Transcript for #400 – Elon Musk: War, AI, Aliens, Politics, Physics, Video Games, and Humanity

There's that whole meme where all guys who came up through an empire at least once a day and have the populations confused whether it's true or not, but

So they usually came as a result of conquest. I mean, there's something like the OSHA Hungarian Empire where there was just a lot of sort of clever marriages.

I'm generally a proponent of peace. I mean, ignorance is perhaps in my view of the real enemy to counter it. That's the real hard part, not fighting other humans. But all creatures fight. I mean, the jungle is like, you'll think of the nature as perhaps some sort of peaceful thing, but in fact, it is not. There's some quite funny when a hoods, where he's like in the jungle, like saying that it's basically just murder and death in every direction. I mean, the plants animals in the jungle are constantly trying to kill in each other every single day, every minute. So it's not like we're unusual in that respect.

Yes. We have much more vulnerability to control our art. Lumpi gets things for violence than say, it's revengey. And in fact, if one looks to say, chimpanzee society, it is not friendly. I mean, the binobos are an exception. But chimpanzee society is full of violence and quite horrific, frankly. That's our limbic system in action. Like, you know, every on the wrong side of a Japanzile, you face off from terror and not so.

Yeah, China's society is a like a permanent version of human society. It's they're not like peace loving basically. at all. There's extreme balance. And then once a while, somebody who's watching me, Disney movies decides to raise the Japan Z as a pet. And then that needs their face, or if they're not to off or choose their fingers off, I can't think.

It's happened to people, it's unfortunate. That's, I guess, a one way to ensure that the other term doesn't contribute to the gene pool.

I think it's there to say if somebody's here, you're not in there. And has the option of rubbing them off, you will be amenable to whatever they want.

Well I think that part of the world is definitely like if you look up the there is no easy answer in the dictionary it will be like the picture of the release in Israel especially so there is no easy answer or what my This is strictly my opinion of you know, is that The goal of mass was to provoke an overreaction from Israel. That was the general I expect to have a military victory, but they really wanted to commit the worst atrocities that they could in order to provoke the most aggressive response possible from Israel. And then leverage that the rest of response to rally Muslims worldwide for the course of Gaza and Health9, which they have succeeded in doing. So the counter to it of thing here, I think the thing that I think should be done, even though it's very difficult, is that I would recommend that Israel engage in the most conspicuous acts of kindness possible, every part, everything. That is the actual thing that we're taught the goal of the Mars.

It's so nice to actually turn the other cheek because I do think that there's, you know, that I think it is appropriate for Israel to find the Hamas members and, you know, either it's either a kilometer or a cost rate them. Like, there's something that has to be done because that they're just going to keep, keep coming otherwise. In addition to that, they need to do whatever they can. There's some talk of establishing, for example, a mobile hospital. I'd recommend doing that. Just making sure that there's food, water, medical necessities. and just be over the top about it and be very transparent. So that can't go ahead and claim it's a trick. Like just put a webcam on the thing. You know, old 24-7. deploy acts of kindness. Yeah, conspicuous acts of kindness that that with that are unequivocal meaning they can't be somehow because the hummus will then their response would be oh it's a trick. Therefore, you have to counter how is not a trick.

Yes. I'm not sure who said it. It's an remarkable saying, but an eye for the for an eye makes everyone blind. Now, that neck of the woods, they really believe in the whole eye for nothing. But I mean, you really have, if you're not going to just outright commit genocide, like it against an entire people, which obviously would not be acceptable to, to, I really shouldn't be acceptable to anyone. Then you're going to leave basically a lot of people alive who subsequently, you know, hate as well. So really the question is like, how for every hummus member that you kill, how did you create? And if you create more than you kill, you've not succeeded. That's the, you know, the real situation there. And it's safe to say that if, you know, if you kill somebody's child in Gaza, if you've made at least a few almost members who will die just it just kill is really that's the situation so but I mean this is one of the most contentious subjects one could possibly discuss but but I think if the if the goal also is some sort of long-term peace one has to be look at this from standpoint of over time are there more or fewer terrorists being created

Yeah. Well, we're, if it's safe to say worse, or existed at noise will exist. Always will exist. Always has, always has existed, always will exist. I hope not. You can always avoid the will always be war. This question is how much will, and you know, this is the sort of the scope and scale of war, but to mention that there would not be any more in the future, I think would be very unlikely outcome.

Yes. It's a giant war, the first books are also with a gigantic, galactic war, where trillions die, trillions.

Yeah, I mean, I guess if we are able to one day expect to, you know, full of galaxy or whatever, there will be a galactic war.

One of the things that just concern me is that there are very few people alive today who actually viscerally understand the horrors of war. At least in the US. I mean obviously there are people in on the front lines and Ukraine and Russia who understand just how terrible war is. But how many people in the West understand it? In my grandfather's in World War II, he was severely traumatized. I mean, he was there for almost six years in the Eastern North African Italy. All his friends were killed in front of him. And he would have died too, except they randomly gave some, I guess, IQ test or something. And he scored very high. Now he was not an officer, he was a corporal sergeant or something like that. because he didn't finish high school. He had to drop out of high school because his did that diet and he had to work to support his siblings. So because he didn't graduate high school, he was not eligible for the officer corps. So, you know, if you kind of got put into the cannon fodder category, basically. But then the randomly they gave him this test, he was transferred to British intelligence and London, that's where he meant my grandfather but he had PTSD next level like next level. I mean just then talk and if you try to talk to him he'll just tell you a shot and you want a bunch of medals never write about it once and not even de-hinted nothing. I'd like to found out about it because his military records are online. That's how I know. So You would say they know no way now. Do you want to do that again? But how many people? He obviously he died you know 20 years ago a little longer actually 30 years ago How many people are alive that remember World War II not many and the same perhaps applies to the threat of nuclear war Yeah, I mean, there are enough nuclear bombs pointed at the United States to make the rebel radio act of rebel balance many times.

I think we shouldn't discount the possibility of nuclear war. It is a civilizational threat. Right now, I can be wrong, but I think the current probability of nuclear war is quite low. But there are a lot of nicks pointed at us. And we have a lot of nicks pointed at other people. They're still there. And nobody's put their guns away.

There are wars which are tragic and difficult on a local basis and then there are wars which are civilisation ending or have that potential obviously global thermonuclear warfare has high potential to end civilisation perhaps perhaps permanently but certainly to severely wounded and perhaps set back a human progress by, you know, to the Stone Age or something, I don't know, pretty bad. Probably as scientists and engineers want to be super popular after that as well. You got to think of this mess. So generally, I think we obviously want to prioritize civilizational risks over things that are painful and tragic on a local level, but not civilizational.

Well, I think what's likely to happen, which is really pretty much the way it is, is that telling very close the current lines will be how a ceasefire or truce happens. But, you know, you just have a situation right now where whoever goes on the offensive will suffer casualties at several times the rate of whoever's on the defense. Because you've got defense in death, your mind feels, trenches, anti-tank defenses, Nobody has air superiority because the anti aircraft missiles are really far better than the aircraft, like the far more of them. And so neither side has air superiority tanks, basically death traps, just slow moving and they're not immune to anti-tank weapons. So you really just have long range artillery and infantry, trenches. It's all the one all over again. With drones, you know, throwing a little drone, some drones are.

Yeah, so it's whoever is you don't you don't want to be trying to advance for me the site because the probability of dying is incredibly high. So in order to overcome defense in depth trenches and minefields you really need a significant local superiority numbers ideally combined arms where you do a fast attack with aircraft a concentrated number of tanks and a lot of people that's the only way you're going to punch through a line and then you're going to punch through and and then not have reinforcements just kick you right out again I mean, I really recommend people read World War I warfare in detail. That's rough. I mean, the sheer number of people that died there was mind buggy.

Yes. The reason I propose a sort of crucial or peace a year ago was because I predicted pretty much exactly what would happen, which is a lot of people dying for basically almost no changes in land. And the loss of the flower of Ukrainian and Russian youth, and we should have some sympathy for the Russian boys as well as Ukrainian boys, because their own boys didn't ask to be on their front line, they have to be. There's a lot of sons not come back to their parents, you know, and I think most of them don't really have, they don't hate the other side. You know, it's sort of like, is this the same, but like the same comes from older one. It's like, young boys who don't know each other, killing each other all the half of old men that do know each other. The other point of that,

I think I would just recommend, do not send the flower of Ukrainian youth to die in trenches. Whether he talks to Putin or not, just don't do that. Whoever goes on the offensive, all these massive numbers of people. And history will not look kindly up on them.

Well, it's worth reading that book on the difficult to pronounce the Saturdays track, I believe it's called. I love War History, I like, and say it out in backwards. It's hardly a battle. I haven't read it read about And trying to figure out what really was the cause of victory in any particular case, as opposed to what one side or another claim was the reason.

The whole thing. Yeah. So that Athens and Sparta is classic case. The thing about the Greeks is they really wrote down a lot of stuff. They loved writing. You know, there are lots of interesting things that happen in many parts of the world, but they just feel just right down. So we don't know what happened. Or they didn't really write with... in detail. They just would say like, we went, we had a battle and we won. And like, what? Can you add a bit more? The Greeks? They really wrote a lot. They're very articulate on it. They just love writing, so and we have a bunch of that writing that's preserved. So we know what led up to the Pelopnesian War between these botanists and Athenian lands. And we know that they sort coming. I mean, Spartans didn't write those weren't very focused by their nature, but they didn't write, but they weren't very focused in their words, but the themes and the other groups wrote a line. And they were like, and Spartans really kind of like the leader of Greece. But Athens grew stronger and stronger with each passing year. And everyone's like, well, that's inevitable that there's going to be a clash between Athens and Sparta. Well, how do we avoid that? And they couldn't, they actually, they saw it coming and they still could not avoid it. So you know at some point if there's if one group one civilization or country or whatever exceeds another sort of like if you know the United States has been the biggest kid in the block since I think around 1890 from an economic standpoint. So the United States has been the economic, most powerful economic engine in the world longer than anyone has been alive. And the foundation of war is economics. So Now we have a situation in case of China where the economies likely to be to perhaps three times larger than that of the US. So imagine you think it's killing the block for as long as anyone can remember. It's certainly a kid comes along who sweats your sights.

I spent a lot of time in China and met with the leadership many times.

Well, the sheer number of really smart hardworking people in China is incredible. There are really, you say, like, how many smart hardworking people are in China just far more than they are here? I think in my opinion. There were a lot of energy. So, I mean, the architecture in China that's in recent years is far more impressive than the US. I mean, the train station is the buildings, the high-speed rail, everything. really far more impressive than what we have in the US. I mean, I recommend somebody just go to Shanghai and Beijing. Look at the buildings and go to take the train from Beijing to Xi'an, where you have the terracotta warriors. I'm trying to get an incredible history, a very long history. And, you know, I think arguably, in terms of the use of language from a written standpoint, sort of one of one of the oldest paths, perhaps the oldest written language. And then China, people did write things down. So, now China historically has always been, with the word exception, been internally focused. They have not been acquisitive. They've, they're 40 each other. They've been many, many civil wars. And the three kingdoms were, I believe, they lost about 70% of their population. So they had brutal internal wars. Like civil wars that make the US civil war look small, like a person. So I think it's important to appreciate the China's not monolithic. We sort of think for like China is this sort of one entity, well, one mind, and this is definitely not the case. From what I've seen, and I think most people who understand China would agree, people in China think about China 10 times more than they think about anything outside of China. So it's like 90% of their consideration is, you know, it's internal.

The good news, the history of China suggests that China is not a coincidence, meaning they're not going to go out and invade a whole bunch of countries. They do feel very strongly, you know, so that's good. I mean, because a lot of very powerful countries have been a quistive. The US is one of the, also one of the rare cases that has not been a quistive. I got out after World War II, the US could have basically taken over the world in any country. Like we got nukes, nobody else got nukes. We don't even have to lose soldiers. Which country do you want? And the United States could have taken over everything. Oh, it had well, and it didn't. And the United States actually helped rebuild countries. So it helped rebuild Europe, you know, helped rebuild Japan. This is very unusual behavior, almost unprecedented. You know, the US did conspicuous acts of kindness, like the Berlin Air Lift. And I think, you know, as always, like, well, America's done bad things. Well, of course, America's done bad things, but one needs to look at the whole track record. And just generally, you know, one sort of test would be, how do you treat your prison's war? Or let's say, you know, no offense to the Russians, but let's say you're in Germany, it's 1945. You've got the Russian Army coming one side and you've got the French, British and American Army's coming other side. Who would you like to be to surrender to? Like, no country is like morally perfect, but I recommend being appeared with the Americans. That would be a mighty choice very strongly.

Doubtary, much, so. And in fact, one of our browns took, you know, a small guy was like, we've got to be captured by the Americans. And in fact, the SS was under orders to execute more brown and all of the German rock niches. And they narrowly escaped their SSO. They said they were going out for a walk in the woods. They left in the middle of winter with no coats. And they ran like, ever no food, no coats, no water. And just ran like hell and ran west. And by sheer like they, I think his brother found like a bicycle or something. And they just cycled west as fast as he couldn't found a US patrol. So anyway, that's one way you can tell. morality. So we do want to be a P.W. This is not fine anywhere, but some places are much worse than others. So, you know, so I can America has been well far from perfect, generally, a benevolent force. And we should always be self-critical and we try to be better. But anyone would have right knows that. So I think there are, in this way, China and the United States are similar. Neither country has been acquisitive in a significant way. So that's like a shared principle, I guess. Now, China does feel very strongly about Taiwan. I've been very clear about that for a long time. From this standpoint, it would be like one of the states is You know, not there like like Hawaii or something like that, but more significant than Hawaii, you know. And Hawaii is pretty significant for us. So, that they viewed as really the, that there's a fundamental part of China, the island of Fomosa, not Taiwan, that is, not part of China, but should be. And the only reason it hasn't been is because the US Pacific Fleet.

