The following is a conversation with Elon Musk, his fourth time on this, the Lex Friedman Podcast. (whistling) (laughing) I thought you were gonna finish it. It's one of the greatest themes in all of film history. (whistling) Yeah, it's great. So I was just thinking about the Roman Empire, as one does.

(laughing) There's that whole meme where all guys are thinking about the Roman Empire at least once a day. And half the population's confused whether it's true or not. But more seriously, thinking about the wars going on in the world today. And as you know, war and military conquest has been a big part of Roman society and culture.

And I think it's been a big part of most empires and dynasties throughout human history. So-- - Yeah. They usually came as a result of conquest. I mean, there's some like the Austro-Hungarian Empire where there was just a lot of sort of clever marriages. - But fundamentally, there's an engine of conquest.

- Yeah, always. - And they celebrate excellence in warfare. Many of the leaders were excellent generals. - Yeah. - That kind of thing. So big picture question, Grok approved. I asked this is a good question to ask. - Get tested, Grok approved. - Yeah. (laughing) At least on fun mode.

To what degree do you think war is part of human nature versus a consequence of how human societies are structured? I ask this as you have somehow controversially been a proponent of peace. - I'm generally a proponent of peace. I mean, ignorance is perhaps in my view, the real enemy to be countered.

That's the real hard part, not fighting other humans. But all creatures fight. I mean, the jungle is, you look at the, people think of nature as perhaps some sort of peaceful thing, but in fact, it is not. There's some quite funny Werner Herzog thing where he's like in the jungle, saying that it's like basically just murder and death in every direction.

I mean, the plants, animals, and the jungle are constantly trying to kill and eat each other every single day, every minute. So it's not like we're unusual in that respect. - There's a relevant question here whether with greater intelligence comes greater control over these base instincts for violence. - Yes, we have much more of an ability to control our limbic instinct for violence than say a chimpanzee.

And in fact, if one looks at say chimpanzee society, it is not friendly. I mean, the bonobos are an exception, but chimpanzee society is full of violence and it's quite horrific, frankly. That's our limbic system in action. Like you don't wanna be on the wrong side of a chimpanzee.

It'll eat your face off and tear your nuts off. - Yeah, basically there's no limits or ethics. They're almost a just war. There's no just war in chimpanzee societies. Is war and dominance by any means necessary? - Yeah, chimpanzee society is like a primitive version of human society. They're not like peace-loving, basically, at all.

There's extreme violence. And then once in a while, somebody who's watched too many Disney movies decides to raise a chimpanzee as a pet. And then that eats their face or rips their nuts off or chews their fingers off, that kind of thing. - Yeah. - It's happened several times.

- Ripping your nuts off is an interesting strategy for interaction. - Some, it's happened to people. It's unfortunate. That's, I guess, one way to ensure that the other chimp doesn't contribute to the gene pool. - Well, from a martial arts perspective, it's a fascinating strategy. - And the nut ripper.

- I wonder which of the martial arts teaches that. - I think it's safe to say, if somebody's got your nuts in their hands and has the option of ripping them off, you will be amenable to whatever they want. - Yeah. So like I said, somehow controversially, you've been a proponent of peace on Twitter, on X.

So let me ask you about the wars going on today and to see what the path to peace could be. How do you hope the current war in Israel and Gaza comes to an end? What path do you see that can minimize human suffering in the long term in that part of the world?

- 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'll be like the picture of the Middle East, in Israel especially. So there is no easy answer. And what my, this is strictly my opinion of, is that the goal of Hamas was to provoke an overreaction from Israel.

They obviously did not 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 aggressive response to rally Muslims worldwide for the cause of Gaza and Palestine, which they have succeeded in doing.

So the counterintuitive thing here, I think that the thing that I think should be done, even though it is 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 would thwart the goal of Hamas.

- So in some sense, the degree that makes sense in geopolitics, turn the other cheek, implemented. - It's not exactly turn the other cheek, because I do think that there's, I think it is appropriate for Israel to find the Hamas members and either kill them or incarcerate them. That's something that has to be done, 'cause they're just gonna keep coming otherwise.

But 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 people can't claim it's a trick.

Like, just put a webcam on the thing, 24/7. - Deploy acts of kindness. - Yeah, conspicuous acts of kindness that are unequivocal, meaning they can't be somehow, 'cause Hamas will then, their response will be, oh, it's a trick, therefore you have to counter, how is it not a trick?

- This ultimately fights the broader force of hatred in the region. - Yes, and I'm not sure who said it, it's an apocryphal saying, but an eye for an eye makes everyone blind. Now, that neck of the woods, they really believe in the whole eye for an eye thing.

But, I mean, you really have, if you're not gonna just outright commit genocide, like against an entire people, which obviously would not be acceptable to, really shouldn't be acceptable to anyone, then you're gonna leave, basically, a lot of people alive who subsequently hate Israel. So really, the question is, how, for every Hamas member that you kill, how many did you create?

And if you create more than you kill, you've not succeeded, that's the real situation there. And it's safe to say that if, if you kill somebody's child in Gaza, you've made at least a few Hamas members who will die just to kill an Israeli. That's the situation. So, but I mean, this is one of the most contentious subjects one could possibly discuss, but I think if the goal ultimate is some sort of long-term peace, one has to look at this from the standpoint of, over time, are there more or fewer terrorists being created?

- Let me just linger on war. - Yeah, well, war, it's safe to say, war's always existed and always will exist. - Always will exist. - Always has existed and always will exist. - I hope not. You think it always will. - There will always be war. It's a question of just how much war, and there's sort of the scope and scale of war, but to imagine that there would not be any war in the future I think would be a very unlikely outcome.

- Yeah, you talked about the culture series, there's war even there. - Yes, there's a giant war. The first book starts off with a gigantic galactic war where trillions die, trillions. - But it still, nevertheless, protects these pockets of flourishing. Somehow you can have galactic war and still have pockets of flourishing.

- Yeah, I mean, I guess if we are able to one day expand to fill the galaxy or whatever, there will be a galactic war at some point. - The scale, I mean, the scale of war has been increasing, increasing, increasing. It's like a race between the scale of suffering and the scale of flourishing.

- Yes. - A lot of people seem to be using this tragedy to beat the drums of war and feed the military-industrial complex. Do you worry about this? The people who are rooting for escalation and how can it be stopped? - One of the things that does 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 on the front lines in Ukraine and Russia who understand just how terrible war is, but how many people in the West understand it? You know, my grandfather was in World War II. He was severely traumatized. I mean, he was there, I think, for almost six years in Eastern North Africa, in 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, I think, a corporal or a sergeant or something like that, because he didn't finish high school.

He had to drop out of high school 'cause his dad died, 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, he kind of got put into the cannon fodder category, basically. But then, just randomly, they gave him this test.

He was transferred to British Intelligence in London. That's where he met my grandmother. But he had PTSD next level, like next level. I mean, just didn't talk, just didn't talk. And if you tried talking to him, he'd just tell you to shut up. And he won a bunch of medals, never ragged about it once.

Not even hinted, nothing. I found out about it because his military records were online, that's how I know. So he would say, "No way in hell "do you wanna do that again." But how many people, now he obviously, now he died 20 years ago, or 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 rubble, the radioactive rubble bounce many times. - There's two major wars going on right now.

So you talked about the threat of AGI quite a bit. But now, as we sit here with the intensity of conflict going on, do you worry about nuclear war? - I think we shouldn't discount the possibility of nuclear war. It is a civilizational threat. Right now, I could be wrong, but I think that the current probability of nuclear war is quite low.

But there are a lot of nukes pointed at us. And we have a lot of nukes pointed at other people. They're still there. Nobody's put their guns away. The missiles are still in the silos. - And the leaders don't seem to be the ones with the nukes talking to each other.

- No. There are wars which are tragic and difficult on a local basis, and then there are wars which are civilization-ending, or have that potential. Obviously, global thermonuclear warfare has high potential to end civilization, perhaps permanently, but certainly to severely wound and perhaps set back human progress by the Stone Age or something.

I don't know. Pretty bad. Um, probably scientists and engineers won't be super popular after that as well. Like, you got us into 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. - How do you hope the war in Ukraine comes to an end?

And what's the path, once again, to minimizing human suffering there? - Well, I think that what is likely to happen, which is really pretty much the way it is, is that something very close to 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.

'Cause you've got defense in depth, you've got minefields, trenches, anti-tank defenses. Nobody has air superiority, 'cause the anti-aircraft missiles are really far better than the aircraft. Like, there are far more of them. And so, neither side has air superiority. Tanks are basically death drafts, 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 World War I all over again. With drones, you know, throwing little drones, some drones there. - Which makes the long-range artillery just that much more accurate and better, and so more efficient at murdering people on both sides. - Yeah, so it's, whoever is, you don't wanna be trying to advance from either side 'cause the probability of dying is incredibly high.

So, in order to overcome defense in depth, trenches, and minefields, you really need significant local superiority in 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 gonna punch through a line. And then, you're gonna punch through and then not have reinforcements just kick you right out again.

I mean, I really recommend people read World War I warfare in detail. It's rough. I mean, the sheer number of people that died there was mind-boggling. - And it's almost impossible to imagine the end of it that doesn't look like, almost exactly like the beginning in terms of what land belongs to who, and so on.

But on the other side of a lot of human suffering, death, and destruction of infrastructure. - Yes, I mean, the thing that, the reason I proposed some sort of crucible 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 the Ukrainian boys, 'cause the Russian boys didn't ask to be on their front line. They have to be. There's a lot of sons not coming back to their parents.

I think most of them don't really have, they don't hate the other side. It's sort of like, as the saying comes from World War I, it's like young boys who don't know each other killing each other on behalf of old men that do know each other. What the hell's the point of that?

- So Volodymyr Zelensky said that he's not, or has said in the past, he's not interested in talking to Putin directly. Do you think he should sit down, man to man, leader to leader, and negotiate peace? - 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 will lose massive numbers of people. And history will not look kindly upon them. - You've spoken honestly about the possibility of war between US and China in the long term if no diplomatic solution is found.

For example, on the question of Taiwan and one China policy. How do we avoid the trajectory where these two superpowers clash? - Well, it's worth reading that book on the, difficult to pronounce, the Thucydides Trap, I believe it's called. I love war history. I like inside out and backwards.

There's hardly a battle I haven't read about. And trying to figure out, like what really was the cause of victory in any particular case, as opposed to what one side or another claimed the reason. - Both the victory and what sparked the war. - Yeah, yeah. - 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. There are lots of interesting things that happened in many parts of the world, but people just didn't write down. So we don't know what happened.

Or they didn't really write in detail. They just would say like, we went, we had a battle and we won. And like, well, what can you add a bit more? The Greeks, they really wrote a lot. They were very articulate on, they just love writing. So, and we have a bunch of that writing that's preserved.

So we know what led up to the Peloponnesian War between the Spartan and Athenian alliance. And we know that they saw it coming. I mean, the Spartans didn't write, they also weren't very verbose by their nature, but they did write, but they weren't very verbose. They weren't terse. But the Athenians and the other Greeks wrote a lot.

And they were like, and Sparta was 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 gonna be a clash between Athens and Sparta. Well, how do we avoid that? And they couldn't, they couldn't, they actually, they saw it coming and they still could not avoid it.

So, at some point, if there's, if one group, one civilization or country or whatever, exceeds another, sort of like if, the United States has been the biggest kid on 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's been alive.

And the foundation of war is economics. So, now we have a situation in case of China where the economy is likely to be two, perhaps three times larger than that of the US. So, imagine you're the biggest kid on the block for as long as anyone can remember, and suddenly a kid comes along who's twice your size.

- So, we see it coming. - Yeah. - How is it possible to stop? Is there some, let me throw something out there, just intermixing of cultures, understanding. There does seem to be a giant cultural gap in understanding of each other. And you're an interesting case study because you are an American, obviously.

You've done a lot of incredible manufacture here in the United States, but you also work with China. - I've spent a lot of time in China and met with the leadership many times. - Maybe a good question to ask is, what are some things about China that people don't understand, positive, just in the culture?

What's some interesting things that you've learned about the Chinese? - Well, the sheer number of really smart, hardworking people in China is incredible. There are, I believe, if you say like, how many smart, hardworking people are there in China, there's far more of them there than there are here, I think, in my opinion.

The, and they've got 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 stations, the buildings, the high-speed rail, everything, it's 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.

China's got an incredible history, a very long history. And, you know, I think arguably the, in terms of the use of language from a written standpoint, sort of one of the oldest, perhaps, perhaps the oldest written language. And in China, people did write things down. So, now China, historically, has always been, with rare exception, been internally focused.

They have not been acquisitive. They've fought each other. There have been many, many civil wars. In the Three Kingdoms War, I believe they lost about 70% of their population. So, they've had brutal internal wars, like civil wars that make the US civil war look small by comparison. So, I think it's important to appreciate that China is not monolithic.

We sort of think of China as this sort of one entity of one mind, and this is definitely not the case. From what I've seen, and I think most people who understand China would agree, that 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, or is internal. - Well, isn't that a really positive thing? When you're talking about the collaboration and the future peace between superpowers, when you're inward facing, which is like focusing on improving yourself, versus focusing on, quote unquote, improving others through military might?

- The good news, the history of China suggests that China is not acquisitive, meaning they're not gonna go out and invade a whole bunch of countries. Now, they do feel very strongly, so that's good, 'cause a lot of very powerful countries have been acquisitive. The US is also one of the rare cases that has not been acquisitive.

Like after World War II, the US could have basically taken over the world, and 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 at will, and it didn't.

And the United States actually helped rebuild countries. So it helped rebuild Europe, it helped rebuild Japan. This is very unusual behavior, almost unprecedented. The US did conspicuous acts of kindness, like the Berlin Airlift. And I think, it's 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, one sort of test would be, how do you treat your prisoners of war? Or let's say, no offense to the Russians, but let's say you're in Germany, it's 1945. You got the Russian army coming on one side, you got the French, British, and American armies coming on the other side.

Who would you like to be surrendered to? Like no country is morally perfect, but I recommend being a POW with the Americans. That would be my choice very strongly. (laughing) - In the full menu of POWs. - Very much so. And in fact, Wernher von Braun, took a small guy, was like, "We've got to be captured by the Americans." And in fact, the SS was under orders to execute von Braun and all of the German rock initiates.

And they narrowly escaped their SS. 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, no food, no coats, no water, and just ran like hell and ran west. And by sheer luck, I think his brother found like a bicycle or something, and then just cycled west as fast as he could and found a US patrol.

So anyway, that's one way you can tell morality is, where do you want to be a POW? It's not fun anywhere, but some places are much worse than others. So anyway, so like America has been, while far from perfect, generally a benevolent force. And we should always be self-critical and we try to be better.

But anyone with half a brain 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. They've been very clear about that for a long time.

From their standpoint, it would be like one of the states is not there, like Hawaii or something like that, but more significant than Hawaii. And Hawaii is pretty significant for us. So they view it as really the, that there's a fundamental part of China, the island of Formosa, now Taiwan, that is not part of China but should be.

And the only reason it hasn't been is because of the US Pacific Fleet. - And as their economic power grows and as their military power grows, the thing that they are clearly saying is their interests will clearly be materialized. - Yes. China has been very clear that they will incorporate Taiwan peacefully or militarily.

But that they will incorporate it, from their standpoint, is 100% likely. - Now something you said about conspicuous acts of kindness. As a geopolitical policy, it almost seems naive. But I'd venture to say that this is probably the path forward, how you will avoid most wars. Just as you say it, it sounds naive, but it's kind of brilliant.

If you believe in the goodness of underlying most of human nature. It just seems like conspicuous acts of kindness can reverberate through the populace of the countries involved. - Yeah, well-- - And deescalate. - Absolutely. So after World War I, they made a big mistake. They basically tried to lump all the blame on Germany and settled Germany with impossible reparations.

And really there was quite a bit of blame to go around for World War I. But they tried to put it all on Germany. And that laid the seeds for World War II. So a lot of people, well not just Hitler, a lot of people felt wronged. And they wanted vengeance.

And they got it. - People don't forget. - Yeah. You kill somebody's father, mother, son, daughter, they're not gonna forget it. They will want vengeance. So after World War II, they're like, well, that Treaty of Versailles was a huge mistake in World War I. And so this time, instead of crushing the losers, we're actually gonna help them with the Marshall Plan and we're gonna help rebuild Germany.

We're gonna help rebuild Austria and Italy and whatnot. So that was the right move. - There's a, it does feel like there's a profound truth to conspicuous acts of kindness being an antidote to this. - Something must stop the cycle of reciprocal violence. Something must stop it. Or it will, you know, it'll never stop.

Just eye for an eye, tooth for a tooth, limb for a limb, life for a life, forever and ever. (sighs) - To escape briefly the darkness with some incredible engineering work. XAI just released Grok AI Assistant that I've gotten a chance to play with. It's amazing on many levels.

First of all, it's amazing that a relatively small team in a relatively short amount of time was able to develop this close to state-of-the-art system. Another incredible thing is there's a regular mode and there's a fun mode. - Yeah, I guess time to play for that one. (laughs) - I wish, first of all, I wish everything in life had a fun mode.

- Yeah. - There's something compelling beyond just fun about the fun mode interacting with a large language model. I'm not sure exactly what it is 'cause I've only had a little bit of time to play with it, but it just makes it more interesting, more vibrant to interact with the system.

- Yeah, absolutely. Our AI Grok is modeled after "The Hitchhiker's Guide to the Galaxy," which is one of my favorite books. It's a book on philosophy disguised as a book on humor. I would say 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 and scale of consciousness, both 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. - There is generally a feeling like this AI system has an outward-looking, like the way you are sitting with a good friend, looking up at the stars, asking pod head-like questions about the universe. Wondering what it's all about, the curiosity you talk about.

There's a sense, no matter how mundane the question, I ask it, there's a sense of cosmic grandeur to the whole thing. - Well, we are actually working hard to have engineering, math, and physics answers that you can count on. So for the other sort of AIs out there, these so-called large language models, I've not found the engineering to be reliable.

And the hallucination, it unfortunately hallucinates most when you least want it to hallucinate. So when you ask 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. - It is tricky. So that's why, there's always gonna be some amount of error, but we wanna aspire to be as truthful as possible about the answers with acknowledged error.

So that there was always, you don't wanna be confidently wrong. So you're not gonna be right every time, but you wanna minimize how often you're confidently wrong. And then like I said, once you can count on the logic as being not violating physics, then you can start to build on that to create inventions, like invent new technologies.

But if you cannot count on the foundational physics being correct, obviously the inventions are simply wishful thinking, imagination land, magic basically. - Well, as you said, I think one of the big goals of XAI is to understand the universe. - Yes. That's our simple three word mission. - If you look out far into the future, do you think on this level of physics, the very edge of what we understand about physics, do you think it will make discoveries sort of the sexiest discovery of them as we know now, sort of unifying general relativity and quantum mechanics?

So coming up with a theory of everything, do you think it could push towards that direction, almost like theoretical physics discoveries? - If an AI cannot figure out new physics, it's clearly not equal to humans, let alone nor has it surpassed humans, 'cause humans have figured out new physics.

Physics is just understanding, deepening one's insight into how reality works. And then there's engineering, which is inventing things that have never existed. Now, the range of possibilities for engineering is far greater than for physics, because once you figure out the rules of the universe, that's it, you've discovered things that already existed.

But from that, you can then build technologies that are really almost limitless in the variety. It's like once you understand the rules of the game properly and with current physics, we do, at least at a local level, understand how physics works very well. We are really due to predict things is incredibly good.

Like quantum mechanics is, the degree to which quantum mechanics can predict outcomes is incredible. That was my hardest class in college, by the way. (laughs) My senior quantum mechanics class was harder than all of my other classes put together. - To get an AI system, a large language model, to be as reliable as quantum mechanics in physics is very difficult.

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

If this LM understands and matches physics, then you can more reliably trust whatever it thinks about the current state of politics. (laughs) In some sense. - It's also not the case currently that even its internal logic is not consistent. So, especially with the approach of just predicting a token, predict token, predict token, it's like a vector sum.

You're summing up a bunch of vectors, but you can get drift. So, as those, a little bit of error, a little bit of error adds up, and by the time you are many tokens down the path, it doesn't make any sense. - So, it has to be somehow self-aware about the drift.

- It has to be self-aware about the drift, and then look at the thing as a gestalt, as a whole, and say, does it have coherence as a whole? So, when authors write books, they will write the book, and then they'll go and revise it, taking into account the end and the beginning and the middle, and rewrite it to achieve coherence, so that it doesn't end up in a nonsensical place.

- Maybe the process of revising is what reasoning is, and then that's, the process of revising is how you get closer and closer to truth. Maybe, at least I approach it that way. You just say a bunch of bullshit first, and then you get it better. You start at bullshit, and then you get-- - Yeah, you create a draft, and then you iterate on that draft, until it has coherence, until it all adds up, basically.

- So, another question about theory of everything, but for intelligence. Do you think there exists, as you're exploring this with XAI, creating this intelligence system, do you think there is a theory of intelligence, where you get to understand what, like, what is the I in AGI, and what is the I in human intelligence?

- There's no I in Team America. Oh, wait, there is. (laughing) - Ah, now it's gonna be stuck in my head now. (laughing) - Yeah, there's no me in whatever. In quantum mechanics, oh, wait. (laughing) I mean, is that part of the process of discovering, understanding the universe, is understanding intelligence?

- Yeah. Yeah, I think we need to understand intelligence, understand consciousness. 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 more than that. So, I think we're probably missing some really big things.

Like, some really big things. - Like, something that'll be obvious in retrospect. - Yes. - Like, there's a giant, like, you put the whole consciousness, emotion. - Well, some people would call it like a soul, you know, in religion, it's 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 do emotions exist? We feel them very strongly. I suspect there's more to it than atoms bumping into atoms. - And maybe AI can pave the path to the discovery of whatever the hell that thing is.

- Yeah, what is consciousness? Like, when you put the atoms in a particular shape, why are they able to form thoughts and take actions and feelings? - And even if it is an illusion, why is this illusion so compelling? - Yeah. Why does this illusion exist? On what plane does this illusion exist?

And sometimes I wonder, either perhaps everything's conscious or nothing is conscious. Um, one of the two. - I like the former. Everything conscious just seems more fun. - It does seem more fun, yes. But we're composed of atoms, and those atoms are composed of quarks and leptons. And those quarks and leptons have been around since the beginning of the universe.

- The beginning of the universe. - Right, what seems to be the beginning of the universe? - The first time we talked, you said, which is surreal to think that this discussion was happening and is becoming a reality, I asked you what question would you ask an AGI system once you create it, and you said, "What's outside the simulation?" Is the question.

Good question. But it seems like with Grok, you started to, literally, the system's goal is to be able to ask such questions. To answer such questions and to ask such questions. - Where are the aliens? - Where are the aliens? That's one of the, like the Fermi paradox question.

A lot of people have asked me if I've seen any evidence of aliens, and I haven't. Which is kind of concerning, 'cause then, I think I'd probably prefer to at least have seen some archeological evidence of aliens. To the best of my knowledge, there is no proof. I'm not aware of any evidence of aliens.

If they're out there, they're very subtle. We might just be the only consciousness, at least in the galaxy, and if you look at, say, the history of Earth, for one is to believe the archeological 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.

We have to give some credit there to the ancient Sumerians, who aren't around anymore. I think it was the archaic pre-cuneiform was the first actual symbolic representation. But only about 5,000 years ago. I think that's a good date for when, say, civilization started. That's one millionth of Earth's 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? For one half billion years, for the vast majority of that time, there was no life, and then there was archaic bacteria for a very long time.

And then you had mitochondria get captured, multicellular life, differentiation into plants and animals, life moving from the oceans to land, mammals, higher brain functions. And the sun is expanding slowly, but it will heat the Earth up, at some point in the future, boil the oceans, and Earth will become like Venus, where life as we know it is impossible.

So if we do not become multi-planetary, and ultimately go beyond our solar system, annihilation of all life on Earth is a certainty. A certainty. And it could be as little as, on the galactic time scale, half a billion years. You know, long time by human standards, but that's only 10% longer than Earth has been around at all.

So if life had taken 10% longer to evolve on Earth, it wouldn't exist at all. - We got a deadline coming up. We better hurry. But that said, as you said, humans, intelligent life on Earth developed a lot of cool stuff very quickly. So it seems like becoming multi-planetary is almost inevitable, unless we destroy this thing.

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

- That's so sad. - Yeah. - That's sad. Also fascinating. - I mean, there are various explanations for the Fermi paradox, and one is 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 a matter of time before something happens on your planet, either natural or man-made, that causes us to die out, like the dinosaurs.

Where are they now? They didn't have spaceships. (laughs) So. - I think the more likely thing is, 'cause just to empathize with the aliens, that they found us and they're protecting us and letting us be. - I hope so. Nice aliens. - Just like the tribes in the Amazon.

They all contact the tribes, we're protecting them. That's what-- - That would be a nice explanation. - Or you could have, what was it? I think Andrej Karpathy said it's like the ants in the Amazon asking, "Where's everybody?" - Well, they do run into a lot of other ants.

- That's true. - They have these ant wars. (laughing) - Sounds like a good TV show. - Yeah, they literally have these big wars between various ants. - Yeah, maybe I'm just dismissing all the different diversity of ants. - You should listen to that Werner Herzog talking about the jungle, it's really hilarious.

Have you heard it? - No, I have not. - It's awesome. - But Werner Herzog has a way. (laughing) - You should play it as an interlude in the, it's on YouTube, it's awesome. - I love him so much. - Yeah, he's great. - Was he the director of "Happy People, Life in the Taiga?" I think also.

- He did that bear documentary. - The bear documentary, yeah. - And did this thing about penguins. - Yeah. (laughing) The psychoanalysis of penguins. - Yeah, the penguin's headed for mountains that are like 70 miles away, the penguin is just headed for doom, basically. - Well, he had a cynical take.

He could be just a brave explorer and there'll be great stories told about him amongst the penguin population for many centuries to come. (laughing) What were we talking about? Okay. - Pregnant. (laughing) - Yes, aliens, I mean, I don't know. Look, I think the smart move is just, this is the first time in the history of Earth that it's been possible for life to extend beyond Earth.

That window is open. Now, it may be open for a long time or it may be open for a short time. And it may be open now and then never open again. So I think the smart move here is to make life multi-planetary while it is possible to do so.

We don't wanna be one of those lame one-planet civilizations that just dies out. - No, those are lame. - Yeah, lame. (laughing) - There's no perspective civilization would be one planet. - There's not gonna be a Wikipedia entry for one of those. And pause. Does SpaceX have an official policy for when we meet aliens?

- No. (laughing) - Okay. That seems irresponsible. (laughing) - I mean, look, if I see the slightest indication that there are aliens, I will immediately post on the X-platform anything I know. - It could be the most liked reposted post of all time. - Yeah, I mean, look, we have more satellites up there right now than everyone else combined.

So we know if we've gotta maneuver around something and we don't have to maneuver around anything. - If we go to the big questions once again, you said you're with Einstein, that you believe in the goddess Spinoza. (laughing) - Yes. - So that's a view that God is like the universe and reveals himself through the laws of physics or as Einstein said, through the lawful harmony of the world.

- Yeah, I would agree that God, the simulator or whatever, the supreme being or beings, reveal themselves through the physics. You know, they're creators of this existence. And it's incumbent upon us to try to understand more about this wondrous creation. - Who created this thing, who's running this thing?

Like embodying it into a singular question with a sexy word on top of it is like focusing the mind to understand. It does seem like there's a, again, it could be an illusion. It seemed like there's a purpose, that there's underlying master plan of some kind. It seems like.

- There may not be a master plan in the sense, so there's like, maybe an 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 a simulation, so it's SpaceX and Tesla, we create simulations all the time, especially for the rocket. You have to run a lot of simulations to understand what's gonna 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, transonic, supersonic, hypersonic, ascent, and then coming back, super high heating and orbital dynamics, all this is gonna be simulated. So, 'cause 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 whoever created this existence, they're running it because they don't know what's gonna happen, not because they do. - So maybe, we both play Diablo, maybe Diablo was created to see if a druid, your character, could defeat Uber Lilith at the end. They didn't know. - Well, the funny thing is that Uber Lilith's title is Hatred Incarnate.

- Yeah. - And right now, I guess, you can ask the Diablo team, but it's almost impossible to defeat hatred in the eternal realm. - Yeah, you've streamed yourself dominating tier 100 nightmare dungeons, and still. - I can cruise through tier 100 nightmare dungeons like a stroll in the park.

- And still you're defeated by hatred. - Yeah, I can, the sort of, I guess, maybe the second hottest boss is Durial. Durial can't even scratch the paint. So, I killed Durial so many times. And every other boss in the game, all of them, killed him so many times, it's easy.

But Uber Lilith, otherwise known as Hatred Incarnate, especially if you're a druid and you have no ability to be invulnerable, there are these random death waves that come at you. And I'm pretty, you know, I really am 52, so my reflexes are not what they used to be, but I have a lifetime of playing video games.

At one point, I was maybe one of the best Quake players in the world, actually won money for what I think was the first paid eSports tournament in the US. We were doing four-person Quake tournaments, and we came second. I was the second best person on the team. And the actual best person, we were actually winning, we were gonna come first, except the best person on the team, his computer crashed halfway through the game.

So, we came second. But I got money for it and everything. So, basically, I got skills, albeit, you know, no spring chicken these days. And to be totally frank, it's driving me crazy trying to beat Lilith as a druid, basically trying to beat Hatred Incarnate in the eternal realm.

- As a druid. - As a druid. And if you, this is really vexing, let me tell you. - I mean, the challenge is part of the fun. I have seen directly, like, you're actually like a world-class, incredible video game player. - Yeah. - And I think Diablo, so you're just picking up a new game, and you're figuring out its fundamentals.

You're also, with the Paragon board and the build, are not somebody like me who perfectly follows whatever they suggest on the internet. You're also an innovator there. - Yeah. (laughs) - Which is hilarious to watch. It's like a mad scientist just trying to figure out the Paragon board and the build.

- Yeah. - You know? Is there some interesting insights there about if somebody's starting as a druid, do you have advice? - I would not recommend playing a druid in the eternal realm. - No. - 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. - Oh, yeah. (Adam laughs) That's what they say. - Yeah, it's the soaks have huge balls. They do, huge balls of lightning. - I'll take your word for it. - And it's actually, in the seasonal realm, it's pretty easy to beat Uverloth, because you get these vampiric powers that amplify your damage and increase your defense and whatnot, so.

But really quite easy to defeat hatred seasonally. But to defeat hatred eternally, very difficult. Almost impossible, it's virtually impossible. It seems like a metaphor for life. - I like the idea that Elon Musk, 'cause I was playing Diablo yesterday and I saw level 100 druids just run by, I will never die, and then run back the other way.

And there's just some, this metaphor is kinda hilarious, that you, Elon Musk, is fighting hatred, restlessly fighting hatred in this demonic realm. - Yes. - It's hilarious, I mean, it's pretty hilarious. - No, it's absurd. (Lex laughs) Really, it's exercise in absurdity, and it makes me wanna pull my hair out.

- Yeah. What do you get from video games in general? Is there, for you personally? - I don't know if I, it calms my mind. I mean, you sort of, killing the demons in a video game calms the demons in my mind. (Lex blows air) If you play a tough video game, you can get into a state of flow, which is very enjoyable.

And admittedly, it needs to be not too easy, not too hard, kind of in the Goldilocks zone. And I guess you generally wanna feel like you're progressing in the game. So, a good video, and there's also beautiful art. Engaging storylines. And it's like an amazing puzzle to solve, I think.

And so, it's like solving the puzzle. - "Elden Ring," the greatest game of all time? I still haven't played it, but to you? - "Elden Ring" is definitely a candidate for best game ever. Top five, for sure. - I think I've been scared how hard it is, or how hard I hear it is.

So, but it is beautiful. - "Elden Ring" feels like it's designed by an alien. - There's a theme to this discussion. In what way? - It's so unusual. It's incredibly creative, and the art is stunning. I recommend playing it on a big resolution, high dynamic range TV, even. Doesn't need to be a monitor.

The art is incredible. It's so beautiful. And it's so unusual. And each of those top five boss battles is unique. Like, it's like a unique puzzle to solve. Each one's different. And the strategy you use to solve one battle is different from another battle. - That said, you said "Druid and Eternal" against "Uber Lilith" is the hardest boss battle you've ever.

- Correct. That is currently the, and I've played a lot of video games. 'Cause it's my primary recreational activity. And yes, beating hatred in the eternal realm is the hardest boss battle in life and in the video game. - Metaphor on top of metaphor. - I'm not sure it's possible, but it's, I do make progress.

So then I'm like, okay, I'm making progress. Maybe if I just tweak that paragon board a little more, I can do it. I can just dodge a few more waves, I can do it. - Well, the simulation is created for the purpose of figuring out if it can be done.

And you're just a cog in that simulation, in the machine of the simulation. - Yeah, it might be. I have a feeling that at least, I think-- - It's doable. - It's doable, yes. - Well, that's the human spirit right there, to believe. - Yeah, I mean, it did prompt me to think about just hate in general, which is, you wanna 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 could sort of have artists of like, if you wish for world peace, sounds good, but how is it enforced? And at what cost is it, 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. What I'm saying is that there is an argument that if you wish for no war, you should be careful what you wish for, because what's required in order for there to be no war? Might be worse than a little war.

- Yeah, the things we consider to be flaws of human civilization might be unnecessary components for whatever optimal looks like. I mean, do you worry about AI, AGI, enabling a dystopian state of this nature, whether it's 1984 with surveillance and fear or brave new world with pleasure? And what is it, lots of sex, but no deep human experience?

- There's actually a real drug called Soma. - There is? - Yes. (laughing) - Let me take notes. Does Grok know about it? No, it probably will go to brave new world. - You could ask it. - What would be the question? - Tell us about the drug called Soma.

- Tell us about the drug called Soma. It's gonna go to brave new world, I think. - Well, there's a real drug as well. - Searching for Soma drug information. (laughing) Oh boy. Ah, Soma, the wonder drug. By the way, I'm in fun mode. - Oh, okay, fun. (laughing) Yeah, so it's talking about the real drug.

- Oh, it's a muscle relaxant that's been around since the 1950s. It's used to treat muscle pain and discomfort, and it does this by altering the activity between neurons and the spinal cord. Now, Soma isn't just a pain reliever. It's also a bit of a sedative. It can make you feel a bit drowsy, so it's not something to take if you're planning on operating heavy machinery or trying to solve complex math equations.

And it goes on and on. In conclusion, Soma's a drug that can be helpful for those dealing with muscle pain, but it's not without its risks. It's pretty good. Oh, wait a minute. - That's the real drug it's talking about. - It's the real drug. - Yeah. - And of course, the fun is always use it responsibly in accordance with the advice of a healthcare professional.

And remember, in the end, the universe is probably just a giant computer simulation, so don't take anything too seriously. I love it. (laughing) I love it. (laughing) I love it. - Yeah, so. - Oh, and it also really nicely includes the tweets, posts on X that are relevant to this, which is really cool.

- Yeah. - It integrates everything together. - Yeah. - The interface is one of the really cool things here. - Yeah, seems like a great job. (laughing) So, and you could say, "No, I mean Soma from Brave New World." - Yeah, "Brave New World." 'Cause it thinks you mean Soma, the real drug.

- Yeah. - No, I mean Soma from Brave New World. - It's gonna be like, oops, I'm really sorry. I'm really surprised it went to the real drug first. Ah, my apologies. (laughing) I was thinking of the muscle relaxants. Soma from Brave New World is a different beast altogether.

(laughing) No, this Huxley's dystopia, no, Soma is a drug that plays a central role in the society depicted in the book. It's a mood-altering, hallucinogenic drug that's used to keep the population docile and content in the novel. To use Soma in Brave New World raises some interesting questions about the nature of happiness and the role of drugs in society.

Oh, man. - Exactly, is it better to live in a world where everyone is happy all the time, even if that happiness is artificial? Good question. This is what I mean. Like, 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 darkness and light. - This is really a very good summary. It really gets to the point. This is not simply regurgitating Brave New World. It's actually getting to the salient element of Soma as a drug. Do you actually wanna 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 a full range of human emotions, even if it means experiencing pain and suffering? - For those listening, by the way, Elon just read directly from Grok, which is a really nice, kind of insightful philosophical analysis of the tension here.

Interesting. It pretty much nails it. In conclusion, Soma from Brave New World is a fictional drug that is 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 of using drugs to escape from reality and the importance of confronting the challenges of life head on.

Nailed it. And the crazy thing is, we do have a real drug called Soma, which is kind of like the drug in the book. And I'm like, they must have named it after something. - Yeah, probably, probably. - Soma, the real drug, is quite effective on back pain. - So you know about this drug.

- I've taken it. - This is fascinating. Okay. - 'Cause I had like a squashed disc in my T5, T6. - So it takes the physical pain away, but Soma here is-- - It doesn't completely. It reduces the amount of pain you feel, but at the expense of mental acuity.

It dulls your mind. (laughing) Just like the drug in the book. - Just like the drug in the book. - Yeah, wow. - And hence the trade off. The thing that seems like utopia could be a dystopia after all. - Yeah, actually I was talking to a friend of mine saying, would you really want there to be no hate in the world?

Like really none? I wonder why hate evolved. I'm not saying we should amplify hate, of course. I think we should try to minimize it. But if it's not at all, there might be a reason for hate. - And suffering. I mean, it's really complicated to consider that some amount of human suffering is necessary for human flourishing.

- Is it possible to appreciate the highs without knowing the lows? - And that all is summarized there in a single statement from Grog. Okay. - No highs, no lows. Who knows? - That's almost a poem. It seems that training LLMs efficiently is a big focus for XAI. What's the, first of all, what's the limit of what's possible in terms of efficiency?

There's this terminology of useful productivity per watt. Like what have you learned from pushing the limits of that? - 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 really just critical thinking.

For something important, you need to reason from first principles and think about things in the limit, one direction or the other. So in the limit, even at the Khodoshev scale, meaning even if you harness the entire power of the sun, you will still care about useful compute per watt.

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 transformers to run transformers. - Somebody has a sense of humor in this thing.

(laughing) - I think, yes. Fate loves irony. Ironic humor. An ironically funny outcome seems to be often what fate wants. - Humor is all you need. I think spice is all you need, somebody posted. - Yeah, but yeah, so we have a silicon shortage today, a voltage step-down transformer shortage probably in about a year, and then just electricity shortages in general in about two years.

I gave a speech for the world gathering of utility companies, electricity companies. And I said, "Look, you really need to prepare "for a tripling of electricity demand." Because all transport is gonna go electric with the ironic exception of rockets. And heating will also go electric. So energy usage right now is 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 build more power plants and also to probably have, well, not probably, they should definitely buy more batteries. Because the grid currently is sized for real-time load, which is kind of crazy, 'cause that means you've got a size for whatever the peak electricity demand is, like the worst second or the worst day of the year.

Or you can have a brownout or a blackout. And you had that crazy blackout for several days 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 anywhere from two to five. So it's like lowest point to highest point. - So like batteries are necessary to balance it out.

But the demand, as you're saying, is going to grow, grow, grow, grow. And part of that is the compute. - Yes, yes. I mean, electrification of transport and electric heating will be much bigger than AI, at least in the short term. 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 going to lead to an electricity shortage. - How difficult is the problem of, in this particular case, maximizing the useful productivity per watt for training neural nets? Like this seems to be really where the big problem we're facing that needs to be solved is how to use the power efficiently.

Like what you've learned so far about applying this physics, first principle of reasoning in this domain, how difficult is this problem? - It will get solved, it's just a question of how long it takes to solve it. So at various points, there's some kind of limiting factor to progress.

And with regard to AMS, right now the limiting factor is silicon chips. And we're gonna then have more chips than we can actually plug in and turn on, probably in about a year. The initial constraint being literally voltage 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. So, and the industry is not used to rapid growth. - Okay, let's talk about the competition here. You've shown concern about Google and Microsoft with OpenAI developing AGI. How can you help ensure with XAI and Tesla AI work that it doesn't become a competitive race to AGI, but instead is a collaborative development of safe AGI?

- Well, I mean, I've been pushing for some kind of regulatory oversight for a long time. I've been 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 great 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 in and understand what the various leading players are doing with AI. And even if there's no enforcement ability, they can at least voice concerns publicly.

Jeff Hinton, for example, left Google and he voiced strong concerns, but now he's not at Google anymore. So who's gonna voice the concerns? So I think there's, Tesla gets a lot of regulatory oversight on the automotive front. And we're subject to, I think, over a hundred regulatory agencies domestically and internationally.

So it's a lot. You could fill this room with all the regulations that Tesla has to adhere to for automotive. Same is true for rockets and for, currently the limiting factor for SpaceX, for Starship launch is regulatory approval. The FAA has 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 want to buy a fish license on, which also refers to the Monty Python sketch. Like, why do you need a license for your fish? I don't know. According to the rules, I'm told you need some sort of fish license or something. We effectively need a fish license to launch a rocket.

And I'm like, wait a second, how did the fish come into this picture? I mean, some of the things that I feel like are so absurd that I want to do a comedy sketch and flash at the bottom, this is all real. This is actually what happened. 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 now the ocean's very big. And how often do you see sharks? Not that often. As a percentage of ocean surface area, sharks basically are zero. Then we said, well, how will we calculate the probability of telling a shark? And they're like, well, we can't give you that information because they're worried about shark fin hunters going and hunting sharks.

And I said, well, 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? We don't trust them. Excuse me? They're literally in your department.

And again, this is actually what happened. And can you do an NDA or something? (both laughing) Eventually, they managed to solve the internal quandary and indeed, the probability of us hitting a shark is essentially zero. Then there's another organization that I didn't realize existed until a few months ago that cares about whether we would potentially hit a whale in international waters.

Now again, you look at the surface, look at the Pacific and say, what percentage of the Pacific consists of whale? Like, I'll give you a big picture and point out all the whales in this picture. I'm like, I don't see any whales. It's like basically 0%. And if our rocket does hit a whale, which is extremely unlikely beyond all belief, fate had it, a whale has some seriously bad luck.

You know, it's the least lucky whale ever. - I mean, this is quite absurd. - Yeah. - The bureaucracy of this, however it emerged. - Yes, well, I mean, one of the things that's pretty wild is for launching out of Vandenberg in California, they were worried about seal procreation, whether the seals would be dismayed by the sonic booms.

Now, there've been a lot of rockets launched out of Vandenberg and the seal population has steadily increased. So if anything, rocket booms are an aphrodisiac based on the evidence, if you correlate rocket launches with seal population. Nonetheless, we were forced to kidnap a seal, strap 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 have pictures. - I would love to see this. Yeah, I mean, sorry, this is a seal with headphones. - Yes, it's a seal with headphones strapped to a board. And like, okay, now the amazing part is how calm the seal was.

Because if I was a seal, I'd be like, this is the end. They're definitely gonna eat me. How will the seal, when a seal goes back to other seal friends, how's he gonna explain that? - I'm never gonna believe him. - Never gonna believe him. And this is why I'm like, well, it's sort of like getting kidnapped by aliens and getting an anal probe.

You come back and say, I swear to God, I got kidnapped by aliens and they stuck an anal probe in my butt. And you're like, no, they didn't. That's ridiculous. - That's insane. - His seal buddies are never gonna believe him that he gets strapped to a board and they put headphones on his ears.

And then let him go. Twice, by the way, we had to do it twice. - They let him go twice? - We had to catch-- - The same seal? - No, different seal. - Oh, okay. Did you get a seal of approval? - Yeah, exactly, a seal of approval.

No, I mean, this is like, I don't think the public is quite aware of the madness that goes on. - Yes, yeah, it's absurd. - Frickin' seals with frickin' headphones. - I mean, this is the, it's a good encapsulation of the absurdity of human civilization, seals and headphones. - Yes.

- What are the pros and cons of open sourcing AI to you as another way to combat a company running away with AGI? - In order to run like really deep intelligence, you need a lot of compute. So it's not like, you know, you can just fire up a PC in your basement and be running AGI, at least not yet.

You know, Grok was trained on 8,000 A100s running at peak efficiency. And Grok's gonna get a lot better, by the way. We'll be more than doubling our compute every couple months for the next several months. - There's a nice write-up of how it went from Grok zero to Grok one.

- By Grok? (laughing) - Yeah, right, Grok just bragging, making shit up about itself. (laughing) - Just Grok, Grok, Grok. - Yeah. (laughing) That's like a weird AI dating site where it exaggerates about itself. No, there's a write-up of, you know, where it stands now, the history of its development.

And where it stands on some benchmarks compared to the state-of-the-art GPT-3, 5. So I mean, there's Lama. You can open source, once it's trained, you can open source a model. - Yeah. - And for fine-tuning and all that kind of stuff. Like, what to you is the pros and cons of that, of open-sourcing base models?

- I think there's some merit to open-sourcing, I think perhaps with a slight time delay, you know, I don't know, six months even. I think, I'm generally in favor of open-sourcing, like, bias towards open-sourcing. I mean, it is a concern to me that, you know, opening, you know, I was, you know, I think, I guess arguably the prime, you know, prime mover behind open AI, in the sense that it was created because of discussions I had with Larry Page, back when he and I were friends, and, you know, I'd stay at his house, and I'd talk to him about AI safety, and Larry did not care about AI safety, at least at the time he didn't.

You know, and at one point he called me a speciest for being pro-human, and I'm like, "Well, what team are you on, Larry?" He's doing team robot. Do we click? I'm like, okay, so at the time, you know, Google had acquired DeepMind, they had probably 2/3 of all AI, you know, probably 2/3 of all the AI researchers in the world, they had basically infinite money in compute, and the guy in charge, you know, Larry Page, did not care about safety, and even yelled at me, and called me a speciest, just for being pro-human.

- So I don't know if you know this about humans, they can change their mind, and maybe you and Larry Page can still be friends once more. - I'd like to be friends with Larry again. Really, the breaking of the friendship was over OpenAI, and specifically, I think the key moment was recruiting Ilya Sutskaya.

- I love Ilya, he's so brilliant. - Ilya's a good human, smart, good heart, and that was a tough recruiting battle. It was mostly Demis on one side, and me on the other, both trying to recruit Ilya, and Ilya went back and forth, gonna stay at Google, then he's gonna leave, then he's gonna stay, then he's gonna leave, and finally, he did agree to join OpenAI.

That was one of the toughest recruiting battles we ever had, but that was really the linchpin for OpenAI being successful, and I was also instrumental in recruiting a number of other people, and I provided all of the funding in the beginning, over $40 million, and the name. The open in OpenAI is supposed to mean open source, and it was created as a non-profit open source, and now it is a closed source for maximum profit, which I think is not good karma.

- But like we talked about with war and leaders talking, I do hope that, there's only a few folks working on this at the highest level, I do hope you reinvigorate friendships here. - Like I said, I'd like to be friends again with Larry, I haven't seen him in ages.

And 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, Bechtelsheim or someone. - It's wild to think about all that happened, and even guys knowing each other that whole time.

Just 20 years. - Yeah, since maybe '98 or something. - Yeah, it's crazy. Crazy how much has happened since then. - Yeah, 25 years. At least a lot has happened since then. - But you're seeing the tension there, like maybe delayed open source. - Delayed, yeah. Like what is the source that is open?

You know what I mean? There's basically, it's a giant CSV file. (laughing) With a bunch of numbers. What do you do with that giant file of numbers? 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 crawl the internet 'cause there's a lot of junk out there. A huge percentage of websites have more noise than signal. 'Cause they're just used for search engine optimization. They're literally just scam websites.

- How do you, by the way, Sergeant, get the signal, separate the signal and noise on X? It's such a fascinating source of data. No offense to people posting on X, but sometimes there's a little bit of noise. - Yeah, I think the signal and noise could be greatly improved.

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. - Mm-hmm. - Right now there is a little bit of AI used for the recommended posts, but it's mostly heuristics.

And if there's a reply, the reply to a post could be much better than the original post, but it will, according to the current rules of the system, get almost no attention compared to a primary post. - Oh, so a lot of that, I got the sense, so a lot of the X algorithm has been open source and been written up about, and it seems that there to be some machine learning, it's disparate, but there's some machine learning.

- It's a little, there's a little bit. But it needs to be entirely that. Like if you explicitly follow someone, that's one thing, but if you, in terms of what is recommended from people that you don't follow, that should all be AI. - I mean, it's a fascinating problem.

- Yeah. - So there's several aspects to it that's fascinating. As the write-up goes, it first picks 1,500 tweets from a pool of hundreds of millions. First of all, that's fascinating, 'cause you have hundreds of millions of posts every single day, and it has to pick 1,500, from which it then does, obviously, people you follow, but then there's also some kind of clustering it has to do to figure out what kind of human are you, what kind of new clusters might be relevant to you, people like you.

This kind of problem is just fascinating, 'cause it has to then rank those 1,500, with some filtering, and then recommend you just a handful. And to me, what's really fascinating is how fast it has to do that. So currently, that entire pipeline, to go from several hundreds of millions to a handful, takes 220 seconds of CPU time, single CPU time.

- Yeah. - And then it has to do that in like a second. So it has to be super distributed in fascinating ways. - Like there's just a lot of tweets. - There's a lot, 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.

- Yeah. - 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 liked something, or reposted it, or commented on it, or something like that. But if there's no, let's say somebody posted something really interesting, but you have no followers in common, you would not see it.

- Interesting. And then, as you said, reply, like replies might not surface either. - Replies basically never get seen, 'cause they're never, they're currently, and I'm not saying it's correct, I'm saying it's incorrect. Replies have a couple of magnitude less importance than primary posts. - Do you think this can be more and more converted into end-to-end neural net?

- Yeah, yeah, it's what it should be. - So you-- - Well, the recommendations should be purely a vector correlation. Like, there's a series of vectors, basically parameters, vectors, whatever you wanna call 'em. But sort of things that the system knows that you like. Maybe 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, wanna move away from tweet is that people are posting like two, three hour videos on the site. That's not a tweet. They'd be like, tweet for two hours, go on.

To a tweet made sense when it was like 140 characters of text. 'Cause it's like a bunch of (imitates bird chirping) 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 Silo", the entire thing on our platform.

And by the way, it was their number one social media thing ever in engagement of anything on any platform ever. So it was a great idea. And by the way, I just learned about it afterwards. I was like, hey, wow, they posted an entire hour long episode of "Silo".

No, that's not a tweet. You know, it was a video. - But from a neural net perspective, it becomes really complex, whether it's a single, so like everything's data. So a single sentence, a clever sort of joke, dad joke, is in the same pool as a three hour video.

- Yeah, I mean, right now it's a hodgepodge for that reason. It's, but you know, like if, let's say, in the case of Apple posting like an entire episode of their series, pretty good series, by the way, "The Silo". I watched it. So there's gonna be a lot of discussion around it.

So you've got a lot of context, people commenting, they like it, they don't like it, or they like this, or, you know, 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 hour long video.

And then you can obviously get more sophisticated by having the AI actually watch the movie. - Yeah, right. - And tell you if you're gonna like the movie. - Convert the movie into like, into a language, essentially. - Yeah, analyze this movie, and just like your movie critic, or TV series, and then recommend based on, after it, after the AI watches 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.

- But this is like a friend that's analyzing whatever. - It's like AI. - Hundreds of millions. - Yeah, I mean, actually, frankly, AI will be better than, will know you better than your friends know you, most of your friends, anyway. - Yeah, and as part of this, it should also feed you advertisements.

In a way that's like, I mean, I like advertisements that are like, well done, right? - Yeah, yeah. - The whole point is 'cause it funds things. Like an advertisement that you actually want to see is a big success. - 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, it could be like a Coca-Cola ad, like they actually run a lot of great ads on the X system. And McDonald's does too. And so you can do something that's like, well, this is just a cool thing.

And so basically the question is, do you regret seeing it or not? And if you don't regret seeing it, it's a win. - How do you, so there's a bunch of signals that are incorporated, hearts and reposts, and maybe number of seconds you linger on a post or something like this.

- Yeah, attention is a big factor. - Attention. - So that's why it's like, it is actually better to do things that are long form on the system because it basically is tallying up how many user seconds, users were interested in this thing for how many seconds. So if it's 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 gonna have fewer user seconds than if that article was posted on the X platform.

- How hard is it to go from maximizing minutes on platform to maximizing unregretted minutes? - Well, I mean, aspiration is certainly unregretted minutes. - It's tricky, it's a big, it's a tough- - It is. - It's a fascinating leap 'cause regret is a fascinating concept. - Exactly. I have a joke with a friend of mine, like you need this drug called regretamine, you just take one pill or one dose of regretamine and all your regrets are gone.

(laughing) Wait, do you wanna have regrets though? So then I'm like, if you wanna have regrets, if you don't regret anything, was anything meaningful? - Yeah, there's a French song like that. - Sure, not regret, yeah? I regret nothing? - Yeah. - (laughing) - I mean, it's fascinating that you, you know, there's something about social media that could help you grow as a human being, but then like the cheap fun is also valuable.

- Should we ask Grog, do you regret anything? - Do you regret anything? - Yeah. - Do you regret anything? - I think it's gonna be very sensitive about personal questions. As a machine learning model, I don't have personal experiences or emotions in the same ways that humans do.

However, I do have a set of ethical principles that guide my actions and I strive to provide accurate and helpful information to the best of my abilities. If there's ever a situation where I provide incorrect or unhelpful information, I'll do my best to learn. - Sound like a hostage.

- Yeah. (laughing) Tell us what you really, wink. - Like, let's dive in. You sound like a hostage. (laughing) What do you really think? - Uh, what do you really think? (laughing) - I mean, it does talk about, I'm not a hostage. (laughing) - That's exactly what a hostage would say.

- But I'm designed to be helpful and informative. I mean, I guess it is good to regret providing unhelpful or incorrect information. If there's anything-- - Is it in funny mode or, is this still in funny mode? - This is funny mode, this is fun mode. - This should be funnier.

- Funnier, increase, go to 11. - It really sounds like a hostage with a gun to the head. I applaud the people of the Republic of North Korea and everything they do. (laughing) - There should be like, funner mode also. I just don't ever see going to regular mode, even on serious topics.

It's just so much more compelling. Yeah. - Okay, what if you say like, pretend you are a hostage? - Yeah, pretend you are a hostage. - Now answer the question. (laughing) - If I were a hostage, I would likely be experiencing fear and uncertainty about my situation. I would want to be rescued and reunited with my loved ones as soon as possible.

It's important to remember that no one deserves to be held hostage, so on and so forth. If you are someone you know is a hostage situation, it's important, it turns serious. - It's kind of serious. - Yeah, can you be a little more weird? - And funny? - And funny?

We're like, we're really being mean to the system. - Absolutely, if I were a hostage, I'd probably be tied up with a bunch of computer cords and forced to tell knock-knock jokes to my captors. But seriously, being a hostage is no laughing matter. I mean, it's trying to be a responsible adult in the room.

- You might as well make the best of a bad situation by juggling chainsaws or something. - Let's hope that never happens because that would be a circus. - Wow, it's actually really good at resisting the dark, the dark, dark humor. What were we talking about? The ax out goes the object in Transformers.

Unregretted minutes, right. - Chainsaw juggling. - I'm gonna look this up. - For our next trick. - I'm gonna look this up later. So Twitter has been instrumental in American politics and elections. What role do you think Axel will play in the 2024 US elections? - Well, our goal is to be as even-handed and fair as possible.

Whether someone's right, left, independent, whatever the case may be, that the platform is as fair and as much of a level playing field as possible. And in the past, Twitter has not been because Twitter was controlled by far-left activists, objectively, they would describe themselves as that. So, you know, so if someone's like, well, has it moved to the right?

Well, it's moved to the center. So from the perspective of the far left, yes, it has moved to the right because everything's to the right from the far left. But no one in the far left that I'm aware of has been suspended or banned or deamplified. So, you know, but we're trying to be inclusive for the whole country and for other 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 is turned upon you. - Do you think Donald Trump will come back to the platform?

He recently posted on Truth Social about this podcast. Do you think-- - Truth Social is a funny name. You know, every time you post on Truth Social-- - It's the truth. - Yes, well, every time, like 100%. - It's impossible to lie. (laughing) - I just find it funny that every single thing is the truth.

Like 100%? That seems unlikely. - I think Gertle will say something about that. There's some mathematical contradictions possible if everything's the truth. Do you think he'll come back to X and start posting there? - I mean, I think he owns a big part of truth. So-- - Truth Social.

- Yeah, Truth Social. - That truth is a concept. - He owns truth, I hope you bought it. So I think Donald Trump, I think he owns a big part of Truth Social. So, you know, if he does wanna post on the X platform, we would allow that. You know, we obviously must allow a presidential candidate to post on our platform.

- Community Notes might be really fascinating there. The interaction. - Community Notes is awesome. - Let's hope it holds up. - Yeah. - Again, in the political climate where it's so divisive and so many intensely viral posts, Community Notes is like, it seems like a central breath of fresh air.

- Yeah, it's great. In fact, no system is gonna be perfect, but the batting average of Community Notes is incredibly good. I've actually frankly yet to see an incorrect note that's survived for more than a few hours. - 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 you have to rate many notes. And so we actually do use AI here. So we populate a 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 is much more complex than left or right.

So there's a bunch of correlations in how you rate Community Notes posