a rifle. The way you can line up your rifle with the target off in the distance by by having an iron sight. Um And uh and they must have done something similar to that effectively would treat with three sticks. And that way they were able to line up sticks uh along the side of the mountain that we're all on the same site. And so that then you could get to the other side and you could and then you could draw that line so this for me is the most plausible uh way that they might have done that And they but then they they described this in detail and other possible approaches in this paper. </s><s>[INST] So this is a mathematician doing this. [/INST] Yeah. This is a mathematician that they did this </s><s>[INST] um Which I suppose is the right mindset instead of skills required to solve an ancient problem. Right? [/INST] Yeah mathematicians and engineers and a lot of things </s><s>[INST] because they didn't have computers or drones or light are back then or whatever technology would use modern day for the civil engineering. [/INST] Another fascinating thing is that like, you know after effectively after the downfall of the roman civilization, people didn't build tunnels for about 1000 years. We go 1000 years without tunnels. And then like only and like in late middle ages that we start doing them again. But but here is the tunnel like sixth century Bc. Like incredibly limited mathematics and they and they built it in this way. Um And and and for and it was a mystery for for a long time exactly how they did it. And then these mathematicians went there and and uh basically with no archaeology kind of background were able to figure it out. </s><s>[INST] How do annotations for this paper look like? What is it? What's the successful annotation or paper like this? [/INST] Yes. So sometimes your for this paper um sometimes adding some more context on on a specific um part like sometimes they mentioned for instance um these instruments that were common in ancient Greece and ancient Rome for for building things. And uh and so in some of those annotations I described these instruments in more detail and how they worked because sometimes it can be hard to to visualize these. Um Then this paper um I forget exactly when, when this was published, I believe maybe maybe the 70s. Um but then there was further research into this tunnel and more interesting, other interesting aspects about it. I add those to that paper as well. There's historical context that I also go into uh there. Um for instance, the fact that as as I said that effectively after the downfall of the roman empire, no tunnels were built like that's something that I that I that I that I added to the paper as well. </s><s>[INST] Yeah. So so so when other people look at the paper, how did they usually consume the annotations? So they like is there commenting feature is uh I mean like this is a really enriching experience the way you read a paper, what what aspects do you do? People usually talk about that they they value from this. [/INST] So yeah, so anybody can just go on there and and uh either add a new annotation or other comment to an existing annotation. And so you can start kind of a threat within an existing annotation. Um and that's something that happens relative frequency. And then because I was the original author of the initial annotation, I get picked. And so oftentimes I'll go back and and and add onto to that threat. </s><s>[INST] How do you pick the paper? I mean first of all this whole process is really exciting. I'm gonna, especially after this conversation I'm gonna make sure I participate much more actively on papers that I know a lot about and on paper I know nothing about both [/INST] quantitative </s><s>[INST] paper. I would love to. I also I mean I I realized that there's a like it's an opportunity for people like me to publicly annotate a paper like [/INST] they are doing Emma </s>

<s>[INST] So there's something about, right, It's automation, but there's something about the there's a certain level of abstraction where you give control to Ai to do the automation, there's a scale that could be achieved. That it feels like the scale of bug and scale mistake and scale of destruction that could be achieved uh of the kind that humans cannot achieve. So ai is much more able to destroy an entire country accidentally versus humans. It feels like the more civilians die as a react or suffer as the consequences of your decisions, the more weight there is on the human mind to make that decision. And so like it becomes more and more unlikely to make that decision for humans. For a I it feels like it's harder to encode that kind of weight [/INST] in a way the Ai that we're currently building automating statistics, right? Intelligence is the ability to make models so you can act on them and there is a tool to make better models. So in principle, if you're using AI wisely, you're able to prevent more harm. And I think that the main issue is is not on the side of the Ai, it's on the side of the human command hierarchy that is using technology responsibly. </s><s>[INST] So the question is, how hard is it uh, to encode too proud to properly encode the right incentives into [/INST] the Ai. So for instance, there's this idea what happens if we let our airplanes being flown with A. I. Systems and the neural network is a black box and so on. And it turns out our neural networks are actually not black boxes anymore. There are function approximate is losing linear algebra. And uh, there are performing things that you can understand. But we can also, instead of letting the neural network fly the airplane used the neural network to generate approval. The correct program with a degree of accuracy of the proof that a human could not achieve. So we can use our AI by combining different technologies to build systems that are much more reliable than the systems that a human being would create? And so in this sense, I would say that if you use an early stage of technology to save labor and don't employ, employ competent people, but just to hack something together because you can that is very dangerous. And if people are acting under these incentives that they get away with delivering shoddy work more cheaply using ai less human oversight than before, That's very dangerous. </s><s>[INST] The thing is though Ai is still going to be unreliable, perhaps less than humans, but it will be unreliable in novel ways. And uh [/INST] yeah, but this is an empirical question and it's something that we can figure out in Berkeley. So the issue is do we trust these systems, the social systems that we have in place and the social systems that we can build and maintain that they are able to use ai responsibly if they can then ai is good news. If they cannot, Then it's going to make the existing problems 1st. </s><s>[INST] Well and also who creates the ai who controls it, Who makes money from it because it's ultimately humans. And then you start talking about how much you trust the humans. [/INST] So the question is, what does who mean? I don't think that we have identity per se. I think that the story of a human being is somewhat random. What happens is more or less that everybody is acting on their local incentives, what they perceive to be their incentives. And the question is, what are the incentives that the one that is pressing the button is operating under? </s><s>[INST] It's nice for those incentives to be transparent. So for example, I'll give you example, there seems to be a significant distrust of a tech like entrepreneurs in the tech space or or people that run, for example, social media companies like Mark Mark Zuckerberg, there is not a complete transparency of incentives under which that particular human being operates the trend. You know, we can listen to the words he says or what the marketing team says for a company, but we don't know. And that's that's becomes a problem when that the algorithms and systems created by him and other people in that company start having more and more impact on society and that it starts, you know, if if the incentives were somehow the definition and the explain ability of the incentives was decentralized such that nobody can manipulate it. No propaganda type manipulation of like how these systems actually operate could be done, then yes, it's not, I think I think a I could achieve much fairer, much more effective uh sort of uh like solutions to difficult ethical problems. But when there's like humans in the loop manipulating the dissemination the communication of how the system actually works that feels like you can run to a lot of trouble? And that's why there's currently a lot of distrust for for people at the heads of companies that have increasingly powerful ai systems. [/INST] I suspect what happened traditionally in the U. S. Was that since our decision making is much more central or decentralised than an authoritarian state, people are making decisions autonomously at many many levels in society. What happened that was we created coherence and cohesion in society by controlling what people saw it and what information they had right? The media is synchronized public opinion and social media have disrupted this. It's not I think so much Russian influence or something. It's everybody's influence. It's that a random person can come up with a conspiracy theory and disrupt what people think. And if that conspiracy theory is more compelling or more attractive than the standardized public conspiracy theory that we give people as a default, then it might get more traction right? You suddenly have the situation at a single individual somewhere on a farm in texas has more listeners than CNN </s>

<s>[INST] R. I. D. And now here's my conversation with Jeff [/INST] Hawkins? Yeah. Are you more </s><s>[INST] interested in understanding the human brain or in creating artificial systems that have many of the same qualities but don't necessarily require that you actually understand the underpinning workings of our mind. [/INST] So there's a clear answer to that question. My primary interest is understanding the human brain. No question about it. But um I also firmly believe that we will not be able to create fully intelligent machines until we understand how the human brain works. So I don't see those are separate problems. Um I think there's limits to what can be done with machine intelligence if you don't understand the principles by which the brain works. And so I actually believe that studying the brain is actually the, the fastest way to get the machine intelligence </s><s>[INST] and within that. Let me ask the impossible question. How do you not defined, but at least think about what it means to be intelligent. [/INST] So I didn't try to answer that question first, we said let's just talk about how the brain works and let's figure out how to turn parts of the brain, mostly the new york cortex, but some other parts too, the parts of the brain, most associated intelligence. And let's discover the principles by how they work because intelligence isn't just like some mechanism and it's not just some capabilities, it's like, okay, we don't even have no where to begin on this stuff. And so now that we've made a lot of progress on this, after we've made a lot of progress on how the new york critics works and we can talk about that. I now have a very good idea, what's going to be required to make intelligent machines? I can tell you today? You know, some of the things are going to be necessary, I believe, to create intelligent machines. </s><s>[INST] So we'll get there, we'll get to the Neocortex and some of the theories of how the whole thing works. And you're saying as we understand more and more uh about the Neocortex, about our human mind, we'll be able to start to more specifically define what it means to be intelligent. It's not useful to really talk about that until [/INST] I don't know if it's not useful. Look, there's a long history of ai as you know, and there's been different approaches taken to it and who knows, maybe they're all useful. All right, so uh you know, the good old fashioned ai the expert systems, the current convolutional neural networks, they all have their utility, they all have a value in the world. But I would think almost everyone agrees that none of them are really intelligent and a set of a deep way that humans are. And so, um it's just the question is, how do you get from where those systems were or are today to where a lot of people think we're going to go And there's a big, big gap, there's a huge gap and I think the quickest way of bridging that gap is to figure out how the brain does that, and then we can sit back and look and say, oh, what are these principles that the brain works on are necessary and which ones are not clear. We don't have to build this in, in intelligent machines aren't gonna be built out of uh, you know, organic living cells. Um, but there's a lot of stuff that goes on. The brain is going to be necessary. </s><s>[INST] So let me ask me be before we get into the fun details, let me ask maybe a depressing or a difficult question. Do you think it's possible that we will never be able to understand how our brain works that maybe there's aspects to the human mind, like we ourselves cannot introspectively get to the core that there's a wall you eventually [/INST] hit. I don't believe that's the case. I have never believe that's the case. There's not been a single thing we've ever humans have ever put their minds to it. We said, oh, we reached the wall, we can't go any further. Just people keep saying that people used to believe that about life, you know, alan vital, right? There's like, what's the difference in living matter and non living matter something special. You never understand. We no longer think that. So there's there's no historical evidence that the justices the case and I just never even considered that possibility. I would also say today. Uh, we understand so much about the neocortex. We've made tremendous progress in the last few years that I no longer think of it as uh an open question. Um The answers are very clear to me and the pieces we know we don't know are clear to me, but the framework is all there and it's like, oh okay, we're gonna be able to do this, this is not a problem anymore. Just takes time and effort, but there's no mystery, big mystery anymore. </s><s>[INST] So then let's get into it for for people like myself who are not very well versed in the human brain except my own. Uh can you describe to me at the highest level? What are the different parts of the human brain? And then zooming in on the new york cortex, the part of the neocortex. And so on. A quick overview [/INST] human brain, we can divide it roughly into two parts, there's the old parts, lots of pieces and then there's a new part, the new partisan your cortex. Um It's new because it didn't exist before mammals. The only mammals have a neocortex in humans and primates is very large In the human brain. The neocortex occupies about 70-75 of the volume of the brain. It's huge and the old parts of the brain are, there's lots of pieces there, there's a spinal cord and there's the brain stem and the cerebellum and the different parts of the basic gang and so on. In the old parts of the brain, you have the autonomic regulation, like breathing and heart rate. You have basic behaviors. So like walking and running are controlled by the old parts of the brain, all the emotional centers of the brain or in the old part of the brain's when you feel anger or hungry, lost with things like that. Those are all in the old parts of the brain. And uh and we associate with the neocortex all the things we think about sort of high level perception and cognitive functions, anything from seeing and hearing and touching things to language, to mathematics and engineering and science and so on. Those are all associated with the neocortex. And they're certainly correlated our abilities in those regards are correlated with the relative size of our neocortex compared to other mammals. So that's like a rough division. And you obviously can't understand the neocortex completely isolated but you can understand a lot of it with just a few interfaces so that all parts of the brain. And so it gives you a system to study. The other remarkable thing about the neocortex compared to the old parts of the brain as the new york cortex is extremely uniform. Uh It's not visually or anatomically or uh it's very, it's like a, I always like to say it's like the size of a dinner napkin about 2.5 millimeters thick and it looks remarkably the same everywhere everywhere. You look in that 2.5 millimeters is this detailed architecture. And it looks remarkably the same everywhere, and that's across species, the mouse versus a cat and a dog and a human where if you look at the old parts of the brain, there's lots of little pieces do specific things. So it's like the old parts of the brain involved, like this is the part that controls heart rate, and this is the part that controls this and this is this kind of thing, and that's this kind of thing. And these evolved for eons a long, long time and they have their specific functions and all of a sudden mammals come along and they got this thing called the neocortex and it got large by just replicating the same thing over and over and over again. This is like, wow, this is incredible. Um so all the evidence we have. Um and this is an idea that was first articulated uh in a very cogent and beautiful argument by a guy named Vernon Mall Castle in 1978, I think it was um that the neocortex all works on the same principle. So, language, hearing, touch, vision engineering, all these things are basically underlying, all built in the same computational substrate. They're really all the same problem </s><s>[INST] with low level, the building blocks all look similar. [/INST] Yeah, and they're not even that low level, we're not talking about, like, like neurons were talking about this very complex circuit that exists throughout the neocortex is remarkably similar. It's like, yes, you see variations of it here and they're more of the cell left and that's not all so on. But what Marcus argued was it says, you know, if you take a section of your cortex, Why is one a visual area and one is a auditory area or why? His answer was it's because one is connected to eyes and one is connected to ears </s><s>[INST] literally. You mean just its most closest in terms of the number of connections [/INST] to censor, literally. If you took the optic nerve and attached it to a different part of the cortex, that part would become a visual region. This actually this experiment was actually done by Margot, Lancaster boy. And uh in in developing I think it was the murders, I can't remember, it was some animal and there's a lot of evidence to this. You know, if you take a blind person, a person is born blind at birth, they are born with a visual neocortex. Um it doesn't may not get any input from the eyes because there was some congenital defect or something. And that region becomes does something else, it picks up another task. So uh and it's it's so it's just it's just very complex thing, it's not like, oh they're all built on neurons. No, they're all built in this very complex circuit. And uh and somehow that circuit underlies everything. So this is uh it's called the common cortical algorithm if you will uh some scientists just find it hard to believe and they just can't believe that's true, but the evidence is overwhelming in this case. And so a large part of what it means to figure out how the brain creates intelligence and what is intelligence in the brain is to understand what that circuit does. If you can figure out what that circuit does um as amazing as it is, then you can then you then you understand what all these other cognitive functions are. </s><s>[INST] So if you were to sort of put neocortex outside of your book on intelligence, you look, if you wrote a giant toma textbook on the Neocortex and you look uh maybe a couple of centuries from now, how much of what we know now will still be accurate two centuries from now. So how close are we in terms of [/INST] understanding? I have to speak from my own particular experience here. So I run a small research lab here. It's like it's like any other research lab in the sort of the principal investigator, there's actually two of us and there's a bunch of other people and this is what we do. We started the Neocortex and we published our results and so on. So about three years ago we had a real breakthrough in this in this field tremendous spectrum. We started, we now publish, I think three papers on it. Um and so I have I have a pretty good understanding of all the pieces and what we're missing. I would say that almost all the empirical data we've collected about the brain, which is enormous. If you don't know the neuroscience literature, it's just incredibly bic and uh it's for the most part all correct, it's facts and and experimental results and measurements and all kinds of stuff, but none of that has been really assimilated into a theoretical framework. It's, it's data without it in the language of thomas Kuhn, the historian would be a sort of a pre paradigm science, lots of data, but no way to fit in together. I think almost all of that's correct. There's gonna be some mistakes in there. Um and for the most part, there aren't really good coaching theories about how to put it together. It's not like we have two or three competing good theories which ones are right which ones are wrong. It's like people just like scratching their heads. You know, some people have given up on trying to like figure out what the whole thing does. In fact, there's very, very few labs that we that we do that focus really on theory and all this unassimilated data and trying to explain it. So it's not like we haven't we've got it wrong. It's just that we haven't got it at </s><s>[INST] all. So it's really, I would say pretty early days in terms of understanding the fundamental theories forces of the way your mind works. I [/INST] don't think so that I would have said that's true five years ago. So as I said we had some really big breakfast on this recently and we started publishing papers on this. So um uh you could get that but so I don't think it's I'm an optimist and from where I sit today most people would disagree with this, but from where I sit today, from what I know uh it's not super early days anymore. We are. It's you know the way these things go is it's not a linear path, right? You don't just start accumulating and get better and better and better. You know you got all the stuff you've collected. None of it makes sense. All these different things we just started around and then you're gonna have some breaking points all of sudden. Oh my God. No we got it. Right. So that's how it goes in science. And I personally feel like we passed that little thing about a couple years ago, all that big thing a couple years ago. So we can talk about that time will tell if I'm right but I feel very confident about it. That's what I want to say it on tape like this. Uh </s><s>[INST] at least very optimistic. So let's before those few years ago let's take a step back to H. T. M. The hierarchical temporal memory theory which you first proposed on intelligence that went through a few different generations. Can you describe what it is, how it evolved through the three generations since you first put it on paper? [/INST] Yeah. So one of the things that neuroscientists just sort of missed for many, many years and especially people were thinking about theory was the nature of time in the brain. Mhm. Brains process information through time. The information coming into the brain is constantly changing the patterns from my speech right now if you're listening to it at normal speed would be changing on yours about every 10 milliseconds or so you'd have a change this constant flow when you look at the world, your eyes are moving constantly 3 to 5 times a second and the inputs completely completely if I were to touch something like a coffee cup as I move my fingers that changes. So this idea that the brain works on time changing patterns is almost completely or was almost completely missing from a lot of the basic theories like fears of vision and so it's like, oh no we're gonna put this image in front of you and flash it and say, what is it? A convolutional neural networks work that way today. Right. You know, classify this picture but that's not what vision is like vision is this sort of crazy time based pattern that's going all over the place. And so is touch and so is hearing. So the first part of higher called temporal memory was the temple part. It's to say you won't understand the brain normally understand intelligent machines unless you're dealing with time based patterns. The second thing was the memory component of it was is to say that um we aren't just processing input, we learn a model of the world and the memory stands for that model. We have to the point of the brain part of the Neocortex, it learns a model of the world. We have to store things that our experiences in a form that leads to a model of the world so we can move around the world, we can pick things up and do things and navigate and know how it's going on. So that's that's what the memory referred to. And many people just they were thinking about like certain processes without memory at all, they're just like processing things. And then finally the hierarchal component was a reflection to uh that the neocortex, although it's just uniform sheet of cells, uh different parts of it projected other parts which project to other parts and there is a sort of a rough hierarchy in terms of them. So the higher the temple memory is just saying look we should be thinking about the brain as time based, you know, model memory based and hierarchical processing. Um and and that was a placeholder for a bunch of components that we would then plug into that we still believe all those things I just said but we now know so much more that I'm stopping the use the word miracle Temple memory because it's it's insufficient to capture the stuff we know. So again, it's not incorrect but it's I now know more and I would rather describe it more accurately. </s><s>[INST] So you're basically we can think of html as emphasizing that there's three aspects of intelligence that important to think about whatever the whatever the eventual theory convergence. So in terms of time, how do you think of the nature of time across different time scales? You mentioned [/INST] things </s><s>[INST] Changing a sensory inputs changing every 10 between what about it? Every few minutes? Every few months and years. [/INST] If you think about a neuroscience problem, the brain problem, neurons themselves can stay active for certain periods of time. They parts of the brain with this doctor for minutes, you know, So you could hold up a certain perception activity um uh for a certain period of time but not most of them don't last that long. Um and so if you think about your thoughts are the activity of neurons. If you're going to want to involve something that happened a long time ago, I mean even just this morning for example, um the neurons haven't been active throughout that time. So you have to store that. So I ask you, what do you have for breakfast today? That is memory. That is you built into your model of the world that you remember that and that memory is in the, in the synapses is basically in the formation of synapses and so um uh it's your sliding into what you know is the different timescales. There's time scales of which we are like understanding my language and moving about and seeing things rapidly over time. That's the time scales of activities of neurons. But if you want to get longer time scales then it's more memory and we have to invoke those memories to say oh yes well now I can remember what I had for breakfast because I stored that someplace I may forget it tomorrow but it's stored for now. </s><s>[INST] So this memory also need to have so the hierarchical aspect of reality is not just about concepts, it's also about time. Do you think of it that way? [/INST] Uh Yeah time is infused in everything. It's like you really can't separate it out. Um If I ask you what is the uh what is your, you know how does the brain learn a model of this coffee cup here? I have a coffee cup and Metro coughing up. I said well time is not an inherent property of this uh this of the model I have of this cup whether it's a visual model or attack the model. Um I can sense it through time but the model itself doesn't really have much time. If I asked you if I said well what is the model of my cell phone? My brain has learned a model of the cell phones. If you have a smartphone like this and I said, well this has time aspects to it, I have expectations when I turn it on, what's going to happen? What what or how long it's gonna take to do certain things. Bring up an app what sequences. So I have an instant, it's like melodies in the world. You know, melody has a sense of time, so many things in the world move and act and there's a sense of time related to them. Uh some don't um but most things do actually. Um so it's sort of infused throughout the models of the world. You build a model of the world, You're learning the structure of the objects in the world and you're also learning how those things change through time. </s><s>[INST] Okay, so it's, it really is just the fourth dimension that's infused deeply and you have to make sure that your models of intelligence uh incorporated. So like you mentioned, the state of neuroscience is deeply empirical. A lot of data collection. It's uh you know, that's that's where it is. He's imagined thomas Kuhn right? And then you're proposing a theory of intelligence and which is really the next step the really important stuff to take. But why why is HTM or what we'll talk about soon? Uh the right theory? So is it more this is it backed by intuition isn't backed by evidence as it backed by a mixture of both. Is it kind of closer to where string theories in physics, where there's uh mathematical components which show that, you know what it seems that this it fits together too well for not to be true. Which is where string theory is. Is that [/INST] where a mix of all those things, although definitely where we are right now, it's definitely much more on the empirical side than, let's say, string theory. The way this goes about were theorists, Right? So we look at all this data and we're trying to come up with some sort of model that explains it basically. And there's uh unlike string theory, that there's this vast more amounts of empirical data here that I think than most. Uh this is just deal with. And so um our challenges to sort through that and figure out what kind of uh constructs would explain this. And when we have an idea, you come up with the theory of some sort, you have lots of ways of testing it. First of all I am, you know, there are 100 years of assimilated, unassimilated empirical data from neuroscience. So we go back and re papers and he said, well, did someone find this already, we can predict X, Y and Z. And maybe no one's even talked about it since 1972 or something. But we go back and find that we say, oh either it can support the theory or it can invalidate the theory. And we said okay, we have to start over again, oh no, it's supported. Let's keep going with that one. Um so the way I kind of view it, when we do our work, we come up we we look at all this empirical data and it's it's what I call it, is a set of constraints. Were not interested in something that's biologically inspired. We're trying to figure out how the actual brain works. So every piece of empirical data is a constraint on a theory. In theory. If you have the correct theory, it needs to explain everything. Right? So, we have this huge number of constraints on the problem which initially makes it very, very difficult. If you don't have any constraints, you can make up stuff all the day. You can say, oh, here's an answer to how you can do this, you can do that, you can do this. But if you consider all biology as a set of constraints, all Neurosciences set of constraints. And even if you're working in one little part of the neocortex for example, there are hundreds and hundreds of constraints. These are empirical constraints. That it's very, very difficult initially to come up with a theoretical framework for that. But when you do and it solves all those constraints at once, you have a high confidence that you've got something close to correct. Its just mathematically almost impossible not to be. So that's the the curse and the advantage of what we have, the curse is we have to solve, we have to meet all these constraints, which is really hard, but when you do meet them, uh then you have a great confidence that you've discovered something. In addition then we work with scientific labs. So we'll say, oh there's something we can't find, we can predict something, but we can't find it anywhere in the literature. So we will, then we have people we collaborated with, we'll say sometimes they'll say, you know what, I have some collected data which I didn't publish but we can go back and look at it and see if we can find that, which is much easier than designing a new experiment, you know, neuroscience experiments take a long time years. So although some people are doing that now too. So uh but between all of these things, uh I think it's a reasonable um actually a very, very good approach. We were blessed with the fact that we can test our theories out the yin yang here because there's so much on a similar data and we can also falsify our theories very easily, which we do often </s><s>[INST] just kind of reminiscent to whenever, whenever that was with Copernicus. Uh you know, when you figure out that the sun is at the center of the solar system as opposed to Earth. The pieces just fall into place. And I think [/INST] that's the general um nature of aha moments uh is it's Copernicus, it could be, you could say the same thing about Darwin. um you could say the same thing about, you know, about the double helix. Uh that that people have been working on a problem for so long and have all this data, they can't make sense of it, they can't make sense of it, but when the answer comes to you and everything falls into place, it's like, oh my gosh, that's it. Um that's got to be right. I asked both Jim Watson and Francis crick about this. Um I asked him, you know, when you were working on trying to discover the structure of the double helix. Um and when you came up with the the sort of uh the structure that ended up being correct. Um but it was sort of a guess, you know, it wasn't really verified. Yeah, I said did you know that? It was right? And they both said absolutely, we absolutely knew was right. And uh it doesn't matter if other people didn't believe it or not, we knew it was right. They get around to thinking, I agree with it eventually. Anyway. Um and that's the kind of thing, you hear a lot with scientists who who really are studying a difficult problem and I feel that way too, about our work, </s><s>[INST] Have you talked to Crick and Watson about the problem, you're trying to solve the, of finding the DNA of the brain. [/INST] In fact Francis Crick was very interested in this uh in the latter part of his life. And in fact I got interested in brains by reading an essay he wrote in 1979 called Thinking about the brain. And that was when I decided I'm gonna leave my profession of computers and engineering and become a neuroscientist. Just reading that one essay from Frances craig. I got to meet him later in life. Um I got I spoke at the Salk Institute and he was in the audience and then I had tea with him afterwards. Um uh you know, he was interested in different problems. He was he was focused on consciousness </s><s>[INST] uh problem. Well, [/INST] I think it's the red herring and so we weren't really overlapping a lot there. Um Jim Watson who is still alive um is is also interested in this problem. And he was when he was director of the charleston Harbor Laboratories, um he was really sort of behind moving in the direction of neuroscience there and so he had a personal interest in this field. Um and I have met with numerous times. Um and in fact the last time was a little bit over a year ago, I gave a talk called the Harbor Labs about the progress we're making in in our work and um it was a lot of fun because um he said, well you you wouldn't be coming here unless you had something important to say. So I'm gonna go tend to talk. So you start in the very front row next the most next time was the director of the lab Bruce Stillman? So these guys are in the front row of this auditorium. Right? So nobody else in the auditorium wants to sit in the front row because it's Jim Watson is the director and uh and I gave a talk and I had dinner with them afterwards. Um but there's a great picture of my colleagues super time on took where I'm up there sort of like screaming the basics of this new framework we have. And Jim Watson is on the edge of his chair, he's literally on the edge of his chair, like intently staring up at the screen. And when he discovered the structure of DNA, the first public talk he gave was that Cold Spring Harbor Labs. So, and there's a picture of the famous picture of Jim Watson standing at the whiteboard with overhead thing pointing at something with holding a double, He looks at this point and it actually looks a lot like the picture of me. So there was sort of funny there there I am talking about the brain and there's Jim Watson staring intently at and of course there was, You know, whatever 60 years earlier, he was standing, you know, pointing out the double helix and </s><s>[INST] it's one of the great discoveries in all of you know, whatever by all the science, all signs of DNA. So that's the funny that there's echoes of that in your presentation, Do you think in terms of evolutionary timeline in history, the development of the neocortex was a big leap? Or is it just a small step? So like if we ran the whole thing over again from the from the birth of of life on earth, how likely redevelop the mechanism of [/INST] the new york? Okay, well those are two separate questions. Uh one is was it a big leap and one was how like it is? Okay, they're not necessarily related. May be correlated, but of course, I mean we don't really have enough data to make a judgment about that. Um I would say definitely was a big league league. And I can tell you why, I think I don't think it was just another incremental step. I'll get that moment. Um I don't really have any idea how likely it is. If we look at evolution, we have one data point which is earth right? Life formed on earth billions of years ago, whether it was introduced here or created here where someone introduced it, we don't really know. But it was here early. It took a long, long time to get to multicellular life. And then from multi tell us about your life. It took a long, long time to get the neocortex and we've only had the new york techniques for a few 100,000 years. So that's like nothing. Okay, so is it likely will certainly isn't something that happened right away on earth uh and there are multiple steps to get there. So I would say it's probably not something that happens instantaneous on other planets that might have life. Uh It might take several billion years on average. Is it likely, I don't know, but you'd have to survive for several billion years to find out? Probably. Um Is it a big leap? Yeah, I think it's um uh it is a qualitative difference than all other evolutionary steps. I can try to describe that if </s><s>[INST] you're like, sure. In which In which way, [/INST] yeah, I can tell you how Pretty much, Yeah, let's start a little preface many of the things that humans are able to do do not have obvious um survival advantages, precedent. You know, we create music. Is that is there a really survival advantage to that? Maybe? Maybe not. What about mathematics? Is there a real survival advantage to mathematically? You can stretch it, you can try to figure these things out right. Um but but mostly evolutionary history, everything had immediate survival advantages too. Right. So, I'll tell you a story, which I like may not be true. Um but the story goes as follows, um, organisms have been evolving for since the beginning of life here on Earth, um, adding this sort of complexity onto that. And this sort of complexity. That and the brain itself is evolved this way. In fact there's an old parts and older parts and older, older parts of the brain that kind of just keeps coming on new things and we keep adding capabilities and we got to the Neocortex initially, it had a very clear survival advantage and that it produced better vision and better hearing and touch and maybe and so on. But what I think happens is that evolution discover it took, it took a mechanism um, and this is in our recent theories, but it took a mechanism evolved a long time ago for navigating in the world for knowing where you are, these are the so called grid cells and place cells of an old part of the brain. And it took that mechanism for building maps of the world uh and knowing where you are in those maps and how to navigate those maps and turns it into a sort of slimmed down idealized version of it. And that idea of this version could now apply to building maps of other things, maps of coffee cups, maps of phones, maps of, you know, concepts, yes, and not just almost exactly. And so you and it just started replicating this stuff right? You just take more and more and more of it. So we went from being sort of dedicated purpose neural hardware to solve certain problems that are important to survival to a general purpose neural hardware that could be applied to all problems. And now it's, it's escaped the orbit of survival. It's, we are now able to apply it to things which we find enjoyment? Um You know, but aren't really clearly um survival characteristics uh and that it seems to only have happened in humans to to the large extent. Um And so that's what's going on, where we sort of have we've sort of escape the gravity of evolutionary pressure in some sense in the neocortex. And it now does things which not that are really interesting discovering models of the universe which may not really help us. Doesn't matter how does it help us surviving? Knowing that there might be multiverses or not, there might be you know, the age of the universe or how do you know various stellar things occur. It doesn't really help us survive at all, but we enjoy it and that's what happened. Or </s><s>[INST] at least not in the obvious way. Perhaps it is required if you look at the entire universe in an evolutionary way it's required for us to do interplanetary travel and therefore survive past our own fun. But you know, let's not get too. [/INST] But you know, evolution works at one time frame. It's survival. If you think of survival of the genotype, survival of the individual, it's what you're talking about there is spans well beyond that. So there's no genetic, I'm not transferring any genetic traits to my Children that are going to help them survive better on mars. Right, </s><s>[INST] totally different mechanism. So let's get into the new as you've mentioned this idea the I don't know if you have a nice name. 1000 [/INST] and call it 1000 brain theory of </s><s>[INST] intelligent like it. So can you talk about the the this idea of uh spatial view of concepts and so on? So [/INST] can I just describe sort of the there's an underlying core discovery which then everything comes from that. It's a very simple, this is really what happened. We were deep into problems about understanding how we build models of stuff in the world and how we make predictions about things. And I was holding a coffee cup just like this in my hand and I had my finger was touching the side, my index finger and then I moved it to the top and I was going to feel the rim at the top of the cup. And I asked myself very simple question. I said well first of all I just say I know that my brain predicts what is going to feel before it touches it, you can just think about it and imagine it. Um And so we know that the brain is making predictions all the time. So the question is what does it take to predict that? Right. And there's a very interesting answer that. First of all it says the brain has to know it's touching a coffee cup has to have a model or a coffee cup and needs to know where the finger currently is on the cup relative to the cup because when I make a movement and used to know where it's going to be on the cup after the movement is completed relative to the cup, and then it can make a prediction about what it's gonna sense. So this told me that the neocortex which is making this prediction, needs to know that it's sensing it's touching a cup and it needs to know the location of my finger relatives that cup in a reference frame of the cup. It doesn't matter where the cup is relative my body, it doesn't matter, it's orientation, none of that matters. It's where my finger is relative to the cup which tells me then that the neocortex is has a reference frame that's anchored to the cup because otherwise I wouldn't be able to say the location and I wouldn't be able to predict my new location. And then we quickly very instantly, instantly you can say, well, every part of my skin could touch this cup and therefore every part of my skin's making predictions. And every part of my skin must have a reference frame um that it's using to make predictions. So the big idea is that throughout the neocortex there are everything is being, is being um stored and referenced in reference. Famous, you can think of them like X, Y. Z referencing, but they're not like that. Uh We know a lot about the neural mechanisms for this, but the brain thinks in reference frames and as an engineer if you're an engineer, this is not surprising you say if I wanted to build a cad model of the coffee cup while I would bring it up in some CAd software and I would assign some reference frame and say this features at this locations and so on. But the fact that this idea that this is occurring throughout the neocortex everywhere, it was a novel idea and um and then a zillion things fell into place after that. So now we think about the neocortex is processing information quite differently than we used to do it. We used to think about the neocortex is processing sensory data and extracting features from that sensory data and then extracting features from the features very much like a deep learning network does today. But that's not how the brain works at all. The brain works by assigning everything every input everything to reference frames and there are thousands, hundreds of thousands of them active at once in your neocortex. Um it's a surprising thing to think about but once you sort of internalize this, you understand that it explains almost every all the almost all the mysteries we've had about this about this structure. So um one of the consequences of that is that every small part of the neocortex. So I am a millimeter square and there's 150,000 of those. So it's about 100,000 m mm if you take every little square millimeter of cortex, it's got some input coming into it and it's gonna have reference frames which assigned that input to and eat square millimeter can learn complete models of objects. So what do I mean by that? If I'm touching the coffee cup, well if I just touch it in one place, I can't learn what this coffee cup is because I'm just feeling one part. But if I move it around the cup and touch with different areas, I can build up a complete model the cup because I'm now filling in that three dimensional map, which is the coffee cup, I can say, what am I feeling at all these different locations, that's the basic idea. It's more complicated than that. Um but so through time and we talked about time earlier through time, even a single column which is only looking at or a single part of the cortex is only looking at a small part of the world can build up a complete model of an object. And so if you think about the part of the brain which is getting input from all my fingers, so they're they're spread across the top of head in here. This is the somatosensory cortex um there's columns associated all the different areas of my skin and what we believe is happening is that all of them are building models of this cup, every one of them or things not, they're not all buildings, all, not every column and every part of the cortex builds models of everything. But they're all building models or something. And so you have it. So when I when I touched this cup with my hand there are multiple models of the cup being invoked. If I look at it with my eyes there again many models of the cup being involved because it's part of the visual system and the brain doesn't process an image. That's that's a misleading idea. It's just like your fingers touching the cups of different parts of my riding or looking at different parts of the cup. And thousands and thousands of models of the cup are being invoked at once and they're all voting with each other trying to figure out what's going on. So that's why we call it 1000 brains theory of intelligence because there isn't one model of the cup. There are thousands of models of this cup. There are thousands of models of your cell phone and about cameras and microphones and so on. Um it's a distributed modeling system which is very different than what people have thought about it. </s><s>[INST] So that's a really compelling and interesting idea to have two. First question. So one on the ensemble part of everything coming together, you have these 1000 brains, how how do you know which one has done the best job of forming [/INST] the great question. Let me explain. There's a problem that's known in neuroscience called the sense of fusion problem. And so the idea is there something like the image comes from the eye, there's a picture on the retina and that gets projected to the neocortex. Oh, by now it's all spread out all over the place and it's kind of squirrely and distorted and pieces are all over the, you know, it doesn't look like a picture anymore. When does it all come back together again? Right. Or you might say well yes, but I also I also have sounds or touch is associated with a couple. So I'm seeing the cup and touching the cup. How do they get combined together again? So this is called the sensor fusion problem is if all these disparate parts have to be brought together into one model. Someplace that's the wrong idea. The right idea is that you got all these guys voting. There's auditory models of the cup, There's visual models, the cup, those tactile models of the cup. Um, there are one in division system, there might be ones that are more focused on black and white and unfortunately color, it doesn't really matter. There's just thousands and thousands of models of this cup and they vote, they don't actually come together in one spot. Just literally think of it this way. Imagine you have these columns are about the size of a little piece of spaghetti Okay, like a 2.5 millimeters tall and about a millimeter in mind they're not physical like but you can think of them that way and each one is trying to guess what this thing is we're touching now. They can they can do a pretty good job if they're allowed to move over touch so I can reach my hand into a black box and move my finger around an object. And if I touch enough pace is like okay I don't know what it is but often we don't do that often. I could just reach and grab something with my hands all at once and I get it. Or if I had to look through the world through a straw so I'm invoking one little column. I can only see a part of something. I have to move the straw around. But if I open my eyes to see the whole thing at once so what we think is going on. It's all these little pieces of spaghetti if you have all these little columns in the cortex or all trying to guess what it is that they're sensing um they'll do a better guest if they have time and can move over time. So if I move my eyes with my fingers. But if they don't they have a they have a poor guest it's a it's a probabilistic s of what they might be touching now imagine they can post their probability at the top of little piece of spaghetti. Each one of them says I think and it's not really a probability distribution. It's more like a set of possibilities in the brain. It doesn't work as a probability distribution works is more like what we call a union you could say. Uh and one common sense, I think it could be a coffee cup, soda can or water bottle. Another calm says, I think it could be a coffee cup or you know telephone or camera or whatever, right? Um and all these guys are saying what they think it might be and there's these long range connections in certain layers in the cortex. So there's some layers in some cell types in each column sending projections across the brain. And that's the voting occurs. And so there's a simple associative memory mechanism. We've we've described this in a recent paper and we've modeled this um that says they can all quickly settle on the only or the one best answer for all of them if there is a single best answer, they all vote and said yeah, it's gotta be the coffee cup. And at that point they all know it's a coffee cup and at that point everyone acts as if it's a coffee cup, then we know it's a coffee, even though I've only seen one little piece of this world, I know it's coffee cup I'm touching or I'm seeing whatever. And so you can think of all these columns are looking at different parts in different places, different sensory input, different locations. They're all different, but this layer that's doing the voting, um that's it solidifies, it's just like it crystallizes and says, oh, we all know what we're doing and so you don't bring these models together in one model, you just vote and there's a crystallization of the vote. </s><s>[INST] Great, that's uh at least a compelling way to think about about the way you form a model of the world. Now, you talk about a coffee cup, do you see this as far as I understand, you're proposing this as well? That this extends to much more than coffee cups? It [/INST] does, </s><s>[INST] or at least the physical world, it expands to the world of concepts. [/INST] It does. And well, the first, the primary face every evidence for that is that the regions of the Neocortex that are associated with language or high level thought or mathematics or things like that, they look like the regions of the Neocortex, that process, vision, hearing and touch, they don't look any different or they look only marginally different. Um and so one would say, well if vernon Mount Castle who proposed that all the, all the parts of the country is doing the same thing, If he's right then the parts are doing language or mathematics or physics are working on the same principle, they must be working on the principle of reference frames, so that's a little odd thought. Um hmm, but of course we had no we had no prior idea how these things happen, so let's let's go with that. Um and uh we, in our recent paper we talked a little bit about that, I've been working on it more since I have better ideas about it now, um I'm sitting here very confident that that's what's happening and I can give you some examples to help you think about that. Um it's not, we understand it completely, but I understand better than I've described it in any paper so far. So, but we did put that idea out there says okay this is it's a good place to start, you know, and the evidence would suggest it's how it's happening and then we can start tackling that problem one piece at a time. Like what does it mean to do? High level thought, what do you mean to do? Language, how would that fit into a reference frame </s><s>[INST] framework? Yeah, so there's uh I don't know if you could tell me if there's a connection, but there's an app called Yankee that helps you remember different concepts and they talk about like a memory palace that helps you remember completely random concepts by trying to put them in a physical space in your mind and putting them next to each other method of lo que lo que for some reason that seems to work really well. Uh now that's a very narrow kind of application of just remembering some facts, [/INST] but that's not that's a very, very telling one. </s><s>[INST] Yes, exactly, so it seems like you're describing the mechanism why this [/INST] seems to work. So so basically the way what we think is going on is all things, you know all concepts, all ideas, words, everything you know um are stored in reference frames. And and so uh if you want to remember something, you have to basically navigate through a reference frame the same way a rat navigates to a made, in the same way my finger right navigates to this coffee cup, you're moving through some space. And so if you have a random list of things you were asked to remember by assigning them to a reference frame, you already know very well to see your house right? The idea of the method located, you can say okay my lobby, I'm gonna put this thing and then and then the bedroom, I put this one, I go down the hall, I put this thing and then you want to recall those facts or recall those things. You just walk mentally, you walk through your house, you're mentally moving through a reference frame that you already had and that tells you there's two things are really important about. It tells us the brain prefers to store things in reference frames. And that the method of recalling things or thinking if you will is to move mentally through those reference frames. You could move physically through some reference frames. Like I could physically move through the reference frame of this coffee cup. I can also mentally move to the reference of the coffee cup, imagining me touching it. But I can also mentally move my house and so now we can ask yourself or are all concept store this way. There was some recent research um using human subjects an FmRI and I'm gonna apologize for not knowing the name of the scientist who did this. Um but um what they did is they put humans in this FmRI machine, which one of these imaging machines and they they gave the humans tasks to think about birds. So they had different types of birds and it looked big and small and long necks and long legs, things like that. And what they could tell from the FmRI. It was a very clever experiment. Get to tell when humans were thinking about the birds, that the birds, the knowledge of birds was arranged in a reference frame similar to the ones that are used when you navigate in the room. That these are called grid cells and there are grid cell like patterns of activity in the new york cortex when they do this. So that it's a very clever experiment, you know? And what it basically says that even when you're thinking about something abstract and you're not really thinking about is a reference frame, it tells us the brain is actually using a reference frame and it's using the same neural mechanisms. These grid cells are the basic same neural mechanism that we we proposed that grid cells which exist in the in the old part of the brain, The antibiotic cortex. That that mechanism is now similar mechanisms used throughout the neocortex. It's the same nature, preserve this interesting way of creating reference frames. And so now they have empirical evidence that when you think about concepts like birds, that you're using reference frames that are built on grid cells. So that's that's similar to the method of low key but in this case the birds are related. So it makes they create their own reference frame which is consistent with bird space. And when you think about something, you go through that you can make the same example. Let's take a math mathematics. All right, let's say you want to prove a conjecture. Okay, what is a conjecture conjecture is a statement you believe to be true, but you haven't proven it. And so it might be an equation. I I want to show that this is equal to that. And you have you have some places you start with you said, well, I know this is true and I know this is true. And I think that maybe to get to the final proof, I need to go through some intermediate results. But I believe it's happening is literally these equations or these points are assigned to a reference frame, a mathematical reference frame. And when you do mathematical operations, a simple one might be multiply or divide, but you might be able to process, transform or something else. That is like a movement in the reference frame of the math. And so you're literally trying to discover a path from one location to another location in a space of mathematics. And if you can get to these intermediate results then you know, your map is pretty good and you know, you're using the right operations. Much of what we think about is solving hard problems. Is designing the correct reference frame for that problem. Figure out how to organize the information and what behaviors I want to use in that space to get me there. </s><s>[INST] Yeah. So if you dig in on an idea of this reference frame, whether it's the math, you start a set of axioms to try to get to proving the conjecture. Uh Can you try to describe? Maybe take a step back how you think of the reference frame in that context? Is is it the reference frame that the axioms are happy in? Is it the reference frame that might contain everything? Is that a changing thing? So [/INST] you have many many reference frames? In fact the way the theory the 1000 Brain theory of intelligence says that every single thing in the world has its own reference frames. So, um every word has its own reference names. And we can talk about this. The mathematics work out. This is no problem for neurons to do </s><s>[INST] this, but how many references does the coffee cup have? It's on the table, [/INST] let's say you ask how many reference fame could call them in my finger. That's touching the coffee cup. Half because there are many, many copies. There are many, many models of coffee cups. So the coffee, there is no model, the coffee cup, there are many miles of a coffee cup. And you can say, well, how many different things can my finger learn is the question you wanna ask? Imagine I say every concept, every idea, everything you've ever know about that you can say, I know that thing has a reference frame associated with him and what we do when we build composite objects. We can we assign reference frames to point another reference frames. So my coffee cup has multiple components to it. It's got a limb, it's got a cylinder, it's got to handle. Um and those things that have their own reference frames and they're assigned to a master reference frame which is called this cup. And now I have this fundamental logo on it. Well that's something that exists elsewhere in the world. It's its own thing. So has his own reference time. So we have to say how can I sign the the momentum bogo reference frame onto the cylinder or onto the coffee cup. So it's all we talked about this in the paper that um came out in december of last year, the idea of how you can sign referencing to referencing how neurons could do this. </s><s>[INST] So Well my question is even though you mentioned reference friends a lot, I almost feel it's really useful to dig into how youth think of what a reference frame is. I mean it was already helpful for me to understand that you think of reference frames is something there is a lot of. [/INST] Okay so let's just say that we're going to have some neurons in the brain. Not many actually 10,000 20,000 are going to create a whole bunch of reference frames. What does it mean? What does a reference from this guy? First of all these reference names are different than the ones you might be used to that. We know lots of references for example we know the Cartesian coordinates X. Y. Z. That's a type of reference frame. We know um longitude and latitude, that's a different type of reference frame. Uh if I look at a printed map it might have columns a through M. and rose, you know, one through 20, that's a different type of reference frame. It's kind of a Cartesian corn reference frame. Um The interesting about the reference frames in the brain and we know this because these have been established through neuroscience studying the anti ironic cortex. So I'm not speculating here. Okay, this is known neuroscience in an old part of the brain. The way these cells create reference frames, they have no origin. So what it's more like you have you have a point a point in some space and you give it a particular movement? You can then tell what the next point should be. Um And you can then tell what the next point would be and so on. You can use this to uh to calculate how to get from one point to another. So how do I get from my house to my home or how do I get my finger from the side of my cup to the top of the cup? How do I get from the axioms to the to the conjecture. Yeah. So it's a different type of reference fame and I can if you want I can describe in more detail, I can paint a picture of how you might want to think about that. It's </s><s>[INST] really helpful to think it's something you can move through. Uh But is there is it uh is it helpful to think of it as spatial in some sense or is there something, you know, it's definitely [/INST] special. Um It's special in the mathematical sense. How </s><s>[INST] many dimensions can it be? Crazy number [/INST] of dimension. That's an interesting question. In the old part of the brain, The anterior cortex, they studied rats and initially it looks like, oh this is just two dimensional, it's like the rat is in some box and a maze or whatever and they know where the rat is using these two dimensional reference frames and know where it isn't that amazing? We said, okay well what about what about bats? That's a mammal and they fly in three dimensional space, How do they do that? They seem to know where they are. Right. So there's this is a current area of active research and it seems like somehow the neurons in the entire on a cortex can learn three dimensional space. We just uh two members of our team along with the Lafayette from M. I. T. Just released a paper this literally last week. It's on by archive where they show that you can if you the way these things work and I won't get unless you want to I won't get into the detail. But um grid cells can represent any n dimensional space. It's not inherently limited. You can think of it this way if you had two dimensional. The way it works is you have a bunch of two dimensional slices, that's the way these things work. There's a whole bunch of two dimensional models and you can just you can slice up any n dimensional space and with two dimensional projections. So and you could have one dimensional models. So there's there's nothing inherent about the mathematics about the way the neurons do this which which constrain the dimensionality of the space uh which I think was important. So obviously I have a three dimensional map of this cup. Maybe it's even more than that, I don't know. Um But clearly three dimensional map of the cup. I don't just have a projection of the cup. Um but when I think about birds or when I think about mathematics, perhaps it's more than three dimensions, who knows? </s><s>[INST] So in terms of each individual column, building up more and more information over time, do you think that mechanism is well understood in your mind? You've proposed a lot of architecture? Is there is that a key piece or is it um is the big piece? The 1000 brain theory of intelligence? The ensemble of it all? [/INST] Well, I think they're both big. I mean, clearly the concept as a theorist. The concept is most exciting, right? We want a little concept. High level concept. This is a totally new way of thinking about how the new york politics work. So that is appealing. It has all these ramifications and with that as a framework for how the brain works. You can make all kinds of predictions and solve all kinds of problems. Now, we're trying to work through many of these details right now. Okay. How do the neurons actually do this? Well, it turns out if you think about grid cells and place cells in the old parts of the brain, there's a lot that's known about it, but there's still some mysteries. There's a lot of debate about exactly the details how these work and what are the signs and we have that still that same level of detail, That same level of concern. What we spend here most of our time doing is trying to make a very good list of the things we don't understand yet. That's the key part here. What are the constraints? It's not like, oh this team seems work, we're done now. It's like okay, it kind of works but these are other things we know it has to do and it's not doing those yet. Um I would say we're well on the way here and we're not done yet. Um There's a lot of trickiness to this system, but the basic principles about how different layers in the neocortex are doing much of this, we understand but there's some fundamental parts that we don't understand. So </s><s>[INST] what would you say is uh one of the harder open problems are one of the ones that have been bothering you uh keeping you up at night the [/INST] most. Well right now this is a detailed thing that wouldn't apply to most people. Okay. But you want me to answer. </s><s>[INST] Yeah. Yeah. [/INST] We've talked about as if, oh to predict what you're going to sense on this coffee cup. I need to know where my finger is gonna be on the coffee cup. That is true, but it's insufficient. Um Think about my finger touches the edge of the coffee cup. My finger can touch at different orientations, right? I can rotate my finger around here. Um And that doesn't change. I can make that prediction. And somehow, so it's not just the location. There's an orientation component of this as well. Um This is known in the old part of the brain to there's things called head direction cells, which which way the rat is facing? It's the same kind of basic idea. Um So my finger a rat, you know, in three dimensions I have a three dimensional orientation and I have a three dimensional location. If I was a rat, I would have a I think it is a two dimensional location, a two dimensional orientation, one dimensional orientation. Like just which way is it facing? So how the two components work together? How is it? I combine orientation? The orientation of my sensor um as well as the the location um is a tricky problem. And uh I think I've made progress on it. </s><s>[INST] So at a bigger version of that. So, prospective. Super interesting. Uh but super specific. [/INST] No, </s><s>[INST] that's really good. But it's uh there's a more general version of that, do you think uh context matters. The fact that we're in a building in north America that uh that we in the day and age where we have mugs. I mean there's all this extra information that you bring to the table about everything else in the room that's outside of just the coffee cup. How does it get? [/INST] So yeah, and that is another really interesting question. I'm gonna throw that under the rubric or the name of attentional problems first of all, we have this model. I have many, many models </s><s>[INST] 1st. And also the question doesn't matter because, [/INST] well it matters for certain things because of course it does. Maybe what we think about as a coffee cup in another part of the world is viewed as something completely different or maybe our logo, which is very benign in this part of the world. It means something very different than the other part of the world. So those things do matter. I think the thing, the way to think about is the following one way to think about it is we have all these models of the world, okay. And remodeled, remodeled everything. And as I said earlier, I kind of snuck it in there are models are actually, we we build composite structure. So every object is composed of other objects which are composed of other objects and they become members of other objects. So this room is chairs and a table in the room and the walls and so on. Now we can just uh arrangements these things a certain way you go. That's the demented conference room. So, so and what we do is when we go around the world and we experience the world. Well, I walk into a room for example, the first thing I did like say, oh I'm in this room, do I recognize the room. Then I can say, oh look there's a there's a table here. Um and I by attending to the table and then assigning this table in the context of the room? And so on the table, there's a coffee cup on the table, there's a logo. And in the logo there's the word momenta. And look in the logo, there's a letter E on look, it has an unusual surf and it doesn't actually but pretended. So the point is you, your attention is kind of drilling deep in and out of these nested structures and I can pop back up, pop back down, I can pop back up, pop back down. So when I attend to the coffee cup, I haven't lost the context of everything else. But it's sort of there's this sort of nested structure. </s><s>[INST] So the attention filters the reference for information for that particular period of time. [/INST] Yes, it basically a moment to moment you attend the sub components and then you can attend the sub components, sub components, </s><s>[INST] You can move up and down, [/INST] you can move up and down that we did that all the time. You're not even now that I'm aware of it. I'm very conscious of it, but until but but most people don't even think about this. You know, you don't, you just walk in a room and you don't say, oh, I looked at the chair and I looked at the board and looked at that word on the board. And I looked over here, what's going on? Right, </s><s>[INST] So what percentage of your day are you deeply aware of this and what part can you actually relax and just be Jeff [/INST] me personally, like my personal day, unfortunately afflicted with too much of the former. Um, I </s><s>[INST] unfortunately are unfortunately, yeah, you don't think it's useful. [/INST] It's useful, totally useful. I think about this stuff almost all the time. And I met one of my primary ways of thinking is when I'm in sleep at night, I always wake up in the middle of night and then I stay awake for at least an hour with my eyes shut in a sort of a half sleep state. Thinking about these things. I come up with answers to problems very often in that sort of half sleeping state. I think about my bike ride, I think about it walks. I'm just constantly think about this. I have to almost a scheduled time to not think about this stuff because it's very, it's mentally taxing. </s><s>[INST] Are you when you're thinking about this stuff, are you thinking introspectively? Like almost taking a step outside of yourself and trying to figure out what is your mind doing? [/INST] I do that all the time. But that's not all I do. I'm constantly observing myself. So as soon as I started thinking about grid cells for example, uh getting into that, I started saying, oh well grid cells have my place of sense in the world, you know, that's where, you know where you are and and essentially, you know, we always have a sense of where we are unless we're lost. And so I started at night when I got up to go to the bathroom, I would start trying to do a complete with my eyes closed all the time and I would test my sense of grid cells. I would I would walk five ft and say, Okay, I think I'm here. AM I really there? What's my error? And then I would calculate error again and see how the errors can accumulate. So even something as simple as getting up in the middle night to go to the bathroom, I'm testing these theories out. Um It's kind of fun and the coffee cup is an example of that too. So I think I find that these sort of everyday introspection czar actually quite helpful. Um It doesn't mean you can ignore the science. I mean I spend hours every day reading ridiculously complex papers. Um that's not nearly as much fun, but you have to sort of build up those constraints. Um and the knowledge about the field and who's doing what and what exactly they think is company here and then you can sit back and say, okay let's try to piece this all together. Um let's come up with some, you know, I'm very in this group here. People, they know they do, I do this all this time. I come in with these introspective ideas and said, well, have you ever thought about this now? What? Well let's all do this together. Um and it's helpful. It's not if as long as you just you don't all you did was that then and you're just making up stuff. But if you're constraining it by the reality of the neuroscience and it's really helpful. </s><s>[INST] So let's talk a little bit about deep learning and uh the successes in the applied space of neural networks, the ideas of training model and on data and these these simple competition units, neuron artificial neurons that with back propagation, the statistical ways of being able to generalize from the training set onto data that's similar to that training set. So where do you think are the limitations of those approaches? What do you think there's strengths relative to your major efforts of constructing a theory of human [/INST] intelligence? Well, I'm not an expert in this field, I'm somewhat knowledgeable. So, but I </s><s>[INST] love it is just your intuition. What are you? [/INST] Well, I have I have a little bit more than intuition, but I just want to say like, you know, uh one of the things that you asked me do, I spend all my time thinking about neuroscience. I do. That's to the exclusion of thinking about things like convolutional neural networks, but I try to stay current. So look, I think it's great the progress they've made. It's fantastic and as I mentioned earlier is very highly useful for many things. Uh the models that we have today are actually derived from a lot of neuroscience principles. There are distributed processing systems and distributed memory systems and that's how the brain works. Um They use things that we we might call them neurons, but they're really not neurons at all. So we can just they're not really neurons, distributed processing systems. Um and uh and the nature of hierarchy that came also from neuroscience. And so there's a lot of things that the learning rules, basically not backdrop but other, you know, heavy. And </s><s>[INST] I'll be I'll be curious to say they're not neurons at all. Can you describe? In which way? I mean some of it is obvious, but I'd be curious if if you have specific ways in which you think are the biggest differences. [/INST] We had a paper in 2016 called Y neurons have thousands of synapses. And it and if you read that paper, you'll you'll know what I'm talking about here. A real neuron in the brain is a complex thing. Uh let's just start with the synapses on it, which is a connection between neurons. Real neurons can everywhere, from 5 to 30,000 synapses on um the ones near the cell body, the ones that are close to the soma of the cell body. Those are like the ones that people model in artificial neurons. There is a few 100 of those, maybe they can affect the cell, they can make the cell become active, 95% of the synapses can't do that, they're too far away. So if you act at one of those synapses, it just doesn't affect the cell body enough to make any difference. Any </s><s>[INST] one of them individually, [/INST] anyone of injury. Or even if you do what mass of them, what what what what real neurons do is the following. If you activate or they, you know, you get 10-20 of them Active at the same time, meaning they're all receiving an input at the same time. And those 10-20 synapses are 40 steps within a very short distance on the dendrite, like 40 microns, a very small area. So if you activate a bunch of these right next to each other at some distant place what happens is it creates what's called the dendritic spike and then drinks bike, travels through the entrance and can reach the soma or the cell body. Now, when it gets there it changes the voltage, which is sort of like going to make the cell fire but never enough to make the self fire. It's sort of what we call it as we d polarize the cell, you raise the voltage a little bit, but not enough to do anything. It's like, well, good is that And then it goes back down again. So Uh we proposed a theory which I'm very confident and basics are, is that what's happening there? Is those 95% of the synapses are recognizing dozens to hundreds of unique patterns. They can, you know about the 10, 20 synapses at the time. And they're acting like predictions. So the neuron actually is a predictive engine on its own. It can fire when it gets enough what they call approximately input from those ones near the cell fire. But it can get ready to fire from dozens to hundreds of patterns that recognizes from the other guys. And the advantage of this to the neuron is that when it actually does produce a spike in action potential, it does so slightly sooner than it would have otherwise. And so what good is slightly sooner? Well, the slightly sooner part is that there's all the neurons in the excited neurons in the brain are surrounded by these inhibitory neurons and they're very fast. The inhibitory neurons, his basketball. And if I get my spike out a little bit sooner than someone else, I inhibit all my neighbors around it. Right. And what you end up with is a different representation. You end up with a reputation that matches your prediction. It's a it's a sparse representation, meaning is fewer non interactive, but it's much more specific. And so we showed how networks of these neurons can do very sophisticated temporal prediction basically. So, so this summarized this real neurons in the brain are time based prediction engines. And and they and there's no concept of this is all in um artificial called point neurons. I don't think you can mail the brain without them. I don't think can build intelligence about because it's the it's where a large part of the time comes from. It's it's these are predictive models and the time is is there's a prior in a prediction in an action and its inherent to every neuron in the neocortex. So, so I would say that point neurons sort of model a piece of that and not very well at that either, but you know, like, like for example, synapses um are very unreliable and you cannot assign any precision to them. So even one digit of precision is not possible. So the way real neurons work is they don't add these, they don't change these weights accurately. Like artificial neural networks do they basically form new synapses. And so what you're trying to always do is is detect the presence of Some 10-20 active synapses at the same time as opposed. And and they're almost binary. It's like because you can't really represent anything much finer than that. So, these are the kind of dish. And I think that's actually another essential component because the brain works on sparse patterns and all about all that mechanism is based on sparse patterns. And I don't actually think you could build our real brains are machine intelligence without incorporating some </s><s>[INST] of those ideas. It's hard to even think about the complex that emerges from the fact that the timing of the firing matters in the brain, the fact that you form new uh new synapses. And I mean everything you just mentioned in the past, [/INST] you can trust me. If you spend time on it, you can get your mind around it. It's not like it's no longer a mystery to me. </s><s>[INST] No, but but sorry, as a function in a mathematical way, it's can you get it start getting an intuition about what gets excited? We're not kind of representation [/INST] as easy as uh there's many other types of neural networks are that are more amenable to pure analysis. You know, especially very simple networks, you know, I have four neurons and they're doing this. Can we describe the mathematically what they're doing, type of thing. Um even the complexity of convolution neural networks today, it's sort of a mystery that can't really describe the whole system. Um And so it's different. My colleague, Super time Ahmad, he did a nice um paper on this. Um You can get all this stuff on our website if you're interested um talking about some of the mathematical properties, a sparse representations. And so we can't, what we can do is we can still mathematically, for example, why 10 to 20 synapses to recognize a pattern is the correct number is the right number you'd want to use. And by the way that matches biology, we can show mathematically some of these concepts about the show why the brain is so robust um to noise and error and fall out and so on. We can show that mathematically as well as empirically in simulations. Um, but the system can be analyzed completely any complex system can, so that's out of the realm. But there is there is mathematical uh, uh, benefits and intuitions that can be derived from mathematics. Uh, and we try to do that as well. Most most of our papers have the section about that. </s><s>[INST] So I think it's refreshing and useful for me to be talking to you about deep neural networks because your intuition basically says that we can't achieve anything like intelligence with artificial neural networks. [/INST] Well, not in the current form, not in the current form. So you can do it in the ultimate form. Sure. </s><s>[INST] So let me dig into it and see what your thoughts are. They're a little bit. So I'm not sure if you write this little blog post called bitter lesson by Rich Sutton recently recently, he's a reinforcement learning pioneer. I'm not sure if you're familiar with him. His basic idea is that all the stuff we've done in a I in the past 70 years, he's one of the old school guys. The biggest lesson learned is that all the tricky things we've done, don't, you know, they benefit in the short term, but in the long term, what wins out is a simple, general method that just relies on moore's law on computation getting faster and faster. So that's what he's saying. [/INST] This is what has worked up to now, </s><s>[INST] this what has worked up to now that if you're trying to build a system, if we're talking about is not concerned about intelligence, is concerned about a system that works in terms of making predictions that applied narrow ai problems. Right. That's what the discussion is about. That. You just try to go as general as possible and wait years or decades for the computation to make it actually. [/INST] Is he saying that as a criticism or is he saying this is a prescription of what we ought to be doing? </s><s>[INST] Well, it's very difficult. He's saying this is what has worked and yes, a prescription, but it's a difficult prescription because it says all the fun things you guys are trying to do we are trying to do. He's part of the community is saying it's only going to be short term gains. So this all leads up to a question, I guess, on artificial neural networks and maybe our own biological neural networks is uh, you think if we just scale things up significantly, so take these dumb artificial neurons? The point, Yeah, I like that term. Uh, if we just have a lot more of them, do you think some of the elements that we see in the brain may start emerging? [/INST] No, I don't think so. We can do bigger problems and uh, of the same type. I mean, it's been pointed out by many people that today's convolutional neural networks aren't really much different than the ones we had quite a while ago. We just they're bigger and train more and we have labeled data and so on. Um uh but I don't think you can get to the kind of things I know the brain can do and that we think about his intelligence by just scaling it up. So uh that maybe it's a good description of what's happened in the past, what's happened recently with the re emergence of artificial neural networks. Um It may be a good prescription for what's going to happen in the short term. Um But I don't think that's the path I've said that earlier. Uh there's an alternate path I should mention to you by the way that we've made sufficient progress on our whole cortical theory in the last few years that last year we decided to start actively pursuing how do we get these ideas embedded into machine learning? Well, that's again being led by my colleague suppertime on and because he's more of a machine learning, I am more of a neuroscience guy. So um this is now our new this is I would say our focus but it is now an equal focus here because we we we need to proselytize what we've learned and we need to show how it's beneficial um to to to the steam works on there. So we're pretty we have a plan in place right now. In fact, we just did our first paper on this, I can tell you about that. Um, but you know, one of the reasons I want to talk to you is because I'm trying to get more people in the machine learning community say like I need to learn about this stuff and maybe we should just think about this a bit more about what we've learned about the brain and what are those team that no matter what have they done, is that useful for us? </s><s>[INST] Yeah, So this is their elements of all the cortical theory that things we've been talking about that may be useful in the short [/INST] term and the short term, Yes, </s><s>[INST] this is the, sorry to interrupt with the open question is, it certainly feels from my perspective that in the long term, some of the ideas we've been talking about will be extremely useful. Question is whether in the short term, [/INST] well this is a always what I would call the entrepreneur's dilemma. So you have this long term vision, oh, we're gonna all be driving electric cars, are, we're all gonna have computers are all gonna whatever. And, and you're at some point in time and you say, I can see that long term vision, I'm sure it's going to happen. How do I get there without killing myself, you know, without going out of business, right? That's the challenge. That's the, that's the really difficult thing to do. So, we're facing that right now. So ideally what you want to do is find some steps along the way that you can get there incrementally, you don't have to like throw it all out and start over again. The first thing that we've done is we focus on the sparse representations. So just just in case you don't know what that means or some of the listeners don't know what that means. Um, in the brain, if I have like 10,000 neurons, what you would see is maybe 2% of them active at the time. You don't see 50%, you don't think 30% you might see 2%. And it's always like that </s><s>[INST] for any set of sensory input. It doesn't [/INST] matter anything. Doesn't matter any part of the brain, </s><s>[INST] but which neurons differs which neurons are [/INST] Active. Yeah. Remember, let's take 10,000 neurons that are representing something sitting there on a bullet block together. It's a teeny little block and around $10,000 and they're representing a location there representing a cop there representing the input from sensors. I don't know. It doesn't matter if it's representing something The way the representations occur. It's always a sparse representation, meaning it's a population code. So which 200 cells are active tells me what's going on. It's not individual cells aren't that important at all. It's the population code that matters. And when you have sparse population codes then all kinds of beautiful properties come out of them. So the brain used the sparse population codes and we've we've written and describe these benefits and some of our papers. So, um they give this tremendous robustness um, to the systems, you know, brains are incredibly robust, neurons are dying all the time and spasming and synapses falling apart and, you know, all the time and it keeps working. So what simple tight. And uh louise, one of our other engineers here have done, I've shown they're introducing sparseness into convolution, neural networks and other people are thinking along designs, but we're going about it in a more principled way, I think. And we're showing that with you enforce sparseness throughout these convolutional neural networks um, in both the, which sort of which neurons are active and the connections between them um that you get some very desirable properties. So one of the current hot topics in uh deploying right now or these adversarial examples. So, you know, I can give me any deep learning network and I can give you a picture that looks perfect and you're going to call it, you know, you're gonna say the monkey is uh, you know, an airplane, so that's a problem. And DARPA just announced some big thing. We're trying to, you know, have some context for this. But if you if you enforce sparse representations here, many of these problems go away, they're much more robust and um, they're not easy to fool. So we've already shown some of those results, uh just literally in january or february, just like last month we did that. Um and um you can, I think it's on by archive right now or an archive, you can read about it, but so that's like a baby step. Okay, that's taking something from the brain. We know we know about sparseness, we know why it's important, we know what it gives the brain. So let's try to enforce that onto </s><s>[INST] this. What's your intuition was sparse? It leads to robustness because it feels like it would be less robust. [/INST] Why, why would you feel the rest of us to you? So </s><s>[INST] it uh it just feels like if the fewer neurons are involved, the more fragile that represents, [/INST] But I didn't say there was lots of future, I said, Let's say 200. That's a lot. </s><s>[INST] There's still a lot. [/INST] So here's an intuition for it. Uh This is a bit technical, so, uh for, you know, for engineers, machine learning people this be easy, but the listeners maybe not. Um if you're trying to classify something, you're trying to divide some very high dimensional space into different pieces, A and B, and you're trying to create some point where you say all these points in this high dimensional space, or a and all these points in high dimensional space would be, and if you have points that are close to that line, it's not for a robust, it works for all the points, you know about, but it's it's not very robust because you can just move a little bit and you've crossed over the line when you have sparse representations. Imagine I pick I'm gonna pick 200 cells active out of out of 10,000. Okay, So I have 200 miles active. Now let's say I pick randomly another, a different representation, 200. The overlap between those is going to be very small. Just a few. I can pick millions of samples randomly Of 200 neurons and not one of them will overlap more than just a few. So one way to think about is if I want to fool one of these representations to look like one of those other representations, I can't move just one cell or two cells are three cells and four cells, I have to move 100 cells and that makes them robust </s><s>[INST] in terms of further. So, you mentioned, Spar City [/INST] will be the next thing. Okay, so we have, we picked one, we don't know if it's gonna work well yet. So again, we're trying to come up incremental ways of moving from brain theory to add pieces to machine learning current machine learning world. And one step at a time. So the next thing we're going to try to do is is sort of incorporate some of the ideas of um the 1000 brains theory that you have many, many models and that are voting. Now, that idea is not new, there's a mixture of models has been around for a long time. Um but the way the brain does is a little different and um uh and the way it votes is different and the kind of way it represents, uncertainty is different. So uh we're just starting this work but we're gonna try to see if we can sort of incorporate some of the principles of voting or principles of 1000 brain theory, like lots of simple models that talk to each other in a very a certain way. Um and can we build more uh machines and systems that learn faster and and also um um well mostly um are multi model and robust to um multiple type of </s><s>[INST] issues. So one of the challenges there is uh you know, the machine learning computer vision community has certain sets of benchmarks. So it's a test based on which they compete and I would argue especially from your perspective that those benchmarks aren't that useful for testing the aspects that the brain is good at or intelligent, they're not really testing intelligence a very fine. Uh It has been extremely useful for developing specific mathematical models, but it's not useful in the long term for creating intelligence. So you think you also have a role in proposing better tests? [/INST] Yeah, this is a very identified a very serious problem. First of all the tests that they have are the tests that they want. Not the test of the other things that we're trying to do right. You know, one of the uh so on. The second thing is sometimes these to be competitive in these tests, you have to have a huge data sets and huge computing power. Um and so, you know, and we don't have that here, we don't have it as well as other big teams that big companies do. Um So there's numerous issues there, you know, we come out of, you know, where our approach to this is all based on, in some sense, you might argue elegance, we're coming at it from like a theoretical base that we think, oh my God, this is this is clearly elegant. This how brains work this one intelligences, but the machine learning world has gotten in this phase where they think it doesn't matter, It doesn't matter what you think as long as you do, you know, .1% better on this benchmark, that's what that's all that matters and and that's a problem. Um You know, we have to figure out how to get around that. That's that's a challenge for us. That's that's one of the challenges we have to deal with. Um So I agree you've identified a big issue, it's difficult. Um for those reasons. Um But you know, part of, you know, part of the reasons I'm talking to you today is I hope I'm gonna get some machine learning people to say read those papers, those might be some interesting ideas, I'm tired of doing this 0.1% improvement stuff, you know? Well </s><s>[INST] that's that's why I'm here as well because I think machine learning now as a community is at a place where the next step is uh needs to be orthogonal to what has receive success in the past. [/INST] You see other leaders saying this machine learning uh leaders, you know Geoff Hinton with this capsules idea. Many people have gotten up to say, you know, we're gonna hit road, well maybe we should look at the brain, you know, things like that. So um hopefully that thinking occur organically and then then we're in a nice position for people to come and look at our work and say well what can we learn from these guys? </s><s>[INST] Yeah, might just launching a billion dollar computing college. The centered around this idea. So is [/INST] on this idea of what uh </s><s>[INST] well the idea that you know the humanity psychology neuroscience have to work all together to get to build the I [/INST] mean stanford just did this human centered AI center, I'm a little disappointed in these initiatives because you know, they're they're folk is sort of the human side of it and it could very easily slip into how humans interact with intelligent machines, which is nothing wrong with that. But that's not that is orthogonal to what we're trying to do, we're trying to say like what is the essence of intelligence? I don't care. In fact, I want to build intelligent machines that aren't emotional, that don't smile at you. You know, they aren't trying to tuck you in at </s><s>[INST] night. Yeah, there's that pattern that you, when you talk about uh understanding humans is important for understanding intelligence, you start slipping into topics of ethics or um yeah, like you said, the interactive elements as opposed to No, no, no. Let's zoom in on the brain. Study, study what the human brain, the baby, the [/INST] let's study what the brain does does, and then we can decide which parts of that we want to recreate in some system. But do you have that theory about what the brain does? What's the point? You know, it's just you're gonna be wasting time. I think </s><s>[INST] just to break it down on the artificial neural network side, maybe you can speak to this on the biological, you know, side the process of learning versus the process of inference. Maybe you can explain to me what is there a difference between, you know, an artificial neural networks, there's a difference between the learning stage and the infant stage. Do you see the brain is something different? One of the, one of the big distinctions that people often say, I don't know how correct it is is artificial neural networks need a lot of data. They're very inefficient learning. Do you see that as a correct distinction from the the biologic, the human brain, that the human brain is very efficient, or is that just something we deceive [/INST] ourselves? No, it is efficient, obviously we can learn new things almost instantly. </s><s>[INST] And so what elements do you think I can [/INST] talk about that? You brought up two issues there? So, remember I talked earlier about the constraints, we always feel well one of those constraints is the fact that brains are continually learning. That's not something we said. Oh, we can add that later, that's something that was up front, had to be there from the start, Um made our problems harder. Um but we showed, going back to the 2016 paper on sequence memory, we showed how that happens. How do brains in for and learn at the same time and our models do that? Um they're not two separate phases or two separate sets of time. I think that's a big, big problem in ai at least for many applications, not for all. Um So I can talk about that, there are some uh gets detailed, there are some parts of the new york cortex in the brain where actually what's going on, there's these, there's these with these cycles uh like cycles of activity in the brain and um there's very strong evidence that you're doing more of inference on one part of the phase and more of learning on the other part of the face. So the brain can actually sort of step with different populations of cells are going back and forth like this. But in general, um, I would say that's an important problem we have, you know, all of our networks that we've come up with do both and they're learning continuous learning networks and you mentioned benchmarks earlier. Well, there are no benchmarks about that. So, so we, you know, we have to like, you know, we get our little uh soapbox, hey, by the way, we, you know, this is important, you know, and here's a mechanism for doing that. But then, you know, but until you can prove it to someone in some commercial system or something a little harder. </s><s>[INST] So yeah, one of the things that I had to linger on that is in some ways to learn the concept of a coffee cup. You only need this one coffee cup and maybe some time alone in a room with it. [/INST] Well, the first thing is when I imagine I reached my hand into a black box and I'm reaching, I'm trying to touch something, I don't know upfront if it's something I already know or if it's a new thing, right? And I have to, I'm doing both at the same time. I don't say, oh, let's see if it's a new thing, oh, let's see if it's an old thing. I don't do that. As I go, my brain says, oh, it's new or it's not new. And if it's new, I start learning what it is. So and by the way it starts learning from the get go, even if he's going to recognize it. So they're they're not separate problems there. So that's the thing, the other thing you mentioned was the fast learning. Um So I was just talking about continuous learning, but there's also fast learning, literally I can show you this coffee cup and I say here's a new coffee cup has got the logo on it, take a look at it, done, you're done, you can predict what is going to look like, you know in different positions. So I can talk about that too in the brain. Um The way learning occurs, I mentioned this earlier but I mentioned again the way learning occurs, I imagine I am a section of a dendrite of a neuron and um I want to learn, I'm going to learn something new. I'm just doesn't matter what it is, I'm just going to learn something new. I I need to recognize the new pattern. So what I'm gonna do is I'm going to form new synapses, new synapses. We got to rewire the brain onto that section of the of the dendrite once I've done that everything else that neuron has learned is not affected by it. That's because it's isolated to that small section of the country, they're not all being added together, like a pointing around. So if I learn something new on this segment here, it doesn't change any of the learning occurred anywhere else in that in around so I can add something without affecting previous learning and I can do it quickly. Um Now let's talk we can talk about the quickness how it's done in real neurons you might say well doesn't it take time to form synapses? Yes it can take maybe an hour to form a new synapse. Um We can form memories quicker than that and I can explain that happens too if you want but it's getting a bit neuroscience. E so that's </s><s>[INST] great. But is there an understanding of these mechanisms at every level? So from the short term memories and the forming uh [/INST] so this idea of synaptic genesis, the growth of new synapses that's well described as well understood and that's an </s><s>[INST] essential part of learning [/INST] that is learning that is learning okay. Um you know back you know they're going back many many years people you know, was uh what's his name? The psychologists proposed heavy Hebb donald trump. He proposed that learning was the modification of the strength Of a connection between two neurons. People interpreted that as the modification of the strength of a synapse. He didn't say that, he just said there's a modification between the effect of one neuron and another. So synaptic genesis is totally consistent with Donald Hebb said. But anyway there's these mechanisms that growth in new standards. You can go online, you can watch a video of a synapse growing in real time. It's literally you can see this little thing going right, It's pretty impressive. So that those mechanism known now. There's another thing that we have speculated and we've written about which is consistent with no neuroscience, but it's less proven and this is the idea. How do I form a memory really, really quickly? Like, instantaneously if it takes an hour to go synapse, like that's not instantaneous. So there are there are types of synapses called silent synapses. They look like a synapse, but they don't do anything, they're just sitting there. It's like they uh actually potential comes in, it doesn't release any neurotransmitter. Some parts of the brain have more of these than others. For example, the hippocampus has a lot of them, which is uh where we associate most short term memory with. Um so what we we speculated again in that 2,016 paper, we propose that the way we form very quick memories, very short term memories or quick memories is that we convert um silence and synopsis into active synopsis. It's going it's like seeing a synapse has a zero weight and one weight. But the long term memory has to be formed by synaptic genesis. So you can remember something really quickly by just flipping a bunch of these guys from silent active. It's not like, it's not from 0.12 point 15, it's like doesn't do anything to release his transmitter if I do that over a bunch of these, I've got a very quick short term memory. Um so I guess the lesson behind this is that most neural networks today are fully connected. Every neuron connects every other neuron from layer to layer. That's not correct in the brain. We don't want that. We actually don't want that. It's bad if you want a very sparse connectivity so that um any neuron connects to some subset of the neurons and the other layer and it does so on a dendrite dendrite segment basis. So it's a very parse elated out type of thing. And that then learning is not adjusting all these ways, but learning is just saying, Okay, connect to these 10 cells here </s><s>[INST] right now in that that process, you know, with artificial neural networks, it's a very simple process back propagation that adjust the weights, the process of synaptic genesis genesis Chapter genesis it's even easier. It's even easier. [/INST] It's even easier. Back propagation requires something we uh it really can't happen in brains. This back propagation of this area. Signal that it really can't happen. People are trying to make it happen in brains. That doesn't happen. This is this is pure heavy and learning Well, it's not the genesis is pure heavy and learning. It's basically saying there's a population of cells over here that are active right now and there's a population of cells over here active right now, how do I form connections between those active cells And it's literally saying this guy became active, this these 100 neurons here became active before this neuron became active. So form connections to those ones. That's it. There's no propagation of error, nothing. All the networks, we do all models, we have work on almost completely on heavy and learning, but in in on dendritic segments and multiple synapses at the same time. </s><s>[INST] So now let's have turned the question that you already answered and maybe you can answer it again, if you look at the history of artificial intelligence, where do you think we stand? How far are we from solving intelligence? You said you were very optimistic. Can you elaborate on that? [/INST] Yeah. You know, it's always the crazy question to ask Because you know, no one can predict the future. So I'll tell you a story. I used to uh I used to run a different neuroscience institute called the redwood neuroscience to two and we would we would hold these symposiums and we got like 35 scientists around the world to come together. And I used to ask them all the same question, I would say well how long do you think it'll be before we we understand how the new york cortex works And everyone went around the room and they had introduced the name and they have to answer that question. So I got The typical answer was 50 200 years. Some people would say 500 years, some people said never. I said, what are you while you're a neuroscientist, it's good pay. Um it's interesting. Um so, you know, but it doesn't work like that, as I mentioned earlier, these are not, these are step functions, things happen and then bingo that happened. You can't predict that. Um I feel I've already passed that step function. So if I can do my job correctly over the next five years, um then meaning I can proselytize these ideas, I can convince other people that right? We can show that other people, uh machine learning people should pay attention to these ideas, then we're definitely in an under 20 year time frame, if I can do those things, if I if I'm not successful in that, and this is the last time anyone talks to me and no one reads our papers and you know, I'm wrong or something like that, then um then I don't know, But it's it's not 50 years, it's it, You know, it'll it'll, you know, the same thing about electric cars, how quickly are they going to populate the world? It's probably takes about a 20 year span. Um it'll be something like that, but I think if I can do what I said, we're starting it </s><s>[INST] and of course there could be other use of step functions, it could be, Everybody gives up on your ideas for 20 years and then all of a sudden somebody picks it up again, wait, that guy was onto [/INST] Something. So that would be that would be a failure on my part. Right. You know, think about Charles Babbage, you know, Charles Babbage. This guy has to have invented the computer back in 18 something, 1800s. Everyone forgot about it until, you know, 100 years later. Hey, this guy figured this stuff out a long time ago, you know, but he was ahead of his time, I don't think, you know, like, uh, as I said, uh, I recognize this is part of any entrepreneurs challenge and I use the entrepreneur broadly in this case, I'm not meaning like I'm building a business trying to sell something. I mean, I'm trying to sell ideas and this is the challenge as to how you get people to pay attention to you, How do you get them to give you positive or negative feedback? Um, how do you get people act differently based on your ideas? So, um, you know, we'll see how, what we do on them. </s><s>[INST] So, you know, that there's a lot of hype behind artificial intelligence currently, do you? Uh, as as you look to spread the ideas that are of no cortical theory, the things you're working on, Do you think there is some possibility will hit an Ai winter? Once again, [/INST] it's certainly it's certainly a possibility that I worry about. Yeah, well I guess do I worry about it. Um I haven't decided yet if that's good or bad for my mission. </s><s>[INST] That's true. That's very true because it's almost like you need the winter to refresh the palate. [/INST] Yeah. So it's like I want here's what you want to have. It is you want like to extend that. Everyone is so thrilled about the current state of machine learning and Ai and they don't imagine they need anything else that makes my job harder if if everything crashed completely and every student left the field and there was no money for anybody to do anything. And it became an embarrassment to talk about machine intelligence and Ai. That wouldn't be good for us either. You want you want sort of the soft landing approach, right? You want enough people in the senior people in AI and machine learning and say, you know, we need other approaches. We really need other approaches. But damn we need other approaches. Maybe we should look to the brain. Okay, let's look who's got some brain ideas. Okay, let's let's start a little project on the side here trying to do brain idea related stuff. That's the ideal outcome we would want. So I don't want a total winter and yet I don't want it to be sunny all the time </s><s>[INST] either. So what do you think it takes to build a system with human level intelligence where once demonstrated you would be very impressed. So does it have to have a body, does it have to have the the C. Word we used before. Consciousness? Uh as as as an entirety as a holistic sense. [/INST] First of all, I don't think the goal is to create a machine that is human level intelligence. I think it's a false goal. Back to touring. I think it was a false payment. We want to understand what intelligence is and then we can build intelligent machines of all different scales, all different capabilities. You know, a dog is intelligent. I don't need, you know, that'd be pretty good to have a dog, you know? But what about something that doesn't look like an animal at all in different spaces? So my thinking about this is that we want to define what intelligence is agree upon what makes an intelligence system. We can then say okay we're now going to build systems that work on those principles or some subset of them and we can apply them to all different types of problems. And um the kind of the idea, it's not computing, we don't ask if I take a little um you know, little one chip computer. I don't say, well that's not a computer because it's not as powerful as this. You know, big server over here. No, no because we know that what the principles of computing are and I can apply those principles to a small problem into a big problem insane. Intelligence needs to get there. We have to say these are the principles, I can make a small one, a big one. I can make them distributed, I can put them on different sensors. They don't have to be human like at all. Now you did bring up a very interesting question about embodiment, does that have to have a body, It has to have some concept of movement, It has to be able to move through these reference frames. I talked about earlier whether it's physically moving like I need if I'm going to have a a I that understands coffee cups, it's gonna have to pick up the coffee cup and touch it and look at it with with its eyes and hands or something equivalent to that. Um If I have a mathematical ai maybe it needs to move through mathematical spaces, I could have a virtual ai that lives um in the internet and its its movements are traversing links and digging into files but it's got a location that it's path, it's traveling through some space. You can't have an Ai to just take some flash thing. Input we call the flash inference. Here's a pattern done. No, it's movement, movement pattern, movement pattern, movement pattern, attention digging, building, building structure decided, figured out the model of the world. So some sort of embodiment embodiment, whether it's physical or not has to be part of it. </s><s>[INST] So self awareness in the way to be able to answer where am I [/INST] what you bring himself to different topics. Self awareness, </s><s>[INST] know very narrow definition, meaning knowing a sense of self enough to know where am I in the space work? [/INST] Basically the system, the system needs to know its location for each component of the system needs to know where it is in the world at that point in time. </s><s>[INST] So self awareness and consciousness, do you think one from the perspective of neuroscience and neocortex, these are interesting topics, solvable topics. Do you have any ideas of what? Why the heck it is that we have a subjective experience at [/INST] all? I have a </s><s>[INST] lot of it is it useful or is it just a side effect of this? [/INST] It's interesting to think about, I don't think it's useful as a means to figure out how to build intelligent machines. It's uh it's something that systems do and we can talk about what it is that are like, well if I build a system like this then it would be self aware or and if I build it like this it wouldn't be a self aware. So that's his choice. I could have, it's not like oh my God, it's self aware, you know, I can't, I heard um an interview recently with this philosopher from Yale, I can't remember his name, I apologize for that but he was talking about well if these computers are self aware then it would be a crime to unplug him and I'm like, oh come on, you know, it's not, you know, I applied myself every night, I go to sleep with? Is that a crime? You know I plug myself in again in the morning. I'm there. I am. So uh huh. Uh you know people get kind of bent out of shape about this. I have very definite very detailed understanding or opinions about what it means to be conscious and what it means to be self aware. Uh I don't think it's that interesting problem. You talked about christoph cock, you know, he thinks that's the only problem. I didn't actually listen to your interview with him. But um I know him and I know that's the thing. </s><s>[INST] He also thinks intelligence and consciousness are this joint. So I mean it's not, you don't have to have one or the other. So he [/INST] disagree with that. I just totally disagree with that. </s><s>[INST] So where is your your thoughts are conscious? Where does it emerge from? Because it [/INST] is so then we have to break it down to the two parts. Okay, because consciousness isn't one thing that's part of the problem with that term is it means different things to different people and there's different components of it. There is a concept of self awareness. Okay. That can be very easily explained. Um You have a model of your own body, the neocortex models, things in the world and it also models your own body and and then it has a memory, it can remember what you've done. Okay, so it can remember what you did this morning, remember what judge for breakfast and so on. And so I can say to you okay lex um uh were you conscious this morning when you hide your bagel? And you say yes I was conscious now. What if I could take your brain and revert all the synapses back to the state they were this morning? And then I said to you that were you conscious when you ate the bagel? He said no I wasn't conscious. So here's a video of eating the bagel. He said I wasn't there. I have no that's not possible because I was I must have been unconscious at that time. So we can just make this 1 to 1 correlation between memory of your body's trajectory through the world over some period of time? A memory and the ability to recall that memory is what you would call conscious. I was conscious of. That. It's a self awareness. Um And and any system that can recall, memorize what it's done recently and bring that back and invoke it again. I would say yeah I'm aware. Remember what I did. All right. I got it. That's an easy one. Although some people think that's a hard one. The more challenging part of consciousness is this is one that sometimes you just going by the word of quality. Um Which is why does an object seem red or what is pain and why does pain feel like something? Why do I feel redness? So why do I feel a little pain nous in the way. And then I could say well why the site seems different than to hear it. You know it's the same problem. It's really uh these are all this neurons. And so how is it that why does looking at you feel different than you know I'm hearing you? It feels different but this is neurons in my head, they're all doing the same thing. So that's an excellent question. Um The best treatise I've read about this is by a guy named Reagan or Regan. He wrote a book called Why Red doesn't sound like a bell. Um It's a little um you know it's not it's not a trade book, easy read. But and and it's an interesting question. Um Take something like color. Color really doesn't exist in the world. It's not a property of the world properly. The world that exists is light frequency. And that gets turned into, we have certain cells in the retina that respond to different frequencies different than others. And so when they enter the brain you just have a bunch of axons that are firing at different rates. And from that we perceive color there is no color in the brain. I mean there's there's no color coming in on those synapses. It's just a correlation between some some exxons and some property of frequency. Um And that isn't even color itself frequency doesn't have a color, it's just a it's just what it is. So then the question is well why doesn't even appear to have a color at all? Um </s><s>[INST] Just as you're describing it there seems to be a connection to the those ideas of reference frames. I mean it just feels like consciousness having the subject assigning the feeling of red to the actual color or to the wavelength is useful. Yeah I think [/INST] that's a good way of putting it. It's useful as a predictive mechanism or useful. There's a generalization idea. It's it's a way of grouping things together to say it's useful to have a model like this. Um Think about the there's a well known syndrome that people who have lost a limb experience called phantom limbs. And what they claim is they can have their arm is removed but they feel the arm that not only feel it, they know it's there, they it's there I can I know it's there, they'll swear to you that it's there and then they can feel pain in their arm and they feeding their finger in and they move there. They move their non existent arm behind your back then they feel the pain behind their back. So this whole idea that your arm exists is a model of your brain. It may or may not really exist. Um And just like but it's useful to have a model of something that sort of correlates to things in the world. So you can make predictions about what would happen when those things occur. It's a little bit funny but I think you're getting right towards the answer there. It's it's useful for the model of um to express things certain ways that we can then map them into these reference frames and make predictions about them. I need to spend more time on this topic. It doesn't bother me. </s><s>[INST] Do you really need to spend more time? It does feel special that we have subjective experience but I'm yet to know why. [/INST] I'm just I'm just personally curious. It's not necessary for the work we're doing here. I don't think I need to solve that problem to build intelligent machines at all. Not at all. </s><s>[INST] But there is sort of the silly notion that you describe briefly that doesn't seem so silly to us. Humans is you know if you're successful building intelligent machines it feels wrong to then turn them off because if you're able to build a lot of them it feels wrong to them be able to you know to turn off the [/INST] boy but just let's let's break that down a bit as humans, why do we fear death? There's there's two reasons we've heard of. Well first of all stay when you're dead. Doesn't matter all. Okay you're dead. So why do we fear death? We fear death for two reasons. One is because we are programmed genetically to fear death. That's a that's a survival and proper beginning the jeans thing. Um, and we also are programmed to feel sad when people we know die, we don't feel sad for someone. We don't know dies people dying right now. The only comes in and I feel bad about it because I don't know them. But I knew they might feel really bad. So again, this is these are old brain genetically embedded things that we feared up outside of those, those uncomfortable feelings. There's nothing else to worry about. </s><s>[INST] Wait, hold on a second. Don't do you know the denial of death by Becker Dental? You know, there's a thought that death is, you know, our whole conception of our world model kind of assumes immortality and then death is this terror that underlies it also like, [/INST] well some people's world, not mine. </s><s>[INST] But okay. So what what Becker would say is that you're just living an illusion. You've constructed illusion for yourself because it's such a terrible terror. The fact that this and the illusion that death doesn't matter. You're still not coming to grips [/INST] with the illusion of what death is going </s><s>[INST] to happen. [/INST] It's </s><s>[INST] not going to happen. You're, you're actually operating, you haven't, even though you said you've accepted it, You haven't really accepted no sugar diet is what you say. So it sounds like it sounds like you disagree with that notion. I mean [/INST] totally like it's not that important every night I go to bed, it's like </s><s>[INST] dying a little death. [/INST] It does. And and if I didn't wake up? It wouldn't matter to me only if I knew that was gonna happen would be bothered him. If I didn't know I was gonna have, how would I know? No, But then I would worry about my wife. So imagine imagine I was a loner and I lived in Alaska and I lived out there and there's no animals. Nobody knew I existed. I was just eating these roots all the time and nobody knew was there. And one day I didn't wake up, where what what pain in the world would there exist? </s><s>[INST] Well, so most people that think about this problem would say that you're just deeply enlightened or are completely delusional. But I would say I would say that's very enlightened, enlightened way to see the world. Is that that's the rational one. Rational. That's right. But the fact is we don't uh I mean, we really don't have an understanding of why the heck it is we're born and why we die and what happens afterwards? [/INST] Maybe there isn't a reason. Maybe there is. So I'm interest in those big problems too. Right? You know, you you interviewed max take Mark, you know, there's people like that, right? I'm missing those big problems as well. And In fact, when I was young, I made a list of the biggest problems I can think of first. Why does anything exist? 2nd? Why did we have the laws of physics that we have? Third is life inevitable? And why is it here? Fourth is intelligence inevitable? And why is it here? I stopped there because I figured if you can make a truly intelligent system will be, that will be the quickest way to answer the first three questions. I'm serious. And and so I said, my mission, you know, you asked me earlier my first mission is to understand the brain. But I felt that is the shortest way to get the true machine intelligence. And I want to get the true machine intelligence because even if it doesn't occur in my lifetime, other people will benefit from it because I think it will come in my lifetime. But you know, 20 years and you never know. And uh but that would be the quickest way for us to, you know, we can make super mathematicians, we can make super space explorers. We can make super physicist brains that do these things and um that can run experiments that we can't run. We don't have the abilities to manipulate things and so on. But we can build intelligent machines that do all those things. And with the ultimate goal of finding out the answers to the other questions, </s><s>[INST] Let me ask you another depressing and difficult question, which is once we achieve that goal, uh do you of creating a no of understanding intelligence, Do you think we would be happier more fulfilled as a species? [/INST] To understand intelligence? Or understanding the answers to the big questions? </s><s>[INST] Understanding [/INST] intelligence? How are totally, totally being far more fun place to live? So, Yeah. Why not? I mean, you know, just put aside this, you know, terminator nonsense. And and and and just think about, you can think about, we can talk about the risk of they are if you want. But I I think the world is far better. Knowing things were always better than no things. Do you think it's better? Is it a better place? The world, the living? That I know that our planet is one of many in the solar system, in the solar cell is one of many of the galaxy. And I think it's more, I dread. I used to I sometimes think like, God, what would be like to live 300 years ago, I'd be looking at the sky. I can't understand anything. Oh my God, I'd be like going to bed and I go and what's going on here? </s><s>[INST] Well, I mean, in some sense, I agree with you, but I'm not exactly sure. I'm also a scientist. So I have I share your views, but I'm not, we're like rolling down the hill together, uh [/INST] what's down the hill? I feel like we're climbing a hill. </s><s>[INST] Whatever. [/INST] Getting we're getting closer to enlightenment and whatever the downtown </s><s>[INST] we're climbing, we're getting pulled up a hill by [/INST] curiosity. Put polio cities, we're pulling ourselves up the hill by our curiosity. </s><s>[INST] Yeah, because we're doing the same thing with the rock. Uh, but okay, our happiness aside, do you have concerns about, you know, you talk about Sam Harris, you know, musk of existential threats of intelligence. [/INST] I'm not worried about existential threats at all. I there are there are some things we really do need to worry about. Even today, I have things we have to worry about. We have to worry about privacy and about how impacts um false beliefs in the world. And we have real problems that uh, and things to worry about with today's Ai um and that will continue as we create more intelligent systems. There's no question, you know, the whole issue about, you know, making intelligent armament and weapons is something that really we have to think about carefully. I don't think of those as existential threats. I think those are the kind of threats we always face. And we'll have to face them here. And and uh, and we have to deal with them. Um, the we can we can talk about what people think are the existential threats. But, uh, when I hear people talking about them, they all sound hollow. To me. They're based on ideas. They're based on people who really have no idea what intelligence is. And and if if they knew what intelligence was, they wouldn't say those things. So those are not experts in the field, you know? </s><s>[INST] So, yeah, So there's two right there. So one is like super intelligence. So a system that becomes far far superior in reasoning ability than us humans. [/INST] How is that an existential threat </s><s>[INST] then? So there's a lot of ways in which it could be one way as us humans are actually irrational and efficient and get in the way of uh of not happiness, but whatever the objective function is of maximizing that objective function and super intelligent [/INST] paperclip problem and things like </s><s>[INST] that. So the paperclip problem. But with the super intelligent. [/INST] Yeah. So uh we already faced this threat in some sense. Uh they're called bacteria. These are organisms in the world that would like to turn everything into bacteria. And they're constantly morphing their constantly changing to evade our protections. And in the past they have killed huge swaths of populations of humans on this planet. So if you want to worry about something that's gonna multiply endlessly we have it. And I'm far more worried in that regard. I'm far more worried that some scientists in the laboratory will create a super virus or super bacteria that we cannot control. That is a more existential strip, putting putting an intelligent thing on top of it actually seems to make it less existential. To me, it's like it limits its power, has limits where it can go. It limits the number of things that can do in many ways that bacteria is something you can't you can't even see </s><s>[INST] uh so that's [/INST] only one of those problems. </s><s>[INST] Exactly. So the the other one. Just in your intuition about intelligence when you think about intelligence as humans, do you think of that as something? Uh If you look at intelligence on the spectrum from zero to us, humans, do you think you can scale that to something far superior? All the mechanisms would [/INST] be let me I want to make another point here before I get there. Intelligence is the new york cortex. It is not the entire brain. If I the goal is not to be make a human, the goal is not to make an emotional system. The goal is not to make a system that wants to have sex and reproduce. Why would I build that if I want to have a system that wants to reproduce, have sex. Make bacteria make computer viruses. Those are bad things don't do that. Those are really bad. Don't do those things regulate those. But if I just say I want an intelligence system, why doesn't have to have any of the human like emotions. Why couldn't why doesn't even care if it lives, Why does it even care if it has food? It doesn't care about those things. It's just you know, it's just in a trance thinking about mathematics or it's out there. Just trying to build the space plan? You know for it on mars it's a we don't that's a choice we make. Don't make human like things don't make replicating things don't make things that have emotions just stick to the new york cortex. </s><s>[INST] So that's that's what you actually that I share. But not everybody shares in the sense that you have faith and optimism about us as engineers and systems humans as builders of systems to uh to do not put in stupid [/INST] not. So this is why this is why I mentioned the bacteria one because you might say, well some person is going to do that well, some person today could create a bacteria that's resistant to all the non antibacterial agents. So we already have that threat. We already know this is going on. It's not a new threat. So just accept that and then we have to deal with it. Right? Yeah. So my point has nothing to do with intelligence. It intelligence is a separate component that you might apply to a system that wants to reproduce and do stupid things. Let's not do that. </s><s>[INST] Yeah. In fact it is a mystery why people haven't done that yet. Uh my my dad is a physicist believes that the reason. So for example, nuclear weapons haven't proliferated amongst evil people. So one is one belief that I share is that there's not that many evil people in the world that would that uh that would use back to whether it's bacteria in nuclear weapons or maybe the future ai systems to do bad. So the fraction is small and the second is that it's actually really hard technically. So the intersection between evil and competent is small in terms of and [/INST] By the way, really annihilate humanity. You'd have to have uh you know, sort of the nuclear winter phenomenon which is not one person shooting, you know, or even 10 bombs. You'd have to have some automated system that, you know, detonates a million bombs or whatever many thousands. We have </s><s>[INST] extreme evil combined with extreme competence [/INST] and just building some stupid system that would automatically, you know, dr strangelove type of thing, you know that name at all. But I mean look, we could have some nuclear bomb go off in some major city in the world. I think that's actually quite likely even in my lifetime. I don't think that's unlikely thing. And it'll be a tragedy. Um, but it won't be an existential threat. Um, and it's the same as, you know, the virus of 1917, whatever it was, you know, the influenza, um, these bad things can happen and the plague and so on. We can't always prevent it. We always to always try, but we can't but they're not existential threats until we combine all those crazy things together one. </s><s>[INST] So on the spectrum of intelligence from zero to human, do you have a sense of whether it's possible to create several orders of magnitude or at least double that of human intelligence. I think in your court tax, [/INST] I think it's the wrong thing to say Double the intelligence. Break it down into different components. Can I make something that's a million times faster than a human brain? Yes, I can do that. Could I make something that is um has a lot more storage than human brain? Yes, I could do that more calm, More copies come. Can I make something that attaches the different senses than human brain? Yes, I can do that. Could I make something that's distributed? So these people, we talked earlier about the departure neocortex voting. They don't have to be co located. You know, they could be all around the places. I could do that too. Um Those are the levers I have but is it more intelligent? What depends what I train it on, What is it doing it </s><s>[INST] Well. So here's the thing. So let's say larger in your cortex and or whatever size that allows for higher and higher hierarchies to form. We're talking about reference frames and [/INST] constant. Could I have something that's a super physicist or super mathematician? </s><s>[INST] And the question is, once you have a super physicist, will they be able to understand something? Uh you have a sense that it will be ordered like us compared [/INST] to what we ever understand it. Most people cannot understand general relativity. It's a really hard thing to get, I mean, you know, you can paint in a fuzzy picture stretchy space, you know, But the field equations to do that. And the deep intuitions are really, really hard and um I've tried I unable to do it, I used to get, you know, it's easy to get special relativity, general man, that's too much. Um and so we already live with this to some extent, the vast majority of people can't understand actually what the vast majority of the people actually know. Uh we're just either we don't have the effort to or we can't or we don't time or just not smart enough, whatever. So um but we have ways of communicating Einstein has spoken in a way that I can understand, he's given me analogies that are useful, I can use those analogies from my own work and think about concepts that are similar. Um It's not stupid, it's not like he's existing some of the plane has no connection with my plane in the world here, so that will occur. It already has occurred. That's when my point that this story is, it already has occurred. We live it every day. Um One could argue that with we create machine intelligence that think a million times faster than us, that it will be so far we can't make the connections, but, you know, at the moment, everything that seems really, really hard to figure out in the world when you actually figure it out. It's not that hard, you know, if we can everyone, most everyone can understand the multiverse is almost everyone can understand quantum physics. Almost everyone can understand these basic things, even though hardly anybody, people could figure those things out. </s><s>[INST] Yeah, but really understand. So you [/INST] need to really only a few people really don't understand. </s><s>[INST] You need to only understand the the projections, the sprinkles of the useful insights. That [/INST] was my example of Einstein right? His general theory of relativity is one thing that very, very, very few people can get. And what if we just said those other few people are also artificial intelligence is how bad </s><s>[INST] is that? In some sense? They are [/INST] right. So they say already, I mean, Einstein wasn't a really normal person. He had a lot of weird quirks. And so so the other people who work with him, so, you know, maybe they already were sort of this astral plane of intelligence that we live with it already. It's not a problem. Um it's still useful and you know, </s><s>[INST] so do you think we are the only intelligent life out there in the universe? [/INST] I would say that intelligent life has and will exist elsewhere in the universe. I'll say that there is a question about contemporaneous intelligence, life, which is hard to even answer when we think about relativity and the nature of space time. You can't say what exactly is this time? Someplace else in the world, but I think it's, you know, I do worry a lot about the filter idea, which is that perhaps intelligent species don't last very long. And so we haven't been around very long. And as a technological species, we've been around for almost nothing, you know, what, 200 years. Something like that. And we don't have any data. Good data point on whether it's likely that we'll survive or not. Uh, so do I think that there have been intelligent life elsewhere in the universe? Almost certain, of course, in the past and the future? Yes. Um, does it survive for a long time? I don't know. This is another reason I'm excited about our work is our work, meaning that general world of ai um, I think we can build intelligent machines, um, that outlast us. Uh, you know, they don't have to be tied to Earth. They don't have to, you know, I'm not saying they're recreating, you know, you know, aliens. I'm just saying if I asked myself and this might be a good point to end on here. If I asked myself, you know, what's special about our species were not particularly interesting, physically. We're not, we don't fly. We're not good swimmers were not very fast, but not very strong. You know, it's our brain. That's the only thing. And we are the only species on this planet that's built a model of the world that extends beyond what we can actually sense. We're the only people who know about the far side of the moon and the other universes and I mean all the Galaxies and other stars. And uh, about what happens in the atom, There's no that knowledge doesn't exist anywhere else. It's only in our heads. Cats don't do it. Dogs into monkeys don't do it just once. And that is what we've created. That's unique, not our genes, it's knowledge. And if I asked me, what is the legacy of humanity? What what what should our legacy be? It should be knowledge. We should preserve our knowledge in a way that it can exist beyond us. And I think the best way of doing that. In fact, you have to do it is to have to go along with intelligent machines that understand that knowledge. Um, that's a very broad idea. But we should be thinking, I call it a state planning for humanity. We should be thinking about what we want to leave behind one as a species. We're no longer here. Um, and that will happen sometime sooner or later. It's going to </s><s>[INST] happen. And understanding intelligence and creating intelligence gives us a better chance to prolong [/INST] it does give us a better chance prolong life. Yes, it gives us a chance to live on other planets. But even beyond that, I mean, our solar system will disappear one day. Just give it enough time. So, I don't know. I doubt we'll ever be able to travel uh to other things. But we could tell the stars, but we could send intelligent machines to do that. </s><s>[INST] So you have uh you have an optimistic and hopeful view of our knowledge of the echoes of human civilization living through the intelligence systems, we create [/INST] totally. Well, I think the intelligence systems are created, in some sense, the vessel for bring him beyond earth, uh, making them last beyond humans themselves. So </s><s>[INST] how do you feel about that? That they won't be human? Quote unquote. [/INST] Okay. It's not human. What is human? Our species are changing all the time. Human today is not the same as human. Just 50 years ago. It's what is human? Do we care about our genetics? Why is that important? As I point out, our genetics are no more interesting than a bacterium's genetic. No more interesting than, you know, monkeys, genetics. What we have, what what's unique and what's valuable is our knowledge of what we've learned about the world. And that is the rare thing. That's the thing we want to preserve. It's what cares about our genes, </s><s>[INST] the knowledge, the knowledge. That's a really good place to end. Thank you so much for talking. [/INST] It was fun. </s>

<s>[INST] But it's interesting if the direction in which that progress is happening has some revolutionary value or if it's merely a drift that can go into any direction, [/INST] I'm not sure it's any direction and I'm not sure it's evolutionarily valuable. What it is is um progressive in the sense that each step is a step in the same direction as the previous step. So it becomes more gentle, more decent as by modern standards, more liberal, um less violent. </s><s>[INST] You put more decent. I think you're using terms in interpreting everything in the context of the 21st century, because Genghis Khan would probably say that this is not more decent because we're now, you know, there's a lot of weak members of society, they were not [/INST] murdered. Yes, I was careful to say bye bye. The standard, the 21st century by our standards. If we with hindsight look back at history, what we see is a trend in the direction towards us, towards our present, our present value for </s><s>[INST] us. We see progress. But it's an open question whether that won't, you know, I don't see necessarily why we can never return to genghis contacts. [/INST] We could, I suspect we won't. But it, but if you look at the history of moral values over the centuries, it isn't a progressive. I use the word progressive, not in a value judgment sense in the sense of a transitive sense. Each step is the same in the same direction as the previous step. So things like we don't um derive entertainment from torturing cats. Um, we don't derive entertainment from, from like the romans did in the coliseum from from </s><s>[INST] or rather or rather we suppress uh, the desire to get, I mean to have play, it's probably in us somewhere. So there's a bunch of parts of our brain, one that probably, you know, olympic system that wants certain pleasures and that's uh, [/INST] I mean, I wouldn't have said that, but you're at liberty to think that like, </s><s>[INST] well there's a, there's a dan Carlin of hardcore history. That's a really nice explanation of how we've enjoyed watching the torture of people, the fighting of people just to torture the suffering of people throughout history as entertainment until quite recently. And now everything we do with sports or kind of channeling that feeling into something else. So I mean there is some dark aspects of human nature, There are underneath everything and I do hope this like higher level software we've built will keep us at bay. [/INST] I'm also </s><s>[INST] jewish and have history with uh the soviet union and the holocaust. And I clearly remember that some of the darker as opposed to human nature creeped up [/INST] there. They do. There have been, there have been steps backwards admittedly and the holocaust is obvious one. But if you take a broad view of history, it's, it's the same direction. </s><s>[INST] So Pamela McCord IQ and machines who think has written that a I began with the ancient wish to forge the gods. Do you see it's, it's a poetic description I suppose. But do you see a connection between our civilizations, historic desire to create gods to create religions and our modern desire to create technology and intelligent technology? [/INST] I suppose there's a link between an ancient disaster explain away mystery and, and science, but um, intelligence, artificial intelligence creating gods creating new gods. Um, I mean I forget what I read somewhere somewhat facetious um, paper which said that we have a new god is called google. And, and, and we, we pray to it and we worship it and we and we ask its advice like an oracle and so on. Um, that's fun and </s><s>[INST] you don't see that you see that as a fun statement of facetious statement. You don't see that as a kind of truth of us creating things that are more powerful than ourselves and natural, [/INST] it has a kind of poetic resonance to it, which I get, but I wouldn't I wouldn't have bothered to make the point myself that way. All right, </s><s>[INST] so you don't think ai will become our new a new religion and new gods like google? [/INST] Well, yes, I mean I I can see that the future of intelligent machines or indeed intelligent aliens from outer space might yield beings that we would regard as gods in the sense that they are so superior to us that we might as well worship them. That's highly plausible I think. But I see a very fundamental distinction between a god who is simply defined as something very, very powerful and intelligent on the one hand and a god who doesn't need explaining by a progressive step by step process like evolution or like or like engineering design. So, um the difference, so suppose we did meet an alien from outer space who was marvelously magnificently more intelligent than us and we would sort of worship it and for that reason nevertheless, it would not be a god in the very important sense that it did not just happen by to be there like God is supposed to, it must have come about by a gradual step by step, incremental progressive process presumably like Darwinian evolution is that there's all the difference in the world Between those two intelligence design comes into the universe late as a product of a progressive evolutionary process or progressive engineering design </s><s>[INST] process. So most of the work is done through this slow moving [/INST] exactly progress. Exactly </s><s>[INST] yeah. Uh huh uh yeah it's but there's still this desire to get answers to the wide question that if if we're if the world is a simulation, if we're living in a simulation that there's a programmer like creature that we can ask questions of this, Well [/INST] let's put let's pursue the idea that we're living in a simulation, which is not not totally ridiculous by the way. Um here we go. Um then you still need to explain. The programmer, The programmer had to come into existence by some, even if we're in a in a simulation, the programmer must have evolved or if he's in a sort of she or she she's she's in a meta simulation, then the meta meta program I must have evolved by gradual process. You can't escape that fundamentally. You've got to come back to a gradual incremental process of explanation to start with, </s>

<s>[INST] How does love win over hate Ryan Hall in this world. We talked about social media, we'll talk about forgiveness of some of the more complicated people in your past if we scale that to the entire world before the ai destroys us. And although the human race is lost to history, how do you think love wins over hate? [/INST] Well, I'd like to preface this by saying I tried to make pancakes the other </s><s>[INST] day. Yes, [/INST] didn't work, but I'm happy to comment on this. So, uh, basically, uh, I think like, I think most of the times that that I can think of that I've struggled. You know, it's uh can and the times that I've read about is it being unable to see the humanity in other people. And also even in sometimes our enemies and the people that have done awful things and you go, what would </s><s>[INST] allow people to [/INST] do this, that or the other? And that doesn't forgive what they've done depending upon. You know, some things are forgivable, some things are less so. But you want to understand why it's like to our knowledge, demons don't populate our world. Neither do like literal angels walking around being actually perfect A lot of times the things that I find it deeply amusing watching, you know, people hoisted by their own petard on twitter, even though it's gross and it's really unproductive. It's actually like equal parts amusing and like awful because you're not you're not happy that someone's being raked over the coals particularly unjustifiably. But it is funny when it's the exact same thing. They were raking others over the coals for not like a week or two prior and that's happened repeatedly and will continue to happen. And I guess I would say as you mentioned, you know, a prior, you know, like a recognition of the humanity of others of that. All of us make mistakes that it's difficult to understand intention. I've had arguments with close friends of mine over text message, we're both of us ended up super pissed because we were completely misreading what the tone the intention of what the other person was doing. And even if I was reading it correctly, which I wasn't, it's so easy to ascribe the most negative possible. You know, either the least charitable assessment of what they're doing. And I think that that's such a dangerous way to live your life. And it's also just a fruitless way to live your life. You know, it's one thing to go, hey, why did you do that? I was pissed. Did you, what did you do? You just, you did that to make yourself feel better Like you're damn right. I did. And have I done that plenty of times my life? Yeah, I would lie if I said that, I didn't, you know, why did why did you punch that guy in the face? He was going crazy at me and hit me and I asked him to stop and then I gave warning and I'd put him on his ask, I'm like, no, I'm not sorry. But then looking back now with years to sit on him, like do I understand why I did what I did absolutely what I like to respond differently now. Yeah. You know, and it doesn't mean that I think plenty of things that people do are understandable doesn't mean understandable, doesn't mean correct, understandable, doesn't mean that you go, yeah, that's great. You know, I could I could see someone doing such a thing, but I guess just record, trying to understand and see the humanity and others because if I can't see the humanity and others, how can I see it in myself. And also, you know, how am I meant to interact with everyone as you said, whether, you know, even if we're a society of individuals for at least for the time being, hopefully, you know in perpetuity we still come together as a whole and watching. It's weird like you said, it's, it's if I only ask why once I start with stay out of my way and I'll stay out of yours, leave me the alone. You're like, okay, that's fine Ryan, but that's easy for you to say living in a society that doesn't actually function like that. So it's a little bit cheap. But if I recognize that that's step one is I don't hurt you and you don't hurt me, but then we go, but how can I help you? That's step two and then it goes way beyond that and a lot further than I thought about it. But I guess what I would just say is again, recognition of the humanity and others and that we all have different strengths, we all have different witnesses and you can never really be sure where the other person is coming from. But if we approach things charitably as charitably as we would hope others would approach us. I think we'll do a lot better. And I guess one thing that I read that I like that I thought was accurate and unfortunately disappointing was everyone is a great, uh, you know, jury or read their, I'm sorry, great lawyer for themselves and a judge for others. And I think that's a terrible way to live life even if it's an understandable one. Yeah, </s><s>[INST] uh, probably sleeping. That is the right way to live being uh, being constantly judgmental and yourself and uh defender of others. And that results ultimately in the interaction that de escalates versus escalates, right? Yeah. [/INST] And you can, you can, we can all live in a world like that. And sometimes you're like, hey man, people that deserve punishment won't get it. Like, okay, what do they say? Better to have? You know, 10 guilty people go free than one innocent person, you know, burn. And ultimately that is, I think that is a better world than the other way around. </s>

<s>[INST] you just briefly, because you used this term a lot and be nice to try to get a little more color to it, which is interception and extra reception. Uh what are we exactly talking about? So like what's included in each category? And how much overlap is there [/INST] into reception? Would be uh an awareness of anything that's within the confines or on the surface of my skin that I'm sensing </s><s>[INST] literally physiological, [/INST] physiological, like within the boundaries of my skin. And probably touch to the skin as well. Extra reception would be perception of anything that's X. Beyond the reach of my skin. So that that bottle of water um a sent um a sound although and this can change dramatically actually if you have headphones in you tend to hear things in your head if as opposed to a speaker in the room, there's actually the basis of ventriloquism. So there are beautiful experiments done by Greg reckon zone of at UC Davis looking at how auditory and visual cues are matched and we have an array of speakers and you can this will become obvious as I say it. But you know obviously the ventriloquist doesn't throw their voice, what they do is they direct your vision to a particular location and you think the sound is coming from that location. And there are beautiful experiments that Greg and his colleagues have done where they suddenly introduce an auditory visual mismatch. And it freaks people out because you can actually make it seem from a perception standpoint as if the sound arrived from the corner of the room and hit you like physically and people will recoil. And so sounds aren't getting thrown across the room, they're still coming from the defined location, an array of speakers. But this is the way the brain creates these internal representations. And again, not to I don't want to go down a rabbit hole, but um I think as much as I'm sure the listeners appreciate this but you know, everything in the brain is an abstraction, right? I mean they're they're the sensory apparatus, there are the eyes and ears and nose and skin and tasting all that are taking information and with interception. Taking information from sensors inside the body. The enteric nervous system for the gut. I've got sensory neurons that integrate my liver um etcetera. Taking all that. And the brain is abstracting that in the same way that if I took a picture of your face and I handed it to you and I'd say that's you you'd say yeah that's me. But if I were an abstract artist I'd be doing a little bit more of what the brain does. Where if I took a pad and paper, maybe I could do this because I'm a terrible artist and I could just mix it up. And let's say I would make your eyes like water bottles but I flip them upside down and I'd start assigning fruits and objects to the different features of your face. And I showed you I say lex that's you say well that's not me. And I'd say no but that's my abstraction of you. But that's what the brain does. The space time relationship of the neurons that fire that encode your face have no resemblance to your face. Right? And I think people don't really I don't know if people have fully internalized that but the day that I and I'm not sure I fully internalize that because it's weird to think about. But all neurons can do is fire in space and in time. Different neurons in different sequences perhaps with different intensities. It's not clear the action potential is all or none. Although people, neuroscientists don't like to talk about that, even though it's been published in nature a couple times, the action potential for a given neuron doesn't always have the exact same waveform people. It's in all the textbooks, but you can modify that way for </s><s>[INST] Well, I mean, there's a lot of fascinating stuff with with neuroscience about the fuzziness of all the uh of the transfer of information from neuron to neuron. I mean, we certainly touch upon it every time. We had all tried to think about the difference between artificial neural networks and biological neural networks. But can we maybe linger a little bit on this uh on the circuitry that you're getting at? So the brain is just a bunch of stuff firing and it forms abstractions that are fascinating and beautiful, like layers upon, layers upon layers of abstraction. And I think it just like when you're programming, I'm programming in python, it's uh it's all inspiring to think that underneath it all, it ends up being zeros and ones and the computer doesn't know about no stupid python or windows or Linux exit? It only knows about the zeros and ones in the same way with the brain. Is there something interesting to you are fundamental to you about the circuitry of the brain that allows for the magic that's in our mind to emerge? How much do we understand? I mean, maybe even focusing on the vision system. Is there something specific about the structure of the vision system, the circuitry of it that uh allows for the complexity of the vision system to emerge? Or is it all just a complete chaotic mess that we don't understand? [/INST] It's definitely not all a chaotic mess that we don't understand if we're talking about vision and that's not because I'm a vision scientist, ballistic division division. Well, because in the beauty of the visual system, the reason David Huebel and torn some weasel on the Nobel prize. It was because they were brilliant and forward thinking and adventurous and all that good stuff. But the reason that the visual system is such a great model for addressing these kinds of questions and other systems are hard is we can control the stimulate, we can adjust spatial frequency. How fine the grading czar, thick grading thin greetings, we can just temporal frequency, how fast things are moving. We can use cohen isolating stimuli we can use. There's so many things that you can do in a controlled way. Whereas if we're talking about cognitive encoding, like they, you know, encoding the space of concepts or something, you know, I you know, I like you if I may our am drawn to the big questions in neuroscience but I confess in part because of some good advice I got early in my career and in part because I'm not perhaps smart enough to go after the really high level stuff. I also like to address things that are tractable and I want, you know, we need to we need to address what we can stand to make some ground on at a given </s>

<s>[INST] it's like I've been there a thousand times already. So not the actual competition, but even leading up to it, [/INST] stepping on the map, all the walk towards it, all that? All that stuff. I'll do the same exact warmup for weeks on end until my competition day comes. That way, when I compete, </s><s>[INST] I'm just like, oh, it's another Tuesday at practice. What about you, Craig? [/INST] How do you prepare mentally for a tournament like ADCC? I push it completely out of my mind. Don't even think about it. Try to avoid any visualization, any rituals, warmups, anything like that. Block it out until the last second, yeah. Try not to think about it. I just go to training to have fun, learn a bit. So I try to approach competition the exact same way. I don't warm up training, do very little warmup for competition. Uh-huh, and you just step on the mat? Step on the mat. My philosophy is there's no warmups on the street. We're so vastly different. All right, so you legit don't warm up. No, I probably should now I'm 31, but I would just like in the gym, take it easy the first round. You know, like if I look around the room and Nicky Ryan's down, I might go, all right, we'll have an easier first round today. Jump, jump, jump. </s><s>[INST] So even for like the most high stakes matches, you try to push it out. Yeah, I didn't even think about it. What about like all the social, like Instagram posts you have to do about that match? You just make a joke out of it and kind of. [/INST] Yeah, I mean, it's kind of pretty silly, you know? We're just wrestling each other, you know? We put the meaning into it, but to someone that doesn't feel this sport, </s><s>[INST] it looks stupid. Well, all of human existence is pretty silly. Like what are we doing? None of us really know what's going on. We kind of have sex to reproduce. We get hungry, we eat, and then we're all chasing money in cars and whatever the hell in a capitalist society, or we worship a dictator in a authoritarian regime. Yeah, and then we get off on, we let power abuse us and then we just murder others because we get off on it. Yeah, and then eventually all of us will die because the sun will run out of energy because colonizing other planets is very difficult. So none of it matters. It's a good philosophy. It's pretty good. That's exactly what I was saying. [/INST] How does the sun run out of energy? </s><s>[INST] Call me there. It's like a, it's a nuclear fusion engine [/INST] and it eventually burns up. Like when you get tired of training. Yeah. It's never happened. I try to get tired. I was like, dude, it's not working. I'm tired. </s><s>[INST] I was like, dude, it's not. All right, cool. So you legit don't care about losing. [/INST] It doesn't weigh heavy on you. I try not to list, like if I win, I try to block out all the compliments, all the niceties and stuff. So I try to do the same with losing. It's happened, move on to the next one, you know? Don't dwell on it too much. And sometimes make a joke out of it. Yeah, exactly. You know, losing, yeah. With the right joke, </s><s>[INST] we can make money off of the event that's transpired. That's just transpired. That's what's most important. Excellent. Thank you. I have a bunch of your merch. [/INST] Oh, nice. This one's the Jordan Burroughs ripoff. </s><s>[INST] All I see is silver. The way pronounced borrow is very, very sexy. Okay. [/INST] I throw lines at people and I try to gauge their reaction. Like sometimes I'll say something to Nicky and I'll be like, all right, that's probably crossing the line. You know what I mean? </s><s>[INST] We'll turn it down to the public, the public. So yeah, yeah, yeah. So it's not just, right. [/INST] You have to think because it's crossing the line. Yeah, yeah. I get as close to it as possible. Yeah. </s><s>[INST] I feel like you can't really cross it. And then cross it just a little bit. Just a little bit, yeah. Okay. Speaking of which, you said that I'm Switzerland in World War II since I'm friends with both you and Gordon and John. Very rich country. Are you a Hitler or a Stalin, by the way, in this analogy? Would you like to be Hitler or Stalin? [/INST] And should you make a t-shirt out of it or? Very rich country. I mean, a Nazi t-shirt, I don't know how well that sells. Yeah. I think it would, you know, </s><s>[INST] I think that let's brainstorm on this one offline. I think since Hitler lost. So you got second place in World War II. That's true, that's true. I think that makes you Hitler. Anyway, to the degree that you can, can you tell the story of how the time you've had [/INST] with the Donahue Death Squad and why you split the tape? That makes you Hitler. I competed against Gordon for ADCC and the EBI in 2017. And I remember I competed against him at ADCC and then we had the EBI event. And then I had a Kasai. I used to compete all the time, every week. I wouldn't even do the preparation or anything. I'd just be like trying to do seminars, make money, and then jump in and compete. And I remember I showed up to Kasai after I faced him twice and they were like four locker rooms and they put me with all the DDS guys. It was just me and all of DDS. And I think we had competed the weekend before. So I thought it was going to be super awkward, but it was actually pretty chill. And the Kasai was in New York and they suggested to come train that week. So I came trained, hung out with them a bit. Ultimately, the goal was to move to America and join a bigger team just because that flight to Australia is death. Australia is so far away from everywhere. It's kind of like, not realistic to base yourself in Australia when all the tournaments are in America. And then I went and trained with the guys and they just had a massive, massively deep talent pool in that room. Like show up to like a, meant to be 7 a.m., actual 8 a.m. class on Brazilian time. And there'd be like a hundred people in there, maybe, I don't know how many black belts, but a ton of elite guys. And I was coming from Australia, training with Lachlan Giles. But really that room was pretty shallow and like most people had serious jobs and stuff. So it was like, basically me just training with Lachlan, maybe a couple of other guys. And then to go to New York and have access to a wide array of training partners and guys that are training twice each day, I feel like that's what you really need. You need people that can train as much as you are. Work together. To get humbled in that room at first. For sure, because my style of the time was basically a rip off version of what they were doing. Leg locks came in. I remember just watching Eddie Cummings nonstop and just seeing this guy rip people's legs off. And I was like, you know what? That's probably a good move. You know, that looks like an easier path to victory than trying to beat these guys at what they're good at already, you know? My philosophy at the time was, if it's bothering old Brazilians, it's bothering them for a reason. It's probably effective. And that's the path I took to sort of try to rip off their moves. And then obviously to go into that room, try to do them to them, </s>

<s>[INST] Thanks for listening to this conversation with Michael Mina and thank you to our sponsors Brave, a fast browser that feels like chrome but has more privacy preserving features. I thought of Green's the only one drink that I start every day with to cover all my nutritional bases express VPN the VPN, I've used for many years to protect my privacy on the internet and cash up the app. I used to send money to friends. Please check out the sponsors in the description to get a discount and to support this podcast. If you enjoy this thing, subscribe on YouTube, review it with five stars on Apple podcast following Spotify supporter on Patreon. I'll connect with me on twitter, elects Friedman and now let me leave you with some words from teddy Roosevelt. It is not the critic who counts, not the man who points out how the strong man stumbles or where the doer of deeds could have done them better. The credit belongs to the man who actually is in the arena, whose face is marred by dust and sweat and blood, who strives valiantly. Who cares who comes short again and again because there is no effort without error and shortcoming. But who does actually strive to do the deeds? Who knows great enthusiasms, the great devotions, who spends himself in a worthy cause, who at the best knows in the end the triumph of high achievement and who at the worst, if he fails at least fails while daring greatly, so that his place shall never be with those cold and timid souls who neither know victory nor defeat. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] yeah, can I ask you for advice to me and to others about what's it take to build a successful startup? [/INST] I don't know. I haven't done that. Talk to someone who did that. </s><s>[INST] Well, if you know, uh, this is like another book of years, I'll buy for $67 I suppose. Uh, so there's [/INST] Uh, one of these days will sell out. Yeah, that's right. Jailbreaks are going to be a dollar and books are going to be 67 </s><s>[INST] How I, how I jail broke the iphone by George shots. That's right, [/INST] how I jailbreak the iphone and you can do, you can do </s><s>[INST] in [/INST] 21 days. </s><s>[INST] That's right. Oh God. Okay. Can't wait, but quite, so you have an introspective. You have built a very unique company. I mean not you, but you and others, but I don't know. Um, there's no, there's nothing you have an interest but you haven't really sat down and thought about like, well like if you and I were having a bunch of we're having some beers and you're seeing that I'm depressed and whatever I'm struggling. There's no advice you can give. [/INST] I mean more beer, more beer. Uh Yeah, I think it's all very like situation dependent. Um Here's okay if I can give a generic piece of advice. It's the technology always wins, the better. Technology always wins and lying always loses build technology and don't lie, </s><s>[INST] I'm with you. I agree very much long run, long run. It's the long run. You know [/INST] what? The market can remain irrational longer than you can remain solvent. </s><s>[INST] Well, this is this is an interesting point because I ethically and just as a human belief that like like hype and smoking mirrors is not at any stage of the company is a good strategy. I mean there's some like you know pr magic kind of like you know, you want to do [/INST] product if there's a call to action if there's like a call to action, like buy my new GPU, look at it, it takes up three slots and it's this big, it's huge by my GPU. But like </s><s>[INST] if you look at, you know, especially in that Ai space broadly but autonomous vehicles, like you can raise a huge amount of money on nothing and the question to me is like I'm against that. I'll never be part of that. I don't think, I hope not willingly not. But like is there something to be said to ah essentially lying to raise money? Like fake it till you make it kind of thing. [/INST] I mean this is Billy Mcfarland, the fire festival. Like we all, we all experienced, uh, you know what happens with that? No, no, don't fake it till you make it be honest and hope you make it the whole way the technology wins, right? The technology wins. And like there is, I'm not, I usually like to anti hype, you know, that's, that's a Slavic a PSS reference. But um, hype isn't necessarily bad. I loved camping out for the iphones. Um, you know, and as long as the hype is backed by like substance, as long as it's backed by something I can actually buy. And like it's real, the hype is great and it's a great feeling. It's when the hype is backed by lies. That it's a bad feeling. </s><s>[INST] A lot of people call Elon musk a fraud. How could it be a fraud? I've noticed this, this kind of interesting effect, which is, he does tend to over promise and deliver, uh, what's, what's the better way to phrase? It promised a timeline that he doesn't deliver on, He delivers much later on. What do you think about that? Because I do that. I think that's a programmer thing too. I do that as well. You think that's a really bad thing to do is is that okay? So I think that's [/INST] again, as long as like you're working toward it and you're going to deliver on and it's not too far off. Right? Right? Like, like, you know, the whole, the whole autonomous vehicle thing? It's like, I mean, I still think Tesla is on track to beat us. I still think even with their, even with their missteps, they have advantages. We don't have. Um, you know, illness is better than me at like marshaling massive amounts of resources. So, you know, I still think given the fact that maybe make some wrong decisions, they'll end up winning and like, it's fine to hype it if you're actually gonna win, right? Like if Elon says, look, we're gonna be landing rockets back on earth in a year and it takes four. Like, you know, he landed a rocket back on earth and he was working toward it the whole time. I think there's some amount of like, I think when it becomes wrong is if you know, you're not going to meet that deadline, if you're lying. </s><s>[INST] Yeah, that's brilliantly put like, this is what people don't, I understand. I think like Ellen believes everything he says he does, [/INST] as far as I can tell he </s><s>[INST] does. And I detected that in myself to like if I it's only bullshit if you if you're like conscious of yourself lying. Yeah, [/INST] I think so, yeah. No, you can't take that to such an extreme, right? Like in a way, I think maybe Billy Mcfarland believed everything he said to </s><s>[INST] right? That's how you started calling and everybody kills themselves. Yeah. [/INST] Like it's, you need, you need, if there's like some factor on it, it's fine and you need some people to like, you know, keep you in check. But like if you deliver on most of the things you say and just the timelines are off. </s>

<s>[INST] look at my interviews. Yeah. I think it's kind of productive. Yeah. So what about more prescient for me? I can't believe I'm walking to this fire for no good reason whatsoever. But Anthony Fauci. So let me tell you why I care about Anthony Fauci because I care a lot about science and the way science is viewed in society. And um, not to put it at the at the feet of this one person, but I him and certain members of the scientific community that was responsible for managing the response to covid I think are somewhat or entirely responsible for a significant decrease in trust in science. Yes. No question. In the past couple of years there was [/INST] a poll that just came out this week that said the numbers just collapsed </s><s>[INST] and if you don't blame him for it, I personally blame him for not um improving the problem. And so there's definitely would be harsh conversation there to be had and I think I wanna have it. But how do you do it? It's tough. Yeah. Because you know, again politicians, there's political answers. If you, if they get too frustrated too quickly, they will not explore these difficult things with you, they'll just shut down. But then if you say too many nice things because I I should also say Anthony Fauci is an incredible career. Like there's several hours worth of conversation to be had about how amazing of a person he is. Well, I [/INST] would also be curious about the AIDS stuff because that's something gets criticized about and I wouldn't come out aggressively. I would say let's set the record straight. This is on the criticism you get blah blah blah. Your role in the AIDS crisis. Let's talk about this. And this is something that is important part of american history. There was a pandemic and but it was localized to certain populations and that part of that population at the first at least was pretty much told goodbye and good luck you're gonna have to deal with this. So how did you deal with that? I mean, were you scared of getting AIDS? You know, so on and so forth. But also there was that comment when and correct me if I'm wrong. I'm not a Fauci expert when he basically they told people not to wear masks or they lied about it to some extent because they said that people are going to run out of them or something like that and they admitted they were being inaccurate, I would nail him on that and like, let's address this, were you being dishonest? Is there sometimes when it's important to be dishonest in service of whatever? Also, I would ask him how as someone who's not a politician, whether his level of fame and adulation has gotten to his head. How do you have a perspective when and how does it feel when a sitting senator tells you that you should be imprisoned? Do you think Ted Cruz means it or you think Ted Cruz is just playing to his base? </s><s>[INST] Yeah, I like the same one, I would love to sneak up. I mean that's got question applies to you too. The question applies to me when you start getting more fame or money or power, are you aware of how that changed you and like explore that? Like how has that changed you? Like if you like in the privacy of your mind, Michael malice, like how did you change now that you've gotten more attention? Let's say, you know, or even the success of the book, like, is it like, take, take yourself back to the, you know, you talk about the 20 uh early twenties, the mid twenties person. How are you different from that person? Are you the same person? Are you totally different? That's an interesting thought is Putin the same person in 2020 as he was in 2010 and then in 2000 it's ah it's a nontrivial almost like and then [/INST] the other thing was actually is this is a dynamic system. Like on the one hand he's gonna want to say we got it right every time. Right. But then how is that even possible when you're dealing with the evolving unknown dynamic situation? When did you guys get it wrong? Did that result in lives lost? Do you feel guilty about that? </s><s>[INST] I mean the big problem with the masks, the changing of mind and on the mask is the arrogance and how it was communicated to me a lot of this goes on to uh how things are communicated. It's like it's obvious that you need to change your mind when you get new information or sometimes yeah, you take policies that are like we know the truth but we're going to lie for a particular reason. Like you have good intentions but if you're not able to communicate that later, like we made a mistake [/INST] or even ask him, can you understand how a rational person might choose not to get vaccinated? </s><s>[INST] Yes, yes. [/INST] Yes. And if you can't steal man that then then that's a situation </s><s>[INST] that's a good test and I've tried and some people succeed and some people fail is the ability to really steal man. The other understand that somebody would be hesitant about taking the vaccine. Yeah. It's a giant mess man. Uh this podcasting is is just a fun little conversation but it also has a responsibility. I don't know. I don't know how joe does it. [/INST] I don't think joe cares as much as you do. It's more fun for him in a sense. And he's less concerned about the I mean he's not unconcerned with the cultural impact but for him it's just more growing out. Yeah. Like he doesn't do as much property doesn't come in with three pages single spaced you. No questions. Yeah. And that's why he's talking to blair white for 10 minutes about whether sharks lay eggs without knowing </s>

<s>[INST] adults five or six. Go on. Father Friedman. You've had three wines tonight. [/INST] I get confused with a brother. Five or six. No, I'm trying to get you to laugh, but you're not gonna laugh. But anyway, no, it's true. So somewhere you lose 30, you know, to 50%. </s><s>[INST] I'm not entertained. But that's because I'm an adult. No, and then I do remember there's some distribution in those studies with the happier adults smile a little more, [/INST] but still the kids blow them out of the water. Just crushing. So can you, is it, or should, in other words, should we invest our energy in getting the half-life decay constant stretched out more for curiosity for kids? Or should we try to reset the dopamine hit and then, you know, I don't know. It's an open question. </s><s>[INST] Well, I think it goes to the day of foster wall, it's the key to life is to be unbearable. I think you could train this kind of thing, which is in every single situation. So like, which I think is at the core, at least this correlated with curiosity, is in every situation, try to find the exciting, the fascinating, like in every situation. You sitting at the, I don't know, waiting for something at a DMV or something like that. Find something that excites you, like a thought, like watch people, or start to think about, well, I wonder how many people have to go to the DMV every day. And then try to go into the pothead mode of thinking like, wow, isn't this weird that there's a bunch of people that are having to get a stamp of approval from the government to drive their cars? And then there's millions of cars driving every day. Or like, how could I do this better? [/INST] Maybe there's something, or like how could I do this better? Maybe it's some blockchain and they could like Vintransf... Yeah, exactly. No, that is a good, </s><s>[INST] that is... And yeah, exactly. Yeah, no, that is a good. And then every situation, I think if you rigorously like just practice that at a young age, I think you can learn that. Because sometimes people ask me for advice and to do this thing or that thing is, I think you at the core really have to have this muscle of finding the awesomeness in everything. Because if you're able to find the awesomeness in everything, like whatever journey you take, whatever weird me entering that you take through life is going to be productive, is gonna end up in a great place. So that muscle is at the core of it. I guess curiosity is central to that. But you didn't win the Nobel Prize. The team of Bicep that led the Bicep II didn't win the Nobel Prize because of some space dust. That's right. It's like schmutz. Which one is the moon? [/INST] Which one is? That one's the dust. </s><s>[INST] The space dust, yeah. The space dust. What are we looking at? [/INST] So why is space dust the villain of this whole story? Well, it's funny, I wrote these books and I don't know about you, but when you get all these books, I'm sure you get books, people sending books. They always come in these dust jackets, right? I was like, what the hell is a dust jacket? How much dust is raining down at any moment? I mean, this is immaculate. This room is Russian tidiness galore. But in a normal household, how much dust is raining down? It's not really until I wrote a book. And I realized, I'm writing a story about the origin of the universe. Now the prologue to the cosmos and dust is going to cover this story. It was actually, it's actually more a story about astrophysics and cosmology than dust. And this is the link between the cosmological and the astrophysical. So what does that mean? So astrophysics is broadly speaking, the study of physical phenomena manifest in the heavens, astronomical phenomena. Cosmology is concerned with the origin, evolution, composition of the universe as a whole, but it's not really concerned with stars, galaxies, and planets per se, other than how they might help us measure the Hubble constant, the density of the universe, the neutrino content, et cetera, et cetera. So we tend, have a tendency to kind of look a little bit, you know, they're like, not all astronomers or astrophysicists are equal. They're all equal, but some are more equal than others. So we have kind of a prejudice, a little swagger, right? And cosmologists are studying, you know, we're using Einstein, we're not using like, you know, Boltzmann, we're thinking of the biggest possible pictures. In so doing, you can actually become blinded to otherwise obvious effects that people, you know, would have not overlooked. In our case, when we sought out the signal, we were using the photons that make up this primordial heat bath that surrounds the universe, luckily only at three degrees Kelvin, approximately. We're using those as a type of film onto which gravitational waves will reverberate it, make them oscillate preferentially in a polarized way, and then we can use our polarized sunglasses, but in a microwave format, to detect the characteristic twofold symmetry pattern of under rotation. That's the technical way that we undergo it. I mean, there's a lot more to it. But there are more than one thing that can mimic exactly that signal. First of all, when you look at the signal, the signal if inflation took place, big if, but if it took place, the signal would be about one or two parts per billion of the CMB temperature itself. So a few nano Kelvin, the CMB is a few Kelvin, the signal from these B-modes would be a few nano Kelvin. It's astonishing to think, Penzies and Wilson, 1965, measured something that's a billion times brighter, and that was what, 60 years ago? Let's call it 60 years ago, since they discovered it. Moore's law, you're more expert than that. Let's call it every two years. So you're talking about like two to the 30th power doubling or something like that at that. So let's call it two to the 20th or something like that. So that's like only two to the 10th is a thousand, all right, correct my math, I'm wrong. Two to the 20th is a million, right? Two to the 30th is a billion. So we're outpacing Moore's law in terms of the sensitivity of our instruments to detect these feeble signals from the cosmos. And they don't have to deal with, on the semiconductor fabric factory in Santa Clara, California, they don't have to deal with like, meteorites and things like coming into the laboratory, it's a clean room, it's pristine, they can control everything about it, right? We can't control the cosmos. And the cosmos is literally littered with particles of schmutz of failed planets, asteroids, meteoroids, things that didn't coalesce to make either the earth, the moon, the planet Jupiter or its moons or get sucked into them and make craters on them, et cetera, et cetera. The rest of it is falling and it comes in a power spectrum. There's very few, thank God, Chicxulub sized impact or progenitors that will take out all life on earth. But there's extremely large number of tiny dust particles and microscopic grains. And then there's a fair number of intermediate sized particles. It turns out this little guy here is the end product of a collapsing star that explodes in what's called a supernova, type two supernova. So stars spend most of their life using helium nuclei protons into, and neutrons into helium nuclei. And then from there it can make other things like beryllium and briefly make beryllium and carbon, nitrogen, oxygen, all the way up until it tries to make iron and nickel. Iron and nickel are endothermic. It takes more energy than gets liberated to make an atom of iron. When that happens, there's no longer enough heat supplying pressure to resist the gravitational collapse of the material that was produced earlier. So the star form is gonna go inside out. That's how scientists discovered helium was discovered on the sun. I don't know, did you know that's why it's called helium? Yeah, they went there at night. And. Oh, well done. They went there at night. Now, helium means helioses, the God of the sun. It was discovered in its spectrum from observations of the telescope like 150 years ago. It wasn't discovered like when oxygen and iron was discovered. </s>

<s>[INST] I think bobby say that character opened up for bobby. [/INST] Yeah, but he said I have to do it as myself too, I think in that podcast he's like, okay you're gonna come with me and open for me and brea but you have to do as yourself </s><s>[INST] that [/INST] it did and I did the character uh you know who's a character I came up with on 10 minute podcast, he's just this comedian, right? He calls himself an open mic veteran, you know, he's been doing open mics forever and so I did it opening up for bobby and he's like you have to do some of it as yourself, so I just kind of did this bit where I would do some of his jokes and then I would take lee leon silly, I gotta fucking wig on and I take the wig off and I go and as myself I start explaining it, hello, my name is will see the reason that it's funny is because Arnold Schwarzenegger is always, he's in these movies and he's got the thick Austrian accent but he's like my name is Ben Williams, I'm a I'm a cop from colorado, no you're not. Uh and it doesn't make sense as the comedian character that I'm doing because that character doesn't do impersonations okay carrying on and then I put the wig back on and go back into this dumb thing and uh I don't think it was very good, but bobby required it in order for me to open for him, he's like you're not fucking doing it so I'm not going to get up on stage and not do we agreed I'll do it, but um having been up there just in you know whatever I've done it like a dozen fucking times, not a bunch of times, right, like nothing uh and you know these comedians that go up every night sometimes two times a night, it's I do, I will say I love performing in front of people when I get the chance but it's it's uh it's a specific thing that that uh that I I just I just I don't know, I got to go back to this, it's like the providing value, you know, I think great stand ups are fucking incredible. I'll go, you know when I've gone and watch stand up, you know, there's your friend you're going to see, but then there's this other person who really speaks to you, you know what I mean? And if you like one comedian tonight, that's a lot because a a a comedy club is like a fucking crazy restaurant where there's no menu and it's like, what would you like? There's nothing else like that. There's like, you don't go to like a, like music place, what do we got here? We got christian metal and there's some world music and then there's a reggae thing and it's all rammed in together. You don't go to a restaurant, I'd love a nice steak. Cool. First here's a bowl of Froot loops and then then we got you a and then this is our sushi tower and well, what about the steak? The steaks coming and then blah blah blah, oh no, the steak got bumped. So there's no steak, but here's a fucking shitty store bought cheesecake, you know, and that's what comedians are up against when they go into a place, it's like, I don't pair well with the poached salmon, you know, I'm chicken fingers. I already, I already am chicken fingers. So, you know these great comedians that are able to go up on a night where poached salmon goes up and then it's like funk. I'm, you are also spicy. I got some kick to me </s><s>[INST] for me even going to open mics. It could be a wonderful escape. [/INST] Yeah, </s><s>[INST] I mean just laughing, laughing together with others can make you don't know, it just feels really good [/INST] when we've done like, you know, like, and I hope to do it with dude see, but like live podcasts are fun in front of groups of people and you know, you talk to them afterwards and and take some pictures and man, they are, they forgot what the funk they got going on and a lot of them got to go back to work the next day. It's a Wednesday or thursday, you know? No, it's, it's, it's a lot of value. I'm fortunate enough to be busy doing my own bullshit. </s><s>[INST] What's the meaning of life? [/INST] Uh, what is </s><s>[INST] why? Why? Why, why why was [/INST] it the meaning of life? Wasn't, didn't they explain it at the end of meaning of life? I think it was Michael Palin that said, uh, try to get a walk in, be nice to neighbors even a fiber. Wasn't that the yeah, I think it's, I think </s><s>[INST] it's have a [/INST] bowl of brand in the morning and don't take yourself too seriously. </s><s>[INST] No, [/INST] Well No one gets out alive, I think is the herman </s><s>[INST] has one of my favorite writers, He's a nobel prize winner um, in a in a book called Steppenwolf says, learn what is to be taken seriously and laugh at the rest. [/INST] That's awesome. </s><s>[INST] What what's the percentage distribution on that? So how much of life should you take seriously? And then how much do you just laugh [/INST] at a man if you can laugh at everything, you're you're winning? But that's almost impossible. I think that there's there's uh and also could be quite irresponsible to do that. I take things, I take a lot of things way too seriously. I know that </s><s>[INST] uh I [/INST] do, I do, I really do, </s><s>[INST] People will be in part surprised by that, but I think that radiates from you [/INST] really? Yeah, I do, I don't take things way too fucking seriously sometimes. But </s><s>[INST] yeah, [/INST] we're gonna loosen the neck up. But no, I think that's that's really good. That's that's really good stuff. I I don't know what the percentage is to have a good life or or or or a happy healthy life, but, you know, for me, the meaning of life is getting to live it as long as you hope to, that's nice. And um and when you're when you lose someone or if perhaps you're faced with your own mortality, I think that puts that into perspective and but, you know, get </s>

<s>[INST] why detriment? [/INST] Because people want you to be something, It's more, you can believe it more. You know, it's like, it's </s><s>[INST] more authentic if you, if you never change, [/INST] I guess, I don't know. I mean, it's certainly it's not something I subscribed to because I create music that, but but I also grew up listening to a lot of different genres like cats. I would listen to like cat stevens and the next song would be like biggie and then the next song would be Nirvana. It was like, I like a lot of, and then Billy Joel and then Enya, It was like, you know what I mean? I was a product and I was a product of the 90s, which if you listen to 90s music, it really was a lot of reason that people say, well 90s were terrible. Like a lot of people say that I love the 90s were my favorite decade of music. Um was there was a lot of genre hopping and I don't know, I love that </s><s>[INST] 90s had the boy bands and it had Pearl Jam and Nirvana [/INST] And it had a lot of like women of the, was is probably my biggest influence um like kind of, that like angry rock, Women of the nineties, like Lanus more set jagged little pill is one of my favorite records of all time. The lyrics were so intimate and um, I don't know if she was angry or not, sorry if she wasn't. Um, </s><s>[INST] but there was an anger to it. [/INST] There was angst, you know, it was like a penis and that in hip hop of the nineties influences me. And then my dad, so anything my dad listened to, which my dad didn't listen to me that my dad listened to like Harry nelson, the Beatles, Cat stevens, bob, Dylan paul, Simon, billy Joel? Um it was very much like singer songwriter, Do </s><s>[INST] you mind if we throughout this listen to a few songs because you mentioned here in this and, and I was actually um yesterday and the day before listening to a lot of his stuff and it's just like, damn, he's good and not as known as he should be. Like I was getting, do you mind if I play? [/INST] Yeah, I </s><s>[INST] don't know. Not to, not to open this conversation with a love song, [/INST] I would like that actually lex </s><s>[INST] but without You is an incredible song. [/INST] Oh man, that's yeah. </s><s>[INST] And the heartbreak in the, in the longing, [/INST] what he's the best to do it. In my opinion, in my opinion, he's the best to </s><s>[INST] do it vocal range [/INST] and just the </s><s>[INST] sadness of like [/INST] there's something I don't even want to talk over him because this is one of my favorite songs too. But I think people have a really good bullshit </s><s>[INST] indicator [/INST] and music in my opinion, whenever I meet a young artist and say, well let's I'm trying to make a new band and I want to do something like how to be successful. I really think understanding that people have a really good bullshit indicator is the most important part of being an artist. I'll explain what that means, at least to me. I think that in order to have success or be a leader or, or whether it's an art or anything, people need to believe that you believe what you're doing. Um I think the best actors really when they're doing their thing, it's like they, it's not acting, they're, they're in it and it's how they feel and they're expressing that sorrow or joy or whatever it is. Harry from me, harry nelson. He just, I just believe it, he could, he sings that and I feel it and whether he's the greatest bullshitter of all time or I don't think that's the case. I think he probably was singing that song to me. He just could transport himself to wherever he was. It's what makes a great live act, It's what makes a great song and someone could be the best actor and seeing that in the same timber, same eq, same compression, same everything and there's some unknown there that I, you know, I don't, I think hopefully it will be known at some point at some scientific thing, but there's something there that the energy or something that people can perceive it and say true or false and if it resonates is true, it's so much more meaningful and it lives on. And if it doesn't, that for me is what is good art or bad? Like for people to dispute over? Like, well, sonics should sound like that's silly to me it's like a song or, or even a painting, like it's just the truthfulness of it. </s><s>[INST] Yeah. The truly great art ghosts has to go to that place where you really are feeling it like you forget that you're being recorded. If you get there's an audience, you really are feeling it. Yeah. Which I totally agree with you. One of the things that I love about the internet is it's brought the bullshit detector of the masses um to power, which is beautiful because then the masses uplift the really authentic, [/INST] correct. </s>

<s>[INST] out of fear, fear, [/INST] fear and like you know, I was kind of nervous because I, you know, there's a whole week and it was anticipating coming here and I watched the mark normand one, I watched the Yannis one to see you know how totally and last night my girlfriend just looked at me just goes, just show up. </s><s>[INST] Yeah, Carla knows who I am. [/INST] Do you think that first of all, let me ask you something? Yes. You think I have the day, you know how busy I'm to drive all the way over here to west Hollywood to do your thing, Why would I do that? Because we are well aware of who you are and we like you thank you God. And we want you on ours. I would love, I would love </s><s>[INST] that as a, I mean that's, that's, that's the reason I'm doing this is just to get in your pocket awesome. Uh yeah, it's funny because I just mentioned to you offline, I got a chance to talk to Oliver Stone and he asked me this thing, which is, you know, how many um listeners does this thing get all that kind of stuff And I don't even pay attention to that. So it's like, I just don't [/INST] a little bit. So you do don't, I </s><s>[INST] wrote extensions in my browser as well. I don't see the views, the number of views don't you [/INST] know that like some of your Youtube videos on interviews and stuff have over a million that </s><s>[INST] I know. I know, I know like loosely that like it bleeds through, but it's not part of my conscious like um thing I think about, I'm very, I've just seen it destroyed people's minds where they're no longer thinking creatively. They're not, they don't feel good if something they do doesn't get as much as attention as they thought it should. It just can destroy you even though it's good. It could be great stuff. You create that nobody everybody ignores. But it was still great. It is, it is still great and uh sort of letting that negatively affect your mind is, I don't know, I've seen it destroy people. So I'm very nervous about that. [/INST] It's like that old saying never live in the results. It's like if I, if I podcast to make, I'd like initially, honestly, when I did tiger belly, we made no money for the first couple of years, like, like not not enough to put a dent. I couldn't buy anything like, you know, nice or anything. Um, it was just side money, you know, I mean, I could buy some shoes once a month or whatever, right? And like I said before, um, I was, my career wasn't the shooter, right? So tiger belly wasn't like, this is gonna be the thing, you know, I mean, it was just something to do with my girlfriend creatively, you know, and it just so happens that it did do all these things for me, right? Um podcasting. But um, yeah, I never and still today, I don't do it for any of those things, you know, I do it because um, it's fun. </s><s>[INST] Yeah, [/INST] yeah, it is right. Yeah. </s><s>[INST] Let me ask you, since you say why you love Kalala, why do you love slash hey George George kimball, your producer, What's your favorite thing about him? Let's say that positive thing positive [/INST] this question because I, because, you know, it's like, you know, I don't wanna give them compliments, but you know, I'll try, </s><s>[INST] I'll [/INST] try. Um, </s><s>[INST] have you actually, I don't think you've publicly ever said anything. I don't [/INST] think I have either, so I'm gonna get I'm gonna give it a go, I'm gonna give it a go. You know, at the end of the day, when it comes to money, when it comes to responsibility, obviously this is a business now for you and me. It is, you know, it's it's a side business, but it's a business and um you want to be able to trust the people that are running it. And I have 100 trust in everything that he does in terms of financial things, in terms of technical things, in terms of all of it, you know, I mean merchandise and I have 100% belief in him, I and that's rare to find someone like that. Um Also at the end of the day, I know his heart and he really is a great guy. He, there's nothing about him, like for instance, you know, he was over the other day and I go, you know, I bought this keith wooden thing that some native man made and I don't know how to put it on the wall. So I just, you know, I go, hey can you, I figured this out and he goes, yeah, I got it, you know, I mean like he's just that guy, you know um he's also, but there is a part of me and this is probably wrong, but there's a part of me that feels like I kind of made him? </s><s>[INST] Yeah, he would be nothing without. [/INST] No, that's what I'm saying, I </s><s>[INST] heard it, that's [/INST] what I meant. </s><s>[INST] Okay, but that's not what you [/INST] said. It's probably wrong because he did all the things that he has in his life, he did on his own right, but still, for some reason </s><s>[INST] he'd be nothing without [/INST] you. But that's what I mean. So basically like, because when I met him, I was a part of this um Youtube studio called Maker Studios and he was just a producer there and that's how I met him and when he left Maker, he came to us and he wasn't a podcast producer and now he has this big company, he produces a bunch of podcasts, you know, and he has a bunch of employees and he has a nice business, you know, and I feel like I had a lot to do with it. </s>

<s>[INST] Why is random is good in this process? Why is the elasticity good? [/INST] Yeah. So, um, I'll give you simple answers, but in some sense, again, it's kind of amazing plasticity. Just uh, you know, particular features of a surface that could have hurt you if you were doing one thing, you know, deterministic lee won't hurt you because uh you know, by chance, you know, there's very little chance that you would get hurt. And um, you know, so, here stochastic city um you know, it's just kind of saves you from some of the particular features of surfaces that, um, you know, and in fact, if you think about uh, you know, surfaces that are discontinuous in the first derivative, like, you know, absolute value function, um you will go down and hit that point where there's non differential bility, right? And if you're running demasiado at that point, you can really do something bad, right? Where so Cassidy just means it's pretty unlikely that's gonna happen. You're gonna you're gonna hit that point. Um so, you know, it's again, not trivial analyzed, but um, especially in higher dimensions, also stood plasticity. Our intuition isn't very good about it, but it has properties that kind of are very appealing in high dimensions for kind of law of large number of reasons. Um, so it's, it's all part of the mathematics behind it. That's what's fun to work in the field, is that you get to try to understand this mathematics and um, but long story short, you know, partly empirically it was discovered stochastic gradient is very effective in theory kind of followed, I'd say um that, but I don't see that we're getting clearly out of that uh </s><s>[INST] what's the most beautiful, mysterious, a profound idea to you in optimization? [/INST] I don't know the most, but let me just say that, you know, Nesterov is work on Nesterov acceleration to me is pretty, pretty surprising and pretty deep. Um can you elaborate? Well, they're strong acceleration is just that uh I suppose that we are going to use gradients to move around in a space for the reasons, I've alluded to there there, there nice directions to move and suppose that I tell you that you're only allowed to use gradients you're not going to be allowed to use this local person that can only sense kind of a change in the surface. Um But I'm gonna give you a kind of a computer that's able to store all your previous gradients and so you start to learn some something about the surface. Um And I'm gonna restrict you to maybe move in the direction of like linear span of all the gradients. So you can kind of just moving some arbitrary direction. Right? So now we have a well defined mathematical complexity model. There's a certain classes of algorithms that can do that and there's a can't and we get asked for certain kinds of surfaces. How fast can you get down to the optima? So there's an answers to these. So for uh you know a smooth convex function there's an answer which is one over the number of steps squared, you will be within a ball of that size uh After after k steps um gradient descent in particular has a slower rate? It's one of her. Kay okay. Um So you could ask is gradient ascent actually even though we know it's a good algorithm is it the best algorithm? And the sense of the answer is no well well not clear yet because what one of our case score is a lower bound that's that's probably the best you can do what gradient is one. Okay but is there something better. And so I think it's a surprise to most, the Nesterov discovered a new algorithm That has got two pieces to it. It uses two gradients and uh puts those together in a certain kind of obscure way and uh the thing doesn't even move downhill all the time and sometimes goes back uphill um and if you're a physicist that kind of makes some sense, you're building up some momentum and that is kind of the right intuition, but that that intuition is not enough to understand kind of how to do it and why it works. Um but it does, it achieves one of our case squared and it has a mathematical structure and it's still kind of to this day, a lot of us are writing papers and trying to explore that and understand it. Um So there's lots of cool ideas and optimization but just kind of using gradients I think is number one that goes back, you know, 150 years. Um and then that stuff I think has made a major contribution with this idea. </s><s>[INST] So like you said, gradients themselves are, in some sense, mysterious. Yeah, they're not, they're not as trivial [/INST] as not as trivial, mathematical coordinate descent is more of a trivial when you just pick one of the coordinates, that's how that's how our human minds are, Human minds think and gradients are not that easy for a human mind to grapple with </s><s>[INST] an absurd question, but what is statistics? [/INST] So here is a little bit, it's somewhere between math and science and technology, It's somewhere in that context hole. So it's uh it's a set of principles that allow you to make inferences that have got some reason to be believed and also principles of how you make decisions where you can have some reason to believe you're not gonna make errors. Um So all of that requires some assumptions about what do you mean by an error? What do you mean by, you know the probabilities and um but you know, start after you start making some assumptions. You're led to uh conclusions that yes, I can guarantee that you know, you know if you do this in this way your probability making air will be small. Um your probability of continuing to not make errors over time will be small and uh probability found something that's real will be </s>

<s>[INST] I think it holds us back, takes us back from that truth. That there's a love that connects all of us and that if you remember about that love, it's all going to be okay. [/INST] I really hope it's going to be okay. Me too. </s><s>[INST] I believe it would be thank you so much for talking today Shannon, you're an incredible person. Thank you for everything you do and for everything you stand for and from everything from your text message to just who you are [/INST] and for this amazing conversation today Shannon, you're an incredible person. Thank you for everything you do. </s><s>[INST] Thank you. Thanks for listening to this conversation with Shannon Currie the support the podcasts. please check out our sponsors in the description. And now let me leave you with some more words from Charles Bukowski. Sometimes you climb out of bed in the morning and you think, I'm not going to make it. But you laugh inside, remembering all the times you felt that way. Thank you for listening. Hope to see you next time. [/INST] </s>

<s>[INST] Can I actually backtrack, listen I love love, OK. And, and there's a story uh that you fell in love with a stripper. I mean you have to tell the story. So how did you fall in love um with somebody, not, there's anything wrong with that profession, but it's, it's, it's romantic. It's like the true romance by the way. Great movie. [/INST] It's truly a great film. </s><s>[INST] Even even brad pitt who makes a brief appearance is genius. This is so much good acting there. Anyway. Uh, so tell me that love story. All right. So, you [/INST] know that, uh, like I said, I get from my dad, I get that fear of being abandoned. You know, I lied to my wife for nine years until she leaves. And um, I was in charleston south Carolina. And what happened was, I noticed that Susan, she was not coming to bed. Like, you know, she used to, she would stay up all night long and sometimes she'd go and be gone a few hours and everything else. And I'm like, well something's going on. And I passed by her computer and she would minimize the screens and I'm like, well, I got to figure out what the hell is going on. So put a key logger on her system </s><s>[INST] as any uh, anybody should in a relationship. [/INST] Absolutely, because you trust them, You know, why not? You </s><s>[INST] should be tracking all their movements, all their [/INST] Exactly. Exactly. Like I said, I was the control freak too. So I found out she'd been cheating on me and she was bad reason I justified, So I found out she was cheating on her, she was asleep when I found it out and I sat there looking at and I was like, well, shit. So I got up, walked in the bedroom, opened up the wardrobe, got a suitcase out, started putting her clothes in it. And she wakes up, she's like, where are you going? I'm like, I'm not. You are. Well, my, my bravado disappeared pretty quickly. I it took about a week of both of us crying and arguing and everything else. And she she finally left around. I went through this depression. I went, I was in charleston south south Carolina. I would just walk around the house, kind of stumbling in a daze. I realized I was getting suicidal and was smart enough to do something about it and picked up the phone book and that's where there's always this sense of humor. So I picked up the phone book. I'm going through the yellow pages. I'm like, psychologist, criminal psychologist, because I need </s><s>[INST] that [/INST] called this psychologist crying to her. I'm crying on the phone, told her everything. I'm just criminal. This is what's happened. She's like, come in now. So I go in, spill my guts. And uh, I saw her for about four months and I joke about it. It's true. She, she was trying to get me to stop breaking the law and to go into real estate. And I remember telling her, is there a difference. She was like, yes, there's a difference. So sorry for about four months. I was I was 34. I didn't start drinking until I was 34. I had never done drugs or anything else like that because my mom was an addict as well. So I was this guy, I always wanted to be in control, didn't want to, you know, lose control of myself. And uh I had never been to a strip club. So one night I was getting lonely. So I walked into the strip club actually, I was researching this strip club and it was joe's roundup in charleston south Carolina, joe's roundup little bitty hole in the wall stuff. I was Yeah, real classy. So, I walked in and I'm literally that guy man that fell in love with the first, the first stripper that he sees, She walks by. I'm like that one. </s><s>[INST] So [/INST] I didn't know I didn't know the strip club game again. Criminal, naive as hell. So, belly up at the bar order of the beer. I'm sitting there drinking it. She comes over to me And we started talking and she's like, would you like to get a bottle of champagne? And I was like, does does that mean going back or what? She's like, well, yeah, you need to do the bottle of going back. And I was like, sure, let's buy a bottle of champagne, $400 bottle of Korbel. So, I'm like, all right. And again, that bravado disappears pretty quickly, I can get back there and we talk for two hours and you know, nowadays, I don't understand that Most men who go to strip clubs, the strippers are their therapist most of the time. Alright. So I'm sitting there talking. We're talking. Of course she's, she's sizing me up. She's looking at the watch, she's like, what kind of car you drive? You know, everything else. And I'm like telling her I'm talking. And so at the end of the night, I'm like, it's really nice to me and she's like, it's so nice meeting you too. So I leave </s><s>[INST] you guys just [/INST] talked and talked </s><s>[INST] and there's no dance feeling of love and all that. [/INST] Yeah. So just talk. Just got along pretty good on my, I like her. I like her. So come back in a week later. I walk in and call her over and I was like, look, I said, I'm not, I said that was my first time at a strip club. I said, I don't know. I like you. I'd like to know you more. Would you like to go out to dinner? And she was like, yeah, I was like, where would you like to go? So she says Rudy john. And I was like, I don't know what it is. That's where we'll go. So I go back And I was had a theater buddy at that point in time because I was trying to get my life trying to get my life together. Uh J C was his name and I was like, I got a date. He's like, he got a date. I was like, yeah man, I got a date and he's like, okay, where are you going? I was like Rudy Giuliani and he's like, take your wallet. I'm like, yeah, he's like, take your wallet. It's like, all right. So we start doing the lunch and the dinner thing and I get to where I really like her. She's, I was 34, she was 23 and got along really well. Listen, had common interest in music and arts and stuff like that. She had, I mean a stereotypical, she was, she had graduated college with a degree in religious studies. </s>

<s>[INST] not a lot of people really understand. So you really, even for recreational competitors, you really need to have a gripping system. You need to understand the gripping system [/INST] if you want to win. Yeah, I mean if the goal is to go and compete, that's a different story. I don't have fun getting beat up or losing in competitions. I enjoy </s><s>[INST] the I don't even know if it's the winning or the losing. I don't I think this is what because I competed a lot in both judo and jiu jitsu and judo, it feels like because I didn't have a gripping system, it feels like you're not even playing judo against the good black belts, You're they're just they're not they're not even trying because they have to get a certain kind of grip and you just can't do anything and I don't have a good answer for that. I don't even know what I'm looking for. And so it's not even it's not even losing, it's it's like uh I don't know, it's like you didn't even show up to play is what it feels like and it's unfortunate. I think that is a big gap in knowledge actually in um judo schools is the gripping part [/INST] when you first go out to to do judo right, Your first thing you have to do is you have to grab your opponent right? And a lot of times you hear coaches, they get a grip, just take a grip. Well, sometimes if you take a grip, you're in a worse position than not having a grip at all. And that's what a lot of people don't understand, like if you hold the G in the wrong way, your opponent can attack you, but you can't attack him. So why would you ever do that grip If it's only to your detriment? Right, so that's and the way you grip does set up what attacks you can do as well. So that is a huge part and I'm not saying that you have to be 100% disciplined and only always out grip your opponent and only be able to throw those where you have a superior grip, I'm just saying that to be able to put the grips together with the throws and understand the movements is gonna make you that much ahead of the game. </s><s>[INST] So if we take a step to our previous discussion of going from zero to hero. So going from the early days through the teenage years to winning an olympic medal. So we mentioned a lot of training, the dedication of the training, the competing, what other elements are there at the mental side visualization, believing that you could perform at that level. Uh so what else can you say [/INST] about, I think that comes at the highest level, the visualization and the success that comes at the highest level, I think in the teen years, um there's the experience plays a huge role in getting to train with other people like as americans, we have to go train in europe, we have to feel the european style of, you know, we have to understand that physicality, they grip very differently, they put you in a very unorthodox positions and if you, if you don't know how to deal with that, you get thrown before you even have a chance to try your own throws, you know, so it takes a lot of, it takes a lot of that experience and understanding what's going on um and then you also need to get that physicality, you need to be physically strong and hard, I would say by doing all those rounds with the Europeans at the same time, you need to go to Asia and you need to train in Japan because you need to feel that free flowing judo for your technical, the technical side, I think that's one of the things that I was able to benefit from, my dad was a coach who said, listen, I've taken it as far as I can take you, I want you to go to the next level I want, and he sent me to, to England with NEal Adams who was an olympic silver medalist and was a world champion, had a great ground game and was good at gripping and actually did Tadatoshi, which is the throw I did, so, but I said I want to go learn from NEal and I ended up going to, To England probably 8-10 times in my career and spending a good amount of time. Their training at the Nail Adams Academy, um he's now the voice of judo neal Adams. </s><s>[INST] What do you make of that guy? Just a brief pause, he's like the, like morgan Freeman is the voice of like march of the penguins and any other nature documentary and NEal Adams is uh very few sports that have a NEal Adams, I would say, because he's legitimately maybe like joe Rogan is that for mixed martial arts, it's just like an exceptionally recognizable voice, He's really knowledgeable. Also, the passion is conveyed so well, like many times I'll watch just because he's talking so who is he? Since he got the chance to train with him to learn from him whose new Adams, [/INST] he's a great friend of mine, he is, he's a mentor, um like I said, I lived and trained at the nail Adams club in Coventry England since I was like 16 years old, I went and visited him for the first time, he's the one who originally taught me how to do jujitsu Tommy and the way that I do jujitsu Tommy. Um I trained with him, he was just retired. He was in his early 30s when I first went out there and you know, so I trained with him many times and over the years, he's he was a mentor, um great person, you know, cares cares about, people, cares about, you know, the sport of judo, um had a good little club that was a fitness club and you know, I had, it was, it was Judah, it was fitness. It, you know, used to go there. I'd show up at that place at like seven in the morning. And the first thing we would do is we'd go for a run and we need to be running mountains, what we'll be doing a five mile run or we'd be doing something at the park, we were doing sprints and buddy carries and all this stuff. And then at nine a.m. We have a technical session with neal Adams where he would, you know, for an hour and a half, we would drill techniques and learn positions and there was no random Rory, it was that sequential drilling that we talked about before, right where you're reinforcing your, your two or three attacks to set up your main attack or if you're on the ground, you're going through repetitions of certain movements. Um and then I'd spend all afternoon at the club, have lunch, I'd go do my weight training in the afternoon at that at that place. And then in the evening we would either do rendering training at the nail Adams club, We're all getting a car and we drive to another, another location, you know, and we go train at another club that might be an hour away and they'd be, you know, 50 bodies there to train with. And each night we'd go to a different dojo and so it would be all day at the club and I do that for like three weeks straight. You know, all we do is try to </s>

<s>[INST] So, on that note, so with the interactive ai do you tend to in your mind visualized ai as a singular system or is it as a collective, huge amount of systems interacting with each other? Like is the social interaction of us humans and of ai systems the fundamental fundamental to intelligence. [/INST] I think, well, certainly fundamental to our kind of intelligence, right? And I actually think it matters quite a bit. So the reason um the interactive ai part matters to me is because I don't this is going to sound simple, but I don't care whether a tree makes a sound when it falls and there's no one around because I don't think it matters right if there's no observer in some sense. And I think what's interesting about the way that we're intelligent is we're intelligent with other people, right? Or other things anyway, and we go out of our way to make other things intelligent. We're hardwired to like find intention, even whether there is no intensify, we anthropomorphize everything. We I think anyway, we we I think the interactive ai part is being intelligent and of myself in an ice in isolation isn't meaningless act in some sense. The correct answer is you have to be intelligent in the way that you interact others. It's also efficient because it allows you to learn faster because you can import from, you know, past history. Uh it also allows you to be efficient in the transmission of that. So we ask ourselves about me my intelligent clearly. I think so, but I'm also intelligent is a part of a larger species and group of people and we're trying to move the species forward as well. And so I think that notion of being intelligent with others is kind of the key thing because otherwise you come and you go and then it doesn't matter. And so that's why I care about that aspect of it and has lots of other implications. One is not just building something intelligent with others, but understanding that you can always communicate with those others, they have been in a room where there's a clock on the wall that you haven't seen, which means you have to spend an enormous amount of time communicating with one another constantly in order to figure out what the other what each other wants. Right? So I mean this is why people project right? You project your own intentions in your own reasons for doing things onto others as a way of understanding them so that you know, you know how to behave, but by the way you completely predictable person, I don't know how you're predictable. I don't know you well enough, but you probably eat the same five things over and over again or whatever it is that you do right? Uh I know I do, if I'm going to a new chinese restaurant, I will get general gals chicken because that's the thing, that's easier. I will get hot and sour soup, you know the people do the things that they do, but other people get the chicken and broccoli that can push this analogy way too far. The chicken and broccoli, I don't know what's wrong with those people, I don't know what's wrong with them either. They we have all had our trauma, so they get their chicken and broccoli and their egg drop soup or whatever. Um we got to communicate and it's gonna change, right? So it's not interactive uh is not just about learning to solve a problem or task, it's about having to adapt that over time, over a very long period of time and interacting with other people Who will themselves change. This is what we mean about things like adaptable models, right? That you have to have a model, that model is going to change. And by the way, it's not just the case that you're different from that person, but you're different from the person you were 15 minutes ago or certainly 15 years ago. And I have to assume that you're at least going to drift hopefully not too many discontinuities, but you're gonna you're gonna drift over time. And I have to have some mechanism for adapting to that as you and individual over time and across individuals over time. </s><s>[INST] On the topic of adaptive modeling. And you talk about lifelong learning, which is a, I think a topic that's understudied or maybe because nobody knows what to do with it. But like, you know, if you look at Alexa or most of our artificial intelligence systems that are primarily machine learning based systems or dialogue systems, all those kinds of things, they know very little about you in the sense of the life long learning sense that we learn as humans. We'll learn a lot about each other, not in the quantity effects, but like the temporarily rich set of information. That seems to like pick up the crumbs along the way that somehow seems to capture a person pretty well. Do you have any ideas how to uh how to do lifelong learning? Because it seems like most of the machine learning community does not [/INST] No. Well by the knowledge of the machine in our community not not spend a lot of time on lifelong learning. I don't I don't think they spend a lot of time on um learning period in the sense that they tend to be very task focused. Everybody is overfitting to whatever problem is they happen to have their over engineering their solutions to the task. Even the people and I think these people do are trying to solve the hard problem of transfer learning right? I'm gonna learn on one task and then the other time it's you still end up creating the task. You know, it's like looking for your keys where the light is because that's where the light is right? It's not because the keys have to be there. I mean one could argue that we tend to do this in general. We tend to kind of do it as a group. We tend to hill climb and get stuck in local Optima. Um And I think we do this in the small the small as well. I think it's very hard to do. Um Because like here's the hard thing about ai right? The hard thing about ai is that keeps changing on us, right? You know what is a Yeah is the you know the art and science of making computers act the way they do in the movies, right? That's what it is, right? But beyond that and they keep coming up with new movies and just right. Exactly. We are driven by this kind of need to sort of ineffable quality of who we are, which means that the moment you understand something is no longer a I. Right, Well, we understand this, that's just you take the derivative and you divide by two and then you average it out over time in the window, so therefore that's no longer A. I so the problem is unsolvable because it keeps kind of going away. This creates a kind of illusion which I don't think is an entire illusion of either. There's very simple task based things you can do very well and over engineer. There's all of a I and there's like nothing in the middle, like it's very hard to get from here to here and it's very hard to see how to get from here to hear. And I don't think that we've done a very good job of it because we get stuck trying to solve the small problem that's in front of myself included. I'm not gonna pretend that I'm better at this than anyone else. Um And of course all the incentives in academia um and an industry are set to make that very hard because you you have to get the next paper out, you have to get the next product out, you have to solve this problem. And it's very sort of naturally incremental and none of the the incentives are set up to allow you to take a huge risk unless you're already so well established, you can take that big risk. Um and if you're that well established that you can take that big risk, then you've probably spent much of your career taking these little risks relatively speaking. And so you have got a lifetime of experience telling you not to take that particular big risk. Right? So the whole system set up to make progress very slow. That's fine. It's just the way it is. But it does make this gap seem really big, which is my long way of saying, I don't have a great answer to it, except that stopped doing in equals one At least try to get an equal to and maybe in equal seven. So that you can say I'm gonna maybe T is a better variable here. I'm going to not just solve this problem to solve this problem. And another problem I'm not going to learn just on you, I'm gonna keep living out there in the world and just seeing what happens and we'll learn something as designers and our machine learning algorithms in our ai algorithms can learn as well, but unless you're willing to build a system which you're going to have lived for months at a time in an environment that is messy and chaotic, you cannot control, then you're never going to make progress in that direction. So I guess my answer to you is yes. My idea is that you should it's not no, it's yes. You should be deploying these things and making them live for months at a time and be okay with the fact it's going to take you five years to do this, not rerunning the same experiment over and over again and refining the machine so it's slightly better at whatever, but actually having it out there and living in the chaos of the world. Um and seeing what it's learning algorithm, say can learn what data structure can build and how it can go from there without that. You're going to be stuck at the moment. </s>

<s>[INST] the push and pull of our dance that we're doing, because then I'll just say in the old world, having come from the soviet union because you had one, a couple of networks than propaganda could be much more effective and then the government can overpower its people by telling you the truth and then uh starving millions and torturing millions and putting millions into camps and starting wars with the propaganda machine, allowing you to believe that you're actually doing good in the world with the internet. Because of all the quote unquote conspiracy theories, some of them are actually challenging the power centers, the very kind of power centers that a century ago would have led to the death of millions. So there's uh again, this double edged sword and I very much agree with you on the Ai side, it's it's often an intuition that people have that somehow ai will be used to maybe overpower people by certain select groups. And to me it's not at all obvious that that's the likely scenario. To me the likely scenario, especially just having observed the trajectory of technology is it will be used to empower people, will be used to extend the capabilities of uh individuals across the world because there's a lot of money to be made that way like improving people's lives. You can make a lot of money [/INST] I think that the the main the main thing that ai prostheses ai amplifiers will do for people is make it easier maybe even unavoidable for them to do good critical thinking. Um So pointing out logical fallacies, logical contradictions and so on in um things that they otherwise would just blithely believe um pointing out um essentially data which um they should take into consideration um if they really want to um um learn the truth about something and so on. So I think um doing not just educating in the sense of um pouring facts into people's heads but educating in the sense of arming people with the ability to do good critical thinking um is um enormously powerful. Um The education system that we have in the U. S. And worldwide generally don't do a good job of that. Um But um I believe that the ai the ai ai as will the A. I. S. Can and will in the same way that everyone can have their own um um Alexa or Siri or um google assistant or whatever. Um everyone will have this sort of cradle to grave assistant which we'll get to know you which you'll get to trust. It'll model you you'll model it. Um And um it'll call to your attention things which will in some sense make your life better easier. Um less um mistake ridden and so on. Less regret ridden um if you listen to listen to it. </s><s>[INST] Yeah, I'm in full agreement with you about this like space of technologies and I think it's super exciting and from my perspective, integrating emotional intelligence. So even things like friendship and companionship and love into those kinds of systems as opposed to helping you just grow intellectually as a human being, allow you to grow emotionally, which is ultimately what makes life amazing is to to sort of, you know, the old pursuit of happiness. So it's not just the pursuit of reason. The pursuit of happiness to the full spectrum. Well, let me uh sort of because you mentioned it so many fascinating things, let me jump back to the idea of automated reasoning. So the acquisition of new knowledge has been done in this very interesting way, but primarily by humans doing this. [/INST] Yes, you can think of monks in their cells in medieval europe, um you know, carefully illuminating manuscripts. So it's </s><s>[INST] a very difficult and an amazing process actually, because it allows you to truly ask the question about the in the white space, what is assumed. I think this exercise is um like very few people do this right. They just do it subconsciously they performed [/INST] by definition because because those pieces of alighted of omitted information of those missing steps as it were. Um are pieces of common sense. If you actually included all of them, it would it would almost be offensive or confusing to the reader. It's like why are they telling me all these? Of course I know that you know, all these things. Um and so uh so it's one of these things which almost by its very nature um has has almost never been explicitly written down anywhere because by the time you're old enough to talk to other people and so on. Um you know, if you survived to that age, presumably you already got pieces of common sense like um you know, if something causes you pain whenever you do it probably not a good idea to keep doing it. Uh </s><s>[INST] so what ideas do you have given, how difficult this step is, what ideas are there for, how to do it automatically without using humans or at least not, you know, doing like a large percentage of the work for humans and then humans only do the various high level supervisory work. [/INST] So we have in fact two directions were pushing on very, very heavily currently it's like or and one involves natural language understanding and the ability to read what people have explicitly written down and and to pull knowledge in that way. Um but the other is to build a series of knowledge editing tools, knowledge entry tools, knowledge um capture tools, knowledge testing tools and so on. I think of them as like user interface um suite of software tools. If you want something that will help people to more or less automatically expand and extend the system um in areas where for instance they want to build some, have it do some application or something like that. So I'll give you an example of one um which is something called abduction. So you've probably heard of like deduction, uh and um induction and so on, but abduction is unlike those, abduction is not sound um it's just useful, so for instance, um deductive lee if someone is out in the rain and they're going to get all wet and when they enter room they might be all wet and so on, so that's deduction, but if someone were to walk into the room right now and they were dripping wet, we would immediately look outside to say, oh, did it start to rain or something like that now, um why did we say, maybe it started to rain? That's not a sound logical inference, but it's certainly a reasonable um abducted um leap to say, well, one of the most common ways that a person would have gotten dripping wet is if they had gotten caught out in the rain or something like that. Um So um what what does that have to do with what we're talking about? So I suppose you're building one of these applications and the system gets some answer wrong, and you say, oh yeah, the answer to this question is um this one not the one you came up with, then what the system can do is it can use everything it already knows about common sense, general knowledge, the domain you've already been telling it about um and context like we talked about and so on and say, well here are um seven alternatives, each of which I believe is plausible given everything I already know. And if any of these seven things were true, I would have come up with the answer you just gave me instead of the wrong answer I came up with is one of these seven things true and then you the expert will look at those um seven things and say, oh yeah, number five is actually true and so without actually having to tinker down at the level of logical assertions and so on, um you'll be able to educate the system in the same way that you would help educate another person who you were trying to apprentice or something like that. </s>

<s>[INST] it out. I'm not I disagree with you but you need to look at the mirror and think like what what is it, is it uh maybe you need a mustache, I don't know but there's something about figuring out how to be a charismatic communicator in this and that that's the responsibility you said like finishing sentences with the L. O. L. It's painful for your soul. [/INST] That's just how somebody lets me know. I don't have to take their opinion seriously. </s><s>[INST] Yeah it's still the language the the way that people are communicating and you're swimming that way. If you have a big platform, I have a growing platform, it feels like this is the place to give, I [/INST] agree but we're gonna get swatted down? I </s><s>[INST] just don't think so, you're wrong, Why are you afraid of the big like [/INST] this? As I've studied it? Because I've studied, let me ask you a question lacks, I believe that every society is supposed to have a collection of what I call a break glass in case of emergency people. Yeah, these are people who are universally loved and trusted by your society. For example, David Attenborough, the great british naturalist and presenter uh, recently came on instagram. He's worried about the planet. And I said, you know, look, there's very few of these people left. Let's pay attention, find out what he has to say. Maybe maybe he's gonna be an ask, maybe he's gonna be in it and maybe he's gonna say wrong things. Don't know. Tell Me About Your Top 10 Universal American Heroes. This is not a </s><s>[INST] rhetorical question. No, [/INST] give me five. Everybody looks to that person and says, yep, the best of us, I'm not divisive, </s><s>[INST] well, everybody is an interesting concept. I mean, Elon musk is very divisive, [/INST] right? But I'm talking about overwhelmingly people would, would follow that person if that person gave a rousing intelligent speech that said, we must act now because we're in dire straits. </s><s>[INST] I think a lot of people fall in that category. For me, it would be uh in the, in the tech world, in the engineer? You almost like [/INST] your own mosque </s><s>[INST] the rock, I'm thinking like who is the most eloquent actor. So like you think celebrities. So [/INST] people platforms, </s><s>[INST] nobody well known, I believe like, yeah, so this goes to joe joe Rogan. Mhm [/INST] First two did not really impress me as being what I said, but okay, Ellen several years ago would have, </s><s>[INST] can you, can you try to [/INST] joe Rogan? Why </s><s>[INST] do they fail? Why does, [/INST] why lots of people treat joe Rogan as if he's some sort of right wing racist because they've never watched his program. They don't know who his friends, I don't know. </s><s>[INST] Oh, but when I thought you said everybody, I thought you meant a large enough people where a huge change can happen. Not actually literally everybody [/INST] because I mean people who have pulled up like people who have pulled off something where everybody is convinced that that person just deeply, I think I've told you this story before, but the one time I've seen the power of a figure like this, I mean very few times I've been in a large crowd and I've seen people just moved where they would do almost anything good, bad and different because they were primed. Um, one was a rolling stones concert. The other one was nelson Mandela coming to boston and man, you've never seen anything like this. You check out the photos from the banks of the Charles river when nelson Mandela came um, there are people that you need in your dark hours and we can't agree on who they are and as soon as they emerge, we tar them with shit. We get out the ship brunch. </s><s>[INST] I just disagree with it. So I think, what do we disagree about? I think it doesn't matter who it is. I think really good speeches are needed. And I think a [/INST] lot of them, I saw killer mike tried to give a good Yeah, you did well in Atlanta, right? Yeah. That was something very impressed. Yeah. Even killer mike immediately gets into this sell out or like </s><s>[INST] uh, yeah, but he, he didn't take up the responsibility. I would say he didn't of, of going bigger. So he was speaking to the community and he was on this particular moment. He's exceptional at it. And he was speaking to this particular moment. He didn't take it a step further, which is like giving the same speech but bigger than race bigger than this particular moment. But more about the, the american project. [/INST] You know, the guy who landed the plane in the Hudson? Yes. Yeah. </s><s>[INST] There you go. That's a good [/INST] example. That guy until we screw him up is the kind of thing that I'm talking about. Exactly. </s><s>[INST] Jack. Oh, maybe that's [/INST] another. Jack was pretty good. Jacko is pretty good. I can't really tell us. He's a democrat as a republican. I don't know. He's an american. That's for damn sure. And I think there's a lot of fun and then, you know, I think Jacko. There aren't. That's one of the reasons why Jack is so important. </s>

<s>[INST] So you mentioned this simulation that we run over and over my start. It's a slow start. So do you think how unlikely, first of all, I don't know if you think about this kind of stuff, but how unlikely is step number zero, which is the springing up, like the origin of life on earth, and second, how unlikely is the anything interesting happening beyond that sort of like the start? Uh that that that creates all the rich complexity that we see on earth today? [/INST] Yeah, there are people who are working on exactly that problem uh from primordial soup. How do you actually get self replicating molecules and they are very close uh with a little bit of help, you can make that happen. Um so of course we know what we want. So they can set up the conditions and try out conditions that are conducive to that uh for evolution to discover </s><s>[INST] that took a long [/INST] time for us to recreate it probably won't take that long and the next steps from there. Um I think also with some hand holding, I think we can make that happen. Um but the revolution, what was really fascinating was eventually the runaway evolution of the brain that created humans and created, well also other higher animals. That that was something that happened really fast. Uh And that's a big question, is that something replicable? Is that something that can happen? And if it happens, does it go in the same direction? Um That is a big question to ask. Even in computational terms, I think that it's relatively possible to come up here create an experiment where we look at the primordial soup and the first couple of steps of multicellular organisms even, but to get something as complex as the brain. Um we don't quite know the conditions for that? Uh and how do you even get started and whether we can get this kind of runaway evolution happening </s><s>[INST] from a detective perspective, if we're observing this evolution, what do you think is the brain? What do you think is the let's say, what is intelligence in terms of the thing that makes humans special? We seem to be able to reason, we seem to be able to communicate. But the core of that is this something in the broad category we might call intelligence. So uh if you put your computer scientists at on ah is there a favorite ways you like to think about that question of what is intelligence? [/INST] Well, my goal is to create agents that are that are intelligent </s><s>[INST] not to define [/INST] with and that that is a bit of defining it and that means that it's some kind of an um object or or a program um that has limited sensory and uh effective capabilities interacting with the world. And then also a mechanism for making decisions. So with limited abilities like that, can it survive? Um uh survival is the simplest goal but it could you could also give it other goals. Can it multiply can it solve problems that you give it? Uh And that is quite a bit less than human intelligence. There are animals would be intelligent of course with that definition and you might have even even some other forms of life even so what? So intelligence in that sense it is a survival um scale given resources that you have and using using your resources so that you will stay around. </s><s>[INST] Do you think death mortality is fundamental to an agent? So like there's I don't know if you're familiar, there's a philosopher named Ernest Becker who wrote the denial of death and his whole idea. And there's folks, psychologists, cognitive scientists that work on terror management theory and they think that one of the special things about humans is that we're able to sort of for cr death, right? We can we can realize not just as animals do sort of constantly fear in an instinctual sense, respond to all the dangers that are out there, but like understand that this ride ends eventually and that in itself is the most is a is the force behind all of the creative efforts of human nature. That's that's the philosophy. [/INST] I think that makes sense. A lot of sense. I mean, animals probably don't think of death the same way, but you must know that your time is limited and you want to make it count. Um and you can make it in many different ways, but I think that has a lot to do with creativity and the need for humans to do something beyond just surviving. Uh and now going from that simple definition to something that's the next level, I think that that could be at the second decision, a second level of definition that um, intelligence means something that you do something that stays behind you, that's more than your existence. Um something you create, something that is useful for others is useful in the future, not just for yourself. And I think that's that's the nicest definition of intelligence in a next level. Uh and it's also nice because it doesn't require that they are humans are biological, they could be artificial agents of the intelligence. They could they could achieve those kind of girls. </s>

<s>[INST] there might be some actual game theoretic wisdom, there there might be something to be said about optimal itty from studying [/INST] him maliti </s><s>[INST] meaning or rather game design perhaps meaning if what he's doing is working, maybe poker is more complicated than we're currently modeling it as [/INST] or there's an extra layer and I don't mean to get too weird and we, but or there's an extra layer of ability to manipulate the things the way you want them to go that we don't understand yet. </s><s>[INST] Do you think Phil hellmuth understands them. Is he just generally [/INST] positivity, positivity, positivity </s><s>[INST] controlling book no [/INST] serious straight up? Yeah. </s><s>[INST] Hell wrote a book about positivity okay. [/INST] About I think, and I think it's about sort of manifesting what you want and getting the outcomes that you want by believing so much in yourself and in your ability to win like eyes on the prize. Um and I mean it's working </s><s>[INST] the man's delivered, but where do you put like Phil Ivey and all those kinds of people? I [/INST] mean, I'm too, I've been, to be honest, too much out of the scene for the last few years to really, I mean Phil Ivey is clearly got, again, he's got that X factor. Um he's so incredibly intimidating to play against, I've only played against him a couple of times, but when he looks you in the eye and you're trying to run a bluff on him, no one's made me sweat harder than Phil Ivey. Just um my my blood got through actually, that was actually one of the most thrilling moments I've ever had in poker was it was in a monte Carlo and a high roller. I can't remember exactly what the hand was, but you know, three bit and then like just barreled all the way through and he just like put his laser eyes into me and I felt like he was just scouring my soul and I was just like hold it together, hold it together. And he was </s><s>[INST] like, [/INST] yeah, I mean I was bluffing, I presume which you know, there's a chance I was bluffing with the best hand, but I'm pretty sure my hand was worse. Um and and he folded, I was truly one of my, one of the deep highlights of my career, you should never show in game. Like because especially as I felt like I was one of the worst players at the table in that tournament. So giving that information unless I had a really solid plan that I was now like advertising or look, I'm capable of bluffing Phil Ivey, but like why? It's much more valuable to take advantage of the impression that they have of me, which is like I'm a scared girl playing a high roller for the first time, keep that going? You know, </s><s>[INST] interesting. But isn't there layers to this like psychological warfare that the scared girl might be way smarter and then like to flip the tables, do you think about that kind of stuff? [/INST] Not to </s><s>[INST] reveal information? [/INST] I mean generally speaking, you want to not reveal information. You know, the goal of poker is to be as deceptive as possible about your own strategies while elucidating as much out of your opponent about their own. So giving them free information, particularly those people who you consider very good players, any information I give them is going into their little database and being calculate, assume it's going to be calculated and used well. So I have to be really confident that my like meta gaming that I'm going to then do or they've seen this so therefore that I'm gonna be on the right level. Um, so it's better just to keep that little secret to myself in the moment. </s><s>[INST] So how much is bluffing part of the game? [/INST] Huge </s><s>[INST] amount. So yeah, I mean, maybe actually let me ask like what did it feel like with Phil Ivey or anyone else wants a high stake when it's a big, it's a big bluff. Um, there's a lot of money on the table and maybe, I mean what defines a big bluff? Maybe a lot of money on the table, but also some uncertainty in your mind and heart about like self doubt, maybe I miscalculated what's going on here, What the bet said, all that kind of stuff like, what does that feel like? [/INST] I mean, it's, I imagine comparable to, you know, running a, I mean any kind of big bluff where you have a lot of something that you care about on the line, you know, So if you're bluffing in a courtroom, not that anyone could ever do that, you know, something equate able to that. It's, it's, you know, in that scenario, you know, I think it was the first time I've ever played a 20 I'd won my way into this 25 K tournament. So that was the buy in €25,000 and I had satellited my way in because it was much bigger than I would never ever normally play. And you know, I hadn't, I wasn't that experienced at the time and now I was sitting there against all the big boys, you know, the Negreanu Phil Ivey and so on. Um, and then, uh, to like each time you put the bets out, you know, you put another bet out your card. Yeah, I was honest, what's called a semi bluff? So there was some cards that could come that would make my hand very, very strong and therefore win. But most of the time those cards don't come. </s><s>[INST] So that it's a semi bluff because you're representing, what are you representing that? You already have something. [/INST] So I think in this scenario I had a flush draw too. So I had to clubs to two clubs came out on the flop and then I'm hoping that on the turn and the river one will come. So I have some future equity. I could hit a club and then I'll have the best hand in which case great. Um, and so I can keep betting and I want them to call. But I'm also got the other way of winning the hand where if my car doesn't come, I can keep betting and get them to fold their hand. Um, and I'm pretty sure that's what the scenario was. Um, so I had some future equity, but it's still, you know, most of the time I don't hit that club. And so I would rather him just fold because I'm, you know, the pot is now getting bigger and bigger and in the end, like I jam jam all in on the river, that's my entire tournament on the line. As far as I'm aware, this might be the one time I ever get to play a big 25 K. You know, this is the first time I played one. So it was, it felt like the most momentous thing and this is also when I was trying to build myself up, you know, build my name, a name for myself in in poker. I wanted to get respect, </s>

<s>[INST] Yeah, but so uh to me honestly the most difficult part is the thing you said with the marvelous paradox is to create a human form that interacts and proceed in the world. But if we just look at a voice like the movie her or just like an Alexa type voice, I tend to think we're not that far away. [/INST] Well for some for some people maybe not but you know I I you know as humans as we think about the future, we always try and this is the premise of most science fiction movies. You've got the world justices today and you change one thing right? But that's not how it's the same with the self driving car. You change one thing. I know you everything changes, everything grows together so surprisingly might be surprising to you might not. I think the best movie about this stuff was bicentennial man and what was happening there. Um It was schmaltzy and you know what was happening there as the robot was trying to become more human. The humans were adopting the technology of the robot and changing their bodies. So there was a convergence happening in a sense so we will not be the same. You know we're already talking about genetically modifying our babies. You know there's a more and more stuff happening around that we will we will want to modify ourselves even more for all sorts of things. Um We put all sorts of technology in our bodies um to improve it. You know I've got I've got things in my ear so that I can sort of hear you uh so we're always modifying our body so so you know I think it's hard to imagine exactly what we like in the future </s><s>[INST] but on the turing test side, do you think uh oh, forget about love for a second. Let's talk about just like the elect surprise actually. I was invited to be uh what is the interviewer for the elixir prize or whatever that's in two days. Their idea is uh success looks like a person wanting to talk to an AI system for a prolonged period of time, like 20 minutes. How far away are we? And why is it difficult to build an ai system with which you want to have a beer and talk for an hour or two hours? Like not for to check the weather or to check music, but just like to uh to talk as friends. Yeah. [/INST] Well, you know, we saw we saw Weidenbaum uh back in the sixties with his program Eliza. Um Being shocked at how much people would talk to Eliza. And I remember, you know, in the 70s typing, you know, and stuff to listen to see what it would come back with. Um You know, I think right now, and this is the thing that um uh amazon has been trying to improve the work. So there is no continuity of of of of topic. There's not you can't refer to what we talked about yesterday. Um It's not the same as talking to a person where there seems to be an ongoing existence changes. </s><s>[INST] Um We share moments together and they last in our memory together. [/INST] Yeah, but there's none of that and there's no um sort of intention of these systems that they have any goal in life, even if it's to be happy, you know, they don't they don't even have a semblance of that now. I'm not saying this can't be done, I'm just saying I think this is why we don't feel that way about them. That's a I'm sort of a minimal requirement. If you want the sort of interaction you're talking about, it's a minimal requirement, whether it's going to be sufficient. I don't know, we haven't seen it yet, we don't know what it feels like. I </s><s>[INST] I tend to be I tend to think it's uh it's not uh as difficult as solving intelligence for example, and I think it's achievable in the near term, but on the touring test, why don't you think the turing test is a good test of intelligence? [/INST] Because you know, again the turing, if you read the paper during wasn't saying this is a good test he was using as a rhetorical device to argue. Um That if you can't tell the difference between a computer and a person, you must say that the computer's thinking because can't tell the difference, you know when it's thinking you can't you can't say something different um what it has become as this sort of weird game of fooling people. Um So back at the uh ai lab in the late eighties we had this thing that still goes on called the ai olympics. And one of the events we had one year was um the original imitation game as cheering talked about because he starts by saying, can you tell whether it's a man or a woman? So we did that at the at the lab. We had, you know, you've gone type and the thing would come back and you had to tell whether it was a man or a woman. Um and um the the uh one of the, one of the, one of the uh one man came up with a question that he could ask which was always a dead giveaway over whether the other person was really a man or woman. You know what he would ask them. Did you have them green plastic toy soldiers as a kid? Yeah. What do you do with them? And a woman, a woman trying to be a man would say I lined them up, We had wars, we had battles and the man just being announced, I stomped on them. So, you know, that's what, that's what the turing test. The turing test with computers has become. What's the trick question? What's that? That's why it sort of devolved into this. </s>

<s>[INST] take a step shaky have arms, that what was the job shake? It [/INST] was a mobile robot but it could push objects and so it would move things around </s><s>[INST] with which actuated with [/INST] itself with spot with its face. Okay. Um so it could but it and they had painted the baseboards black. So it used it used vision to localize itself in a map, It detected objects, it could detect objects that were surprising to it. It would plan and re plan based on what it saw, it reasons about whether to look and take pictures. I mean it really had the basics of of so many of the things that we think about now. How </s><s>[INST] did it represent the space around it? [/INST] So it had representations that a bunch of different levels of abstraction. So it had I think a kind of an occupancy grid of some sort at the lowest level at the high level. It was abstract symbolic kind of rooms and connectivity. </s><s>[INST] So where does flaky come in? [/INST] Yeah, Okay. So I should have but S. R. I. And the we were building a brand new robot as I said, none of the people from the previous project, we're kind of there are involved anymore. So we're kind of starting from scratch and my advisor was stan Rosenstein, he ended up being my thesis advisor. And he was motivated by this idea of situated computation are situated at tomorrow. And the idea was that the tools of logical reasoning were important but possibly only for the engineers or designers to use in the analysis of the system, but not necessarily to be manipulated in the head of the system itself. Right? So I might use logic to prove a theory about the behavior of my robot, even if the robot's not using logic and it's had to prove their apps right? So that was kind of the distinction. And so the idea was to kind of use those principles too make a robot do stuff. But a lot of the basic things we had to kind of learn for ourselves because I had zero background in robotics, I didn't know anything about control, I don't know anything about sensors. So we reinvented a lot of wheels on the way to getting that robot to do stuff. </s><s>[INST] Do you think that was an advantage or hindrance? Oh [/INST] no, it's I mean I'm big in favor of well reinvention actually. I mean I think you learned a lot by doing it. Uh it's important though to eventually have the pointers to so that you can see what's really going on. But I think you can appreciate much better the good solutions once you've messed around a little bit on your own and found a bad one. </s><s>[INST] Yeah, I think you mentioned reinventing reinforcement learning and referring to uh rewards as pleasures, pleasure I think, which I think is a nice name for it. It's more it's more fun almost. Do you think you could tell the history of ai machine learning reinforcement learning how you think about it from the fifties to know [/INST] one thing is that it oscillates, right? So things become valuable and then they go out and then something else becomes cool and it goes out and so on. And I think there's so there's some interesting sociological process that actually drives a lot of what's going on early days was kind of cybernetics and control, right? And the idea that of homeostasis, people who made these robots that could, I don't know, try to plug into the wall when they needed power and then come loose and roll around and do stuff. And then I think over time the thought well that was inspiring. But people said no, no, we want to get maybe closer to what feels like real intelligence or human intelligence and then maybe the expert systems, people tried to do that, but maybe a little too superficially right? So, oh, we get this surface understanding of what intelligence is like because I understand how a steel mill works and I can try to explain it to you and you can write it down in logic and then we can make a computer and for that and then that didn't work out. But what's interesting I think is when the thing starts to not be working very well? It's not only do we change methods, we change problems. So it's not like we have better ways of doing the problem with the expert systems. People are trying to do we have no ways of trying to do that problem. Oh yeah. I know. I think maybe a few but we kind of give up on that problem and we switched to a different problem and we we worked that for a while and we </s><s>[INST] make progress as a broad community, [/INST] as a community and </s><s>[INST] There's a lot of people who would argue you don't give up on the problem, it's just you decrease the number of people working on it. You almost kind of like put on the shelf so we'll come back to this 20 years later. Yeah, [/INST] I think that's right. Or you might decide that it's malformed, like you might say it's wrong to just try to make something that does superficial symbolic reasoning behave like a doctor. You can't do that until you've had the sensory motor experience of being a doctor or something, right? So there's arguments that say that that's problem was not well formed or it could be that it is well formed but we just weren't approaching it. Well </s>

<s>[INST] like you're seeing yourself in black and white almost. [/INST] I was seeing him. Yeah, I was only seeing </s><s>[INST] him channeling in some [/INST] in some weird way you're channeling him because you've seen so much of it. The only thing you know about jerome Lester Horwitz is curly. I'm not saying he was exhumed or something or spirit when I hear some weird, you know, crystal mommy ship like that. I'm saying that this because you know, so much of it because of the heavy blueprint that they left with you. You are, you're channeling what that person does and you're I was seeing entire scenes, you know, before you do them the way he would do it and then you want a couple takes to make sure that you're doing it right. But that was hard. That one was hard to let go of. Some of them </s><s>[INST] are. Do you think Larry David who was also in there dressed as a nun also had trouble letting go. That we mentioned clothes make the man. I think that worked for him in that case [/INST] man. You know, he uh </s><s>[INST] was it like working with the guy, Come [/INST] on, he's the greatest and he's a he's a big stooge. He's a stooge fan and him and Pete fairly are good friends. And then, but then Larry David has to show up and hang out with us for a couple of weeks. He's like, I didn't realize it was going to take this long, you know? But she's gonna be out here in Atlanta, it's boiling hot. But at one point uh there was this line where he kept doing a he would just spit a different line every time he was like, getting hit in the head with something, he's laying there on the ground and he goes, He comes to and he says at one point he goes, Miami audiences are the best audiences in the world, right? And because he's loopy now, he's playing a nun at the at the orphanage where the three stooges grew up and I'm super intimidated by Larry David, he's a genius and stuff and and uh and but I walk up to him and I go, uh so he's what is he, like a like a belt florida comedian who is on the lam. And so he's dressing as a woman, he ends up in an orphanage, like, what's going on in there? And he just, and he looks at me and goes, yeah, like like I'm like, he's got like, actor motivation, like of course, he looks it's Larry David in a nun's habit, which is hilarious, that's such a p fairly casting thing, it's, you know, and he's but he's doing this whole like, what a warm audience, you know, like, like, oh, he's like this Catskill comedian who's been living in, you know, </s><s>[INST] living through in his mind as he's having fun with it, right? [/INST] I mean that and probably a combination of that and getting the lines right? Because he's like, what are we doing here? What is, you know, just frustrated all day with what the heck we're trying to do? </s><s>[INST] What do you think makes? I mean, that guy is one of the best improv people ever. So what do you think makes him so good? Like what? Why is it so compelling to watch that guy? Because [/INST] He's a comedic genius. Like he literally he knows what he does, he's been a writer for 50 years or whatever and he's and he just happens to be that brilliant. I mean, I've gotten a chance just to do. I did it just an episode of curb a small part and it's crazy what he sees. I don't know what he sees as a matter of fact. So I auditioned for it for curb, like, you know, two or three times, right? And never got anything. And then it was only after working with him on the stooges, I got a call to do a bit part, but I remember auditioning, you go into that into that room and the guys waiting are all people that, you know, you're like, oh, I know them, I know her, I knew him and uh so I went in, I auditioned for this for this part. And the only thing I know the thing is like, okay, so you really want to go to this play with me. You really want to go to this plane when you hear that? I have an extra ticket. You sincerely want to think. And I'm like, got it. And </s><s>[INST] so that's [/INST] the premise of the scene </s><s>[INST] and that's [/INST] all I know. And so he goes, he does his bit and I'm just supposed to come in and interrupt and I'm like, excuse me, I couldn't help but hear you guys were talking about, you know, whatever the play was, you know, death of a salesman, I am, I'm a huge fan of that player. I mean, if it's not, if it's not, if you're looking for someone to take a ticket, I would love to go, My name is so and so by the way, and he goes, I'm gonna stop you. I'm gonna stop you. And I'm like, you really you I mean, you truly want to go to this play. And I go, yes, yes, sir. You really want to go. You actually, this is you would love to do this. I go, okay, let's try it again. So then he's like, no, no, no. And I go, hey, excuse me, I'm sorry, I don't mean to interrupt. I was just I couldn't help it over here. You have tickets to? The thing I am the biggest fan. I do the same thing, I'm gonna stop you again. Okay. I mean, you really want to go to this and I'm just like, he's fuckinwith me, right? Remember Jeff garland was sitting there in the audition. He goes, he did it, He said it. What? Shut up, hold on. Listen, you really want to go, okay, three or four times, You know, there I am. I couldn't help but notice it and then do it again. I guess I ship the bed because he looks at me and just goes, okay, alright, okay, well thanks for coming up and that was it. And I didn't get it. So I still, I don't know what the heck that guy's thinking. He sees he's in the Matrix. I don't know what the heck. Larry david sees, you know what he </s>