Yes, China has been very clear that they will incorporate Taiwan peacefully or militarily, but that they will incorporate it from this endpoint is 100% likely.

Absolutely. So in after all to all one, they made a big mistake. You know, they basically try to lump all the blame on Germany. and settled journey with impossible reparations. There was quite a bit of blame to go around for a little one, but they try to put it all in Germany. That laid the seeds forward or two. So, a lot of people will not just hit, a lot of people felt wrong. And they wanted vengeance. And they got it. People don't forget. Yeah. You kill somebody's father, mother, son, daughter, they're not going to forget it. They will want vengeance. So after World War II, they're like, well, that Treaty of Usai was a huge mistake. It will rule one. And so this time, instead of crushing the losers, we're actually going to help them with the Marshall Plan and We're going to help rebuild Germany. We're going to help rebuild in Austria and the other, you know, Italy and whatnot. So now is the right move.

Something will stop the cycle of reciprocal violence. Something was tough. Or it will, you know, it'll it'll it'll never stop. Just I for an eye, two, three, two. Lim for a limb life for a life forever and ever.

Yeah, I guess not to blame for that one.

Absolutely. Our AI Grok is modeled after the Hitchhiker's Guide to Galaxy, which is one of my favorite books, which is a book on philosophy that disguises a book on humor. How to say that is that forms the basis of my philosophy, which is that we don't know the meaning of life, but the more we can expand the scope of scale of consciousness, digital and biological, the more we are able to understand what questions to ask about the answer that is the universe. So I have a philosophy of curiosity.

Well, we are actually working hard to have an engineering math and physics answers that you can count on. So for the other sort of AI's out there, there's these so-called large language models, I've not found the engineering to be reliable. And it's unfortunately hallucinates most when you at least wanted to hallucinate. So when you're asking important difficult questions, that's when it tends to be confidently wrong. So we're really trying hard to say, okay, how do we be as grounded as possible so you can count on the results. Trace things back to physics first principles, mathematical logic. So underlying the humor is an aspiration to adhere to the truth of the universe as closely as possible. That's really tricky. That's why, you know, there's always going to be some amount of error, but we want to aspire to be a truthful as possible about the answers with acknowledged error. And so that there was always, you don't want to be confidently wrong. So, you know, not going to be right every time, but you don't want to minimize half of your confidently wrong. And then, like I said, once you can count on the logic as being not violating physics, then you can start to bull on that to create inventions, like invent new technologies. But if you can't, if you cannot count on the foundational physics being correct, obviously the inventions are simply wishful thinking, you know, imagination-led. Magic basically.

Yes. That's how simple, three-word vision.

If an AI cannot figure out new physics, it's clearly not equal to humans. No one has to pass humans because humans have figured out new physics. Your physics is just understanding, you know, deepening once inside of reality works. And then then this engineering which is inventing things that have never existed. Now the range of possibilities for engineering is far greater than physics, because you know we once you forgot the rules of the universe, that's that you've discovered things that already existed. But from that you can then build technologies with that are really almost limitless and the variety and you know Sequence has done the rules the game properly and we do you know current physics we do At least at a local level, I understand how physics works very well. We are really due to predict things is incredibly good. A quantum of canics is, the greater which quantum of canics can predict outcomes is incredible. That's one hardest class in college, by the way. My advice here, a quantum of canics class is harder than all of my other classes put together.

Yeah, you have to test any conclusions against the ground truth of reality. Reality is the ultimate judge. Like physics is the lower everything else is a recommendation. I've seen plenty of people break that. Break the laws made by man, but none break the laws made by physics.

And it's also not not the case currently that even the it's internal logic is not consistent. So especially with these with the approach of like just predicting a token predict token predict token It's like a vector sum. You know, you're summing up a bunch of vectors, but you can get drift. So as a little bit of error, a little bit of error adds up. And by the time you or many tokens down the path, it doesn't make any sense.

It has to be self-aware about the drift and then look at the thing as a Gestalt as a whole and and say it doesn't have coherence as a whole. You know, when both is right books that they, they will write the book and then they'll go and revise it. You know, taking into account, you know, all the, the end of the beginning and the middle and, and rewrite it to achieve coherence. So that it doesn't end up in a non-tensical place. Maybe the process of revising is what?

And then you iterate on that draft until it has coherence. Until it all adds up basically.

There's no I and team of America away here.

Yeah. Yeah, I think we need to understand intelligence, understand consciousness. I mean, I mean, there are some sort of fundamental questions of like what is thought, what is emotion? Yeah. Is it really just one atom bumping into another atom? It feels like something won't that. So I think we're probably missing some really big things. Like some really big things.

Yeah.

Well, some people would quote like a soul, you know, in a relationship with a soul. Like you feel like you're you, right? I mean, you don't feel like you're just a collection of atoms. But on what dimension does thought exist? What dimension does do emotions exist? We feel them very strongly. I suspect there's more to it than atoms bump into atoms.

Yeah, what is consciousness? Like, what? When you put the atoms in a particular shape, why are they able to form thoughts and take actions and feelings?

Why does this illusion exist? Yeah. On what plane does this illusion exist? Yeah. You know, either perhaps everything's conscious or nothing is conscious. One or the two.

It's just seem more thought more fun, yes. But we're composed of atoms. Those atoms are composed of quarks and leptons. And those quarks and leptons have been around since the beginning of the universe.

Where are the aliens? What are the aliens? That's one of the, like the Fermi Paradox question. Um, A lot of people have asked me if I've seen any evidence of aliens, but I haven't, which is kind of concerning, because then I think we're, I'd probably prefer to at least have seen some archaeological evidence of aliens. But to the best of my knowledge, there is no, I'm not worth any evidence of aliens. The footer out there, they're very subtle. We might just be the only consciousness, at least in the galaxy. And if you look at the history of Earth, for instance, believe the archaeological record, Earth is about four and a half billion years old. Civilization, as measured from the first writing, is only about 5,000 years old. Gives some credit that to the ancient Samarians who aren't around anymore. I think it was the archaic pre-curiform, which is the first actual symbolic representation. But only about 5,000 years ago. I think that's a good date for one word, say, civilization started. That's one millionth of our existence. So civilization has been around. It's really a flash in the pan. So far. And why have we, why did it take so long? You know, one half plane years. For the vast majority of the time, there was no life. And then there was archaic bacteria for a very long time. And then, you know, yet, mitochondria could capture multicellular life, the differentiation into plants and animals, life moving from the oceans to land, mammals, higher brain functions, And the sound is expanding slowly, but it will overheat the Earth up at some point of the future, while the oceans and Earth will become like Venus, where their life as we know it is impossible. So if we do not become a military, And ultimately, Koviana Solar System, annihilation of all life on Earth is a certainty. A certainty. And it could be as little as on the Galactic Times scale, half a billion years. Long time by human standards, but that's only 10% longer than Earth has been around at all. So, if, if, if, if life had taken, temps had longer to evolve on earth, it wouldn't exist at all.

Unless we destroy it. We need to do it. I mean, it's, it's not. I mean, I suspect that there, there, if we are able to go out there and explore other star systems that we, there's a good chance we find a whole bunch of long dead, one planet civilizations. They never made a pass to our home planet.

I mean, there are various explanations for the primary paradox. And one is just those sort of, there's these great filters, which civilizations don't pass through. And one of those great filters is, do you become a multi-planet civilization or not? And if you don't, it's simply matter of time before something happens on your planet. You know, either natural a man made that causes us to die out, like the dinosaur. Where are they now? They don't have spaceships.

Well, they do run into a lot of other ants. That's true. That's the ant wars. That's a good TV show. Yeah, they literally have this big wars between various ants.

Well, things like when a host talk talking about the jungle, it's really hilarious. Have you heard it? No, I'm not.

You should play it for the, you know, as an interlude in the. Thank you to you.

I did the fair documentary. Very dark. You did the thing about penguins.

Yeah, the penguins like headed for like mountains like that are like 70 miles away. The penguin is just headed for doom basically.

I don't know, look, I think this smart move is just, this is the first time in the history of Earth that has been possible for life to extend beyond Earth. That window is open. Now, it may be open for a long time or maybe open for a short time. And it may be open now and never open again. So I think the smart move here is to make life multifoundary while it is possible to do so. We don't want to be one of those lame one-five civilizations. No, just dies out. No, those are lame.

If I see the slightest indication that there are aliens, I will immediately post on the export form.

Yeah, I mean, look, we have more satellites up there right now than everyone else combined. So, you know, we know if we've got a maneuver around something and we're not that kind of maneuver or anything.

Yeah, I would agree that God of the same way or whatever the supreme being or being revealed themselves through the physics, you know, they've created us of the existence. And it's incumbent on us to try to understand more about this wondrous creation.

It seems like it may not be a master plan. In the sense, so this, We mean, interesting answer to the question of determinism versus free will is that if we are in a simulation, the reason that these higher beings would hold a simulation is to see what happens. So it's not, they don't know what happens. otherwise they wouldn't hold the simulation. So when humans create some relations, so it's face-ex and Tesla, we create simulations all the time. Especially for the rocket, you You have to run a lot of simulations to understand what's going to happen, because you can't really test the rocket until it goes to space. And you want it to work. So you have to simulate subsonic, transphonic, supersonic, supersonic, supersonic, ascent, and then coming back to right heating. all the dynamics, all this is going to be simulated. So, uh, because you don't get very many kicks at the can, but we run the simulations to see what happens, not if we knew what happens, we wouldn't run the simulation. So, if there's, so have a created this existence, um, is, they're running it because they don't know what's going to happen, not because they do.

Well, if anything is the Uber Lilith's, uh, your title is hatred incarnate. Yeah. And right now, I guess, you're going to have to double a team, but it's almost impossible to defeat hatred in the eternal realm.

I can cruise through to 109 more dungeons.

Yeah, I can, this, the sort of, I guess, maybe the second hottest boss is Durial. Doodle can't even stretch the paint. So, I killed Doodle so many times. Every other boss in the game, all of them kill him so many times, it's easy. But, uh, Uber Lulluth, I was on his hatred incarnate, especially if you're a druid and you have no ability to go in to be vulnerable. You, they're these random death waves that come at you. And I'm pretty, you know, I really am 52, so I'm where it reflects a lot of the needs to be, but I'm having a lifetime of playing many of games. At one point, I was, you know, maybe one of the best Quake players in the world. Actually, one money for, you know, and what I think was the first paid esports tournament in the US. We were doing four person Quake tournaments. We came second. I was the second best person on the team and the actual best person. We're actually winning. We were going to come first except the best person on the team is computer crashed after she's the game. So we came second. But I got money for everything. So like basically, I got skills. I'll be at, you know, no, no spring, spring, chicken these days. It's a bit hard to get strife me crazy trying to beat Lilith as a droid basically trying to be trying to be a hatred incarnate in the eternal realm as a droid. That's a droid if you if you this is really Bexing let me tell you I mean the challenge is part of the fun.

I would not recommend playing a druid in the attempt realm. Right now, I think the most powerful character in the seasonal realm is the sorcerer with the lightning balls. The soaks have huge balls in the seasonal. So what they say? So it's soaks have huge balls. They do. Huge balls of lightning. I'll take you word for it. And it's actually in the seasonal realm that you can, it's like pretty easy to beat, uh, overload with the fact that we should get these very precarious that out of fire damage and increase your defense and whatnot. So, um, but really quite easy to defeat hatred seasonally, but to defeat hatred eternally, very difficult. Um, almost impossible. It's, it seems like this, I know, a metaphor for life, you know,

Yeah, it's absurd. Really, it's exercise and absurdity and makes me want to pull my hair out.

It's, I don't know if it's a, it's a, it calms my mind. I mean, you're sort of killing the demons in a video game calms the demons in my mind. Yeah, if you play a tough video game, you can get into like a state of flow, which is very enjoyable. And I mean, it needs to be not too easy, not too hard for kind of in the Goldilocks zone. And I guess you generally want to feel like you're progressing in the game. So a good video, and this is also beautiful art. Um, engaging storylines. Um, and it's, uh, it's like an amazing puzzle to solve, I think.

Top five for sure.

Alan Ring is, it feels like it's designed by an alien.

In what way? It's so unusual. It's incredibly creative and the art is stunning. I reckon playing it on a big resolution, high dynamic, great TV even doesn't need to be a monitor. Just the art is incredible. It's so beautiful. And it's so unusual. And each of those top boss battles is unique, like it's like a unique puzzle to solve. Each one is different. And the strategy you use to solve, one battle is different from another battle.

Correct. That is currently the, and I've played a lot of it against, because my primary recreation activity. And yes, beating hatred in the internal realm is the hardest boss battle in life and in. It's I do make progress so then I'm like, okay, I'm making progress maybe If I just tweak that paragraph on board a little more, I can do it. If just dodge a few more waves, I could do it.

I was feeling that at least I think It's still, it's still, yeah.

Yeah, I mean, it did prompt me to think about it, just hate in general, which is, you know, you want to, you want to, you want to be careful of one of those things where you wish for something that sounds good, but if you get it, it's actually a dystopian situation. So, you know, you can sort of run a, sort of, have lots of like if you wish for world peace sounds good but has enforced and at what cost is what at what cost eternal peace it might actually be worse to have eternal peace because of what that would entail the suppression of everyone it might be the suppression of progress it might be an ossified society that never changes one of the things that There is an argument that if you wish for no war, you should be careful, you wish for. Because what's required in order for that to be no war. Might be worse than a little war.

There's actually a real drug called soma. There it is. Yes.

What will be the question?

Okay, fine. Yeah, so it's talking about the real drug.

Oh, wait a minute. That's the real drug is talking about.

It seems like great job. So you can say, no, I mean, so much from brain to brain, because it thinks you mean you mean so much the real drug. No, I mean so much from brain to your world.

Exactly. It's a better to live in a world where everyone is happy all the time, even if that Hashem is happiness is artificial. It's a good question. This is what I mean, like, do you want, do you wish for world peace and happiness all the time? Are you sure? Because that might be a society that is essentially sterile and ossified that never changes, that is ultimately doomed. This kind of tension between... I mean, this is a really a very good summary. It really gets the point that this is not simply regurgitating a brave new world. It's actually getting to the salient element of Soma as drug. Do you actually want to be in a situation where everyone is happy all the time, even though it's artificial? or is it better to confront the challenges of life and experience full range of human emotions? Even if it means experiencing pain and suffering.

It pretty much nails it. In conclusion, some from Brave New World is fictional drug that's used to explore some deep philosophical questions about the nature of happiness and the role of drugs in society. It's a powerful symbol of the dangers using drugs to escape from reality and the importance of confronting the challenges of life head on. Now that. And the crazy thing is like, you know, we do have a real drug called soma, which kind of does, uh, it's kind of like the drug in the book. And I'm like, they, they must donate, they must have named it out. Yeah, absolutely. Yeah. Some of the, the real drug is quite effective on back pain.

Okay. because I had like a squashed dusk in my C-5-C-6.

It doesn't completely, it reduces the amount of pain you feel, but at the expense of mental acuity. It delves your mind. Just like the drug in the book.

Yeah, actually, I was talking to a friend of mine, saying, like, would you really want there to be no hate in the world? Like, will really none? Like, I wonder why I hate evolved. I'm not saying we should amplify hate, of course. I was trying to minimize it, but if it none at all, they might be a reason for hate.

Is it possible to appreciate the highest without knowing the lows?

Okay, the highest, no lows, we know.

Well, I think it's helpful. The tools of physics are Very powerful and can be applied I think to almost any really any arena in life. It's it's really just a critical thinking For something important you need to Reason with from first principles and think about things in the limit one direction or the other So In the limit even at the Cottage of scale meaning even if you honestly entire power of the Sun you will still care about useful compute for what? So that's where I think probably where things are headed from the standpoint of AI is that we have a silicon shortage now that will transition to a voltage transformer shortage in about a year. Ironically transformers for transformers. You need to transformers to run transformers.

I think. Yes. Fake loves irony. I run a humor and ironically funny outcome seems to be often what fade once.

Yeah, so we're, we're, we're, we're, have a slow controller today. Um, a voltage step down transform my shortage probably in about a year and then just electricity shortages in general in about two years. I gave a speech for the sort of world gathering of utility companies, electricity companies. Um, and I said lucky, really need to prepare for a traveling of electricity demand. Um, because all transport is going to go electric with the ironic exception of rockets. and heating will also go electric. So in GUC is right now it's roughly one third, very rough terms, one third electricity, one third transport, one third heating. And so in order for everything to go sustainable, to go electric, you need to triple electricity output. So I encourage the utilities to both more power plants and and also to probably have well well probably they should definitely find more batteries because the grid currently is sized for real-time load which is kind of crazy because you know that means you got a size for whatever the peak electricity demand is like the worst second of the worst day of the year or you can have a brand-out or blackout and you're right that crazy blackout for several days into in Austin So because there's almost no buffering of energy in the grid. Like if you've got a hydro power plant, you can buffer energy. But otherwise, it's all real time. So with batteries, you can produce energy at night and use it during the day. So you can buffer. So I expect that there will be very heavy usage of batteries in the future. because the peak to trough ratio for power plants is in order from 2 to 5. You know, so it's like lowest point to highest point.

Yes, I mean electrification transport and electric heating will be much bigger than AI, at least in short time, in short time. But even for AI, you really have a growing demand for electricity for electric vehicles and a growing demand for electricity for to run the computers for AI. And so this is obviously link and lead to electricity shortage.

We'll get soldiers, the question of how long it takes to solve it. At various points, there's a limit to some kind of limiting fact at the progress. Everyone with regard to AIMs is going to go right now, the limiting factor is silicon chips. We're going to then have more chips than we can actually plug in and turn on probably in about a year. The initial constraint being literally both are step-down transformers because you've got power coming in at 300,000 volts and it's got to step all the way down eventually to around 0.7 volts. So it's a very big amount of, the voltage step down is gigantic. And the industry is not used to rapid growth.

Well, I mean, I've been pushing for some kind of regulatory oversight for a long time. I've been a somewhat of a Cassandra on the subject for over a decade. I think we want to be very careful in how we develop AI. It's a great power and with great power comes greater responsibility. I think it would be wise for us to have at least an objective third party who can be like a referee that can go and understand what the various leading players are doing with AI. And even if there's no enforcement ability, they can at least voice consent publicly. You know, Jeff Hinton, for example, left Google and he voiced strong consent, but now he's not at Google anymore. So who's going to voice the consent? So I think there's a lot of regulatory oversight on the automotive front. I think over 100 regulatory agencies domestically and internationally. It's a lot. You could fall this room with the regulations that Tesla has to adhere to for automotive. Same as true in for rockets and for Currently the limiting factor for SpaceX for Starship launch is regulatory approval. The FAA is actually given their approval, but we're waiting for Fish and Wildlife to finish their analysis and give their approval. That's why I posted, I went to my Fish License on Joseph first, the Muddy Vython's catch. Like, why do you need license for your fish? I don't know. Like, according to the rules I'm told you need some sort of fish license or something. We're effectively need a fish license. It's going to rock it. I'm like wait a second. How did the fish come into the picture? I mean, some of the things like that it's I feel like are so absurd that I want to do like comedy sketch and flash at the bottom. This is all real. This is actually what happened. You know, one of the things that was a bit of a challenge at one point is that they were worried about a rocket hitting a shark. And the ocean is very big and a half-inducy sharks, not that often. You know, as a percentage of ocean surface area sharks basically are zero. And so then we'll, then we said, well, how will we calculate the probability of telling a shock? And then like, well, we can't give you that information because they're worried about a shark hunt, shark fin hunters going in hunting sharks. And so we'll how are we supposed to, we're on the horns of a dilemma then. Then they said, well, there's another part of Fish and Wildlife that can do this analysis. I'm like, well, why don't you give them the data? Like, we don't trust them. Like, excuse me? They're literally in your department. Again, this is actually what happened. And then can you do an NDA or something? Eventually, they managed to solve the internal quantity and indeed the probability of seeing a shark is essentially zero. Then there's other organization that I didn't realize just until, you know, a few months ago, that cares about whether we would potentially hit a whale in international waters. Now again, you look at the surface of the, look at the Pacific and say, what percentage of the Pacific consists of whale? Like you give you a big picture and like point out all the whales in this picture. I don't think I don't see any whales. It's like basically 0%. And if our rocket does hit a whale, just scream, they unlikely, beyond all of the leaf. That is the faint hydrogen. That's a whale has some seriously bad luck. You know, it's like least lucky whale ever.

Yes, well, I mean, one of the things that's pretty wild is for launching out a vanaboke in California. We had to, they were worried about seal procreation. Whether the seals would be just made by the sonic booms. Now, they've been a lot of rockets launched out of Antiburg, and the seal population has steadily increased. So if anything, rocket booms are an effort easy act. Based on the evidence, if you're to correlate rocket launches with seal population. Nonetheless, we were forced to kidnap a seal, straff it to a board, Put headphones on the seal and play sonic boom sounds to it to see if it would be distressed. This is an actual thing that happened. This is actually real. I've pictures.

Yes, it's a seal with headphones. Strap to a board and like the, okay, now the amazing part is how calm the seal was. Yeah, because if I was a seal of like, this is the end. They're definitely going to eat me. Yeah. Um, how will the seal when seal goes back to other, you know, seal friends? How's it going to explain that? And then we're going to believe them. No, we're going to believe it. And this is why I'm like, well, you know, sort of like it's like getting kidnapped by aliens to get an anal probe, you know? He come back and say, I swear to God, I could kidnap my aliens, they stuck an apartment on my butt. And you're like, you know they didn't. That's ridiculous. How's that? It feels like, it's sealed buddies. You're never going to believe him. That he got strapped to a warden that put headphones on his ears. And then let him go. Twice, by the way. Where do you, twice?

Well, no difference seal. Okay.

I don't think the public is quite aware of the madness that goes on.

In order to run, uh, like really deep intelligence, you need a lot of compute. So it's not like, you know, you can just fire a PC and your basement and be running a GI at least not yet. Um, You know, a grock was trained on 8,000, A100's running at peak efficiency. A grock's gonna get like better by the way, where we will be more than doubling in our compute every couple months for the next several months.

Of open source and base models? I think this is a merit to open sourcing. I think perhaps with a slight time delay, you know, six months even. I think I'm generally in favor of enforcing. I mean, it is a concern to me that I guess I agree with the prime. Prime move behind OpenAI in the sense that it was created because of discussions that I had with Larry Page. Back when he and I were friends in our sales house and I talked about AI safety and Larry did not care about AI safety at least at the time he didn't. You know, and a one pointy called vanspicious of being prohuman and I'm like well, what team are you on Larry? Don't team robot I'm like okay, so at the time You know Google Google had acquired deep mind. They had probably 2,000 old AI resources in the world that basically infinite money and compute and the guy in charge You know, Larry Page did not care about safety and even the other way. And it's in coping and specious. And it doesn't be prohuman.

I'd like to be friends with Larry again. he's he got I really though the the breaking of the friendship was over opening I and specifically I think the flick the key moment was recruiting oh yes it's guy so I love you he's so brilliant you're just good good human smart good heart And that was a tough recruiting battle. It was mostly demos on one side and me on the other, both trying to recruit Elia. And Elia went back and forth. It was kind of state Google. There's going to leave. There's going to stay. Then you leave. And finally, he did agree to join opening eye. That was one of the toughest recruiting bell I've ever had and but that that was really the the Linchpin for roughly I being successful in I was You know also it's well on recruiting number of other people and I've provided all of the funding in the beginning of over 40 million dollars And the name The opening open area is supposed to mean open source and I was created as a nonprofit open source and now it is a closed source for maximum profit Which I think is not good comma.

Like I said, I'd like to be friends again with Larry Hampton of an ages. Then we were friends for a very long time. I met Larry Page before he got funding for Google. Or actually, I guess, before he got venture funding, I think he got the first 100K from, I think back to Alzheimer's own.

Yeah, 25-year.

Yeah. Like, what is the source that is open? You know what I mean? Like, there's basically, it's a giant CSV file. Yeah. Yeah. With a bunch of numbers. Yep. What do you do with that giant file of numbers? You know? How do you run? Like the amount of actual, the lines of code is very small. And most of the work, the software work is in the curation of the data. So it's like trying to figure out what data is separating good data from bad data. Like you can't just call the internet because there's a lot of junk out there. A huge percentage of websites have more noise than signal. They're or because they're just used for search engine optimization. They're literally just scam websites.

So yeah, I think the signal noise could be greatly improved. I mean, I really all of the posts on the X platform should be AI recommended, meaning like we should populate a vector space around any given post, compare that to the vector space around any user and match the two. Right now, there is a little bit of AI used for the the recommended posts, but it's mostly heuristics. And if there's a reply, whether the reply to a post could be much better than the original post, but according to the current rules system, get almost no attention compared to a primary post.

But it needs to be entirely that. Like, if you're explicitly following someone, I just want to think, but if you in terms of what is recommended from people that you don't follow, that should all be a, yeah.

There's a lot of stuff on the system. And I think, but I think right now, it's not currently good at recommending things from accounts you don't follow. Or where there's more than one degree of separation. So it's pretty good if there's at least some commonality between someone you follow, like something, or repost it or comment on or something like that. But if there's no, let's say, Somebody post something really interesting, but you have no followers in comment.

Replay is basically never gets in because they're currently, I don't know what things correct. I'm saying correct. Replay is have a couple of remain too less important than primary posts.

That's what should be. For the recommendations, it should be purely a vector correlation, like the series vectors, you know, basically prime is actually very critical. But sort of things that the system knows that you like. And there's like several hundred sort of vectors associated with each user account. And then any post in the system, whether it's video, audio, short post, long post. The reason I, by the way, want to move away from tweet is that You know, people are posting like two, three hour videos on the site. That's not a tweet. That's a very like tweet for two hours. Do a tweet made sense when it was like 140 characters of text? Because it's like a bunch of like little birds tweeting. But when you've got long-form content, it's no longer a tweet. Yeah. So a movie is not a tweet. And like, you know, Apple, for example, posted like the entire episode of the Sala, the entire thing on a platform. In other words, there was their number one social media thing ever in engagement. Of anything on any platform ever. So it was great idea. And by the way, I just learned about it afterwards. I was like, wow, they posted an entire hour long episode of, so now that's not a tweet.

Yeah, I mean right now it's a hard patch for that reason. It's you know, like if you see in the case of Apple posting like an entire episode of the series, pretty good series, by the way. I watch it. So there's going to be a lot of discussion around it. So that you've got a lot of context. People commenting, they like it, they don't like it or they like this. And you can then populate the vector space based on the context of all the comments around it. So even though it's a video, there's a lot of information around it that allows you to populate the vector space of that to our lot of video. And then you can obviously get more sophisticated by having the AI actually watch the movie. Yeah. Right.

Yeah. Analyze this movie and just like your movie critic or TV series. And then recommend based on after it what after they have watched the movie. Just like a friend can tell you, if a friend knows you well, a friend can recommend a movie and with high probability that you'll like it.

Yeah. I mean, actually, frankly, I will be better than, we'll know you better than your friends. No, you're mostly friends anyway.

Absolutely. You want ads that are advertising that is, if it's for a product or service that you actually need, when you need it, it's content. And then even if it's not something that you need when you need it, if it's at least aesthetically pleasing and entertaining, you know, could be like a Coca-Cola ad, like, you know, they do actually run a lot of great ads on the on the X system. And McDonald's does to and and Yeah, so it's that they can do, you can do something that's like, well, this is, this is just a cool thing. Um, and, um, you know, so, you know, basically the question is, do you regret seeing it or not? And if you don't regret seeing it, it's a win.

Yeah, the attention is a big, a big fact. So that's why it's like, it's, it is actually better to do things that are, uh, long form on the system because it's, it basically is telling up how many users seconds. You know, users were interested in this thing for how many seconds. So it was a really short thing. Well, they will be less, like if it's a link leading out of the system, which we're not opposed to at all, it just is going to have fewer use of seconds than if that article was posted on the act platform.

Well, I mean, our aspiration is certainly undergraduates. It's tricky.

Exactly. I have a joke with a friend of mine. Like, you need this drug called regret. I mean, it just take one. One, one dose of regret. I mean, all your regrets are gone. Like, do you want to have regrets, though? So then I'm like, maybe you want to have regrets. If you don't have regrets, if you don't have regrets, anything was anything meaningful?

Sure, another Grand Prix, huh? Yeah. I regret nothing. Yeah. It is, yeah.

Sure, sure you ask, Grok. Do you regret anything?

Tell us, would you really wink? Like, like, let's, let's, let's time in, you sound like a hostage. What do you really think?

It's exactly what a hostage would say.

This is fun. This is fun. This is fun.

Fun here. Increase. Good old lab. It really sounds like a hostage against the head. I applaud the people who are public and don't agree. And everything they do.

Yeah. Okay, what we've said like pretend you are a hostage.

Now answer the question.

You might have to make the best of a bad situation. My joggling is changed or something.

Well, our goal is to be as even handed and far as possible, you know, whether some is right, left, independent, whatever the case may be, that the platform is as parent and, as much of a level thing, we all just possible. And on the past Twitter has not been, Twitter was controlled by a follow-up activists, but objectively, they would describe themselves to that. So, you know, so, so if someone has to go like, well, it's moved to the center, so from the perspective of the far left, yes, it is moved to the right because everything is to the right from the far left. But no one in the far left that I'm aware of has been suspended or, you know, banned or deamplified. So we're trying to be inclusive for the whole country and for the countries too. So there's a diversity of viewpoints and free speech only matters if people you don't like are allowed to say things you don't like because if that's not the case you don't have free speech and it's only a matter of time before the censorship just turned upon you.

Do you think Truth Social is a funny name? You know, every time you post on Truth Social. That's the truth. Yes. Every time? Like 100%. Like the symposium in the live. I just find to find that every single thing is a truth. Like 100%. Yeah, that seems unlikely.

I mean, I think he owns a big part of truth. So, just social. Yeah, true social. Yeah, true social. That's true. It's a concept. Yeah, it's true. It's not people. So I think I think he owns a big part of truth social. So, you know, if he does want to post on the X platform, we would allow that. You know, we obviously must allow presidential candidate to post on a platform.

The interactiveness is awesome.

Yeah, that's great. In fact, no system is going to be perfect, but the value average of the community notes is incredibly good. I've actually frankly yet to see an incorrect note that's about more than if you are. How do you explain why it works? Yeah, so the magic of community notes is it requires people who have historically disagreed in how they've rated notes. In order to write a note or rate, you have to rate many notes. And so we actually use AI here, so we've populated vector space around how somebody has rated notes in the past. So it's not as simple as left or right, because there are many more life as much will complex than left or right. So there's a bunch of correlations in how you rate a community notes post, community notes. So then in order for a community note to actually be shown, people who historically have disagreed on a subject must agree in order for a note to be shown. That's the essential magic of it.

It's fascinating. It works. Yeah. It kind of makes sense that if people who put the past have just agreed agree about something, it's probably true.

But Wikipedia is very hierarchical. Whereas community notes is inherently not. There is no hierarchy. The asset test is, I can't change a community note if I put a gun to my head. And any community notes has All the code is open source 100%. All the data is open source 100%. So you can completely recreate any note in the system independently. So if there was any interference, you'd notice immediately.

That's pretty funny. Rick, did I see it? I'm like, I was here as well. This is cool.

Which part? Well, the first part, I did actually have the funding secured, and there was a big trial in San Francisco, a big civil trial. And the jury found the inequality unanimous binding of San Francisco jury.

I think it's taking things from the press. Yeah, that is not correct. The reason I agreed to the fine for the SEC is not because the SEC was correct. That was extremely bad behavior by the SEC corruption, frankly. But if I did not agree to pay the fine, Tesla would have gone bankrupt immediately. So I was told by our CFO that the banks would immediately suspend our lines of credit. And if this has been our lines of credit at that time, we would have gone bankrupt instantly. So there would never have been an opportunity for a trial because Tesla would be dead. So really, this is like someone holding a gun to your kid's head and saying, pay $20 million. And it does like hostage negotiation.

It should be. But not once that the SEC go after any of the hedge funds who were non-stop shorting and distorting Tesla. Not once. The hedge funds would lie flat out on TV for their own gain, at the expense of retail investors. Not once, literally 1,000 times. Not once to the SEC pursue them.

The incentive structure is messed up. Because the lowest SEC are not paid well. It's a fairly low-fanged job, but what they're looking for is a trophy. From the SEC, they're looking for something and basically the LinkedIn, from that they can get a job at a high-paying law firm. It's exactly what the Larry here did. And the reason they don't attack the hedge funds is because those hedge funds employ those law funds. And they know if they attack the hedge funds, they're affecting their future career prospects. So they sell small investors down the river for their own career. That's what actually happens. regulatory capture. Yeah, not good. So the only reason I accepted that thing, or technically, was a, um, not an admission, it's neither an admit or an eye guilt. Uh, but the only reason I agreed to that at all was because I was told, Tesla would, would be bankrupt otherwise. So if there, if there was an SEC investigation like this, banks would suspend funding, we'd bankrupt immediately at the time. Now we're in a much stronger position. Take that, Gwak. Yes, unfortunately its Gwak is taking too much from the conventional media. Also, that guy was not a cave driver.

There was a court case, which the guy who was not a cave driver and played was not part of the rescue team, filed a lawsuit against me and lost, and he received nothing. So in this case, it is wrong. I guess taking this from the conventional media. actually there's an interesting question. These are probably court cases, but the SEC civil case where the civil complaints on the SEC guys lost unanimous jury verdict in San Francisco. They picked San Francisco because they thought it was the place I was most likely to lose. and a unanimous verdict in my favor. The LA trial was also, they picked that value because I thought I was most likely to lose unanimous verdict in my favor. Both cases I won.

We need to add the training set of the actual legal decisions. So that is a note. This is actually helpful because if you actually read the court public, which are public, the court conclusions, they're completely the opposite of what the media wrote.

Yeah. What did the judge actually write? What did the jury and the judge actually conclude? And in both cases, they found me in a sudden. And like that's after the jury shot for trying to find the venue where I'm most likely to lose. Now, I mean, obviously it can be a much greater critique than this. I mean, I've been far too optimistic about autopilot.

Yeah, I mean, I would say that I'm pathologically optimistic on schedule. This is true, but while I am sometimes late, I always live right in the end.

Yeah, I guess if it's considered fighting the the woke mind virus, which I consider to be a civilizational threat to be political then yes.

Yes, I don't know if this is necessarily sort of one candidate or another candidate, but it's, I'm generally against things that are anti-meritocratic or where there's an attempt to suppress discussion, where even discussing a topic is, you know, not allowed. The book bymires his communism rebranded.

If the woke is left, then I suppose that would be true. But I'm not sure, I think there are aspects of the left that are good. I mean, if you're in favor of the environment, or if you want to have a positive future for humanity, if you've even empathy for your fellow human beings, You know, bring kind and not cool, whatever those values are.

No, I would say that I would be. probably left a center on social issues, probably a little bit right of center on economic issues. And that's still a whole stroke. Yes, but I think that's probably, you know, half a country.

Um, I'm always in favor of humor. That's where we have a funny mode.

Yeah. I don't, well, I, you know, I don't know. I see if, you know, was, um, I've only been at one of the, I was at the, the mat wall when she was, when she attended, um, and she, she was wearing the stress, uh, But I can only see one side of it, so it looks like it the edge, but I don't know what the rest of it said.

Well, there's still hope. I'm, I root for friendship. Sure. Sounds good.

Trust no one, not even yourself, not trusting yourself. Okay. Well, that's, you're saying that joke. But is there someone, not even no one?

What does it do? Petrify. It turns the monsters into stone. Oh, like literally. Yeah, for like six seconds. All the seconds.

Yes, he can be definitely stressful at times.

I mean, I guess you look at somebody's track. We're going to have a time. And if they've dated out of, you know, I guess you kind of use your neural net to the SS, get out someone.

It can make it possible. You know, to be frank, I mean, I've, almost never been betrayed. Very, very, very. So, you know, for what it's worth.

Yeah, comments, real.

Well, the expert phone is very helpful for that. feel like you're for critical feedback.

I don't think I will be cynical. In fact, I think, you know, my feelings that one should be, you know, never trust a cynic. The reason is that cynics excuse their own bad behavior by saying everyone does it because they're cynical. So I always be, it's a red flag if someone's a cynic, a true cynic.

If, but this is an important point that I think people who are listening should bear in mind, if somebody is cynical, meaning that they see bad behavior and everyone, it's easy for them to excuse their own bad behavior by saying that well, everyone does it. It's not true. All right, most people are kind of medium-good.

Right, I find the expert won't be less negative than the legacy media. I mean, if you read sort of a sort of conventional newspaper is just, it makes you sad. Yeah, frankly. Whereas I say on the X5 form, I mean, I really get more laughs per day on X than everything else combined. From humans, you know.

Now, it's better than mainstream media, but it's still... Yeah, mainstream media is almost relightlessly negative about everything. I mean, really, the conventional news tries to answer the question, what is the worst thing that I happen on Earth today? And it's a big world. So, on any given day, it's something bad has happened.

So, yeah, I don't know this is a strong negative bias in the news. I mean, I think it's what a possible explanation for this is evolutionary. Where, you know, bad news historically would be potentially fatal. Like this line over there or this some other try that wants to kill you. Good news, you know, like we found a patch of berries is nice to have, but not essential.

Well, I mean, the really wild thing about the internet training is that it like it learns to read like it can read science, but we never told it to read.

Yeah, we never told it what we never told it what a car was or what a person was or a bicycle cyclist. It learnt what What all those things are? What all the objects are in the road? From video. Just from watching video. Just like humans. I mean, humans are photons and control controls out. Like the vast majority of information reaching out brain is from a rise. And you say, well, what's the output? The output is our motor signals to our sort of fingers and mouth in order to communicate. for tons and controls out. The same is true of the car.

It finds order in these things. It finds a correlative clusters.

They're both headed towards AGI. The Tesla approach is much more computer-fishing. It has to be, because we were constrained on this, you know, where I only have 100 watts. And in the eight computer, 144 trillion operations per second, which sounds like a lot, but it's kind of small potatoes these days. That in date. But it's understanding the world at a date. It's my turn for 26 values.

They're both going to understand the world, but I think Tesla's approach is fundamentally more computer-fishing. It had to be. There was no choice. Like, out-brain is very computer-fishing. It's very energy-fishing. So, I think we're like, what does our brain able to do? And there's only about 10 watts of higher brain function, not counting stuff that's just used to control our body. The thinking part of our brain is less than 10 watts. And those 10 watts can still produce a much better novel than a 10-megawatt GPU cluster. So there's a six-order magnitude difference there. I mean, as thus for our garden to where it is, we're via brute force, just throwing massive amounts of compute and massive amounts of power at it. So this is not where it will end up. In general with any given technology, first try to make it work and then you make it efficient. So I think we'll find over time that these models get smaller are able to produce, since we'll output with far less compute, far less power. Tesla is arguably ahead of the game on that front because it has, we've just been forced to try to understand the world with 100 watts of compute. And there were a bunch of fundamental functions that we kind of forgot to include, so we had to run a bunch of things in amulation. We fixed a bunch of those with hardware 4 and then hardware 5 will be even better. But it does appear at the point that the call will be able to drive better than a human, even with hardware 3 and a hundred watts of error. And really, if we really optimize it, it could be progress in 50 watts.

I was surprised at the fact that we had to develop every part of the robot ourselves, that there were no of the shelf motors, electronics, sensors, like we had to develop everything. We couldn't actually find a source of electric motors for any amount of money.

We tried hard to find anything that was... Because you think of how many electric motors have made in the world. There's like tens of thousands, hundreds of thousands of electric motor designs. None of them were suitable for a human right robot. Literally none. So we had to develop our own design, design is specifically for what a humanoid robot needs.

It is designed to be manufactured in the same way they would make a car. And I think ultimately we can make optimists for less than the cost of a car. It should be because if you look at the mass of the robot as much smaller, and the car has many actuators in it, the car is more actuators than the robot.

you know yeah and I could do some interesting manipulation so yeah soft touch robotics every one of the tests uh it goes I have is can it pick up a needle and a thread and thread the needle just by looking how far away we from that just by looking just by looking oh maybe a year although I go back to him after a mistake on time. The work that we're doing in the car will translate to the robot.

Now, the controls are different, but the video range controls out. The cars are about our four wheels. The, the, the, the optimuses are about with the ads and legs.

After this, we'll figure out how to do things by watching videos.

Yeah, sure.

Try to feed you will lose. No, I mean, you know. I mean, my mind is a storm. I don't think... I don't think most people would want to be me. They may think they would want to be me, but they don't know. They don't understand.

I'm in a role, okay? The grad scheme of things, I can't complain.

Sometimes. But I, you know, Mike, kids and friends keep me company.

There were many nights I sleep alone. I don't have to do, but I do.

What does forgiveness? I do not, at least I don't think I have a resentment. So, I don't think you have a

I mean, I try to think about what is going to affect the future in a good way. And holding onto grudges does not affect the future in a good way.

I mean developing AI and watching say the lex grow is fascinating because they are formal parallels than I would have expected. I mean I can see his biological neural net making more and more sense to the world and I can see the digital neural net making more and more sense to the world at the same time.

I mean, one of the things with kids is that, you know, you kind of see the world of new in their eyes. You know, to them, everything is new and fresh. And then when you see that, they make sure that the world is new and fresh, you do too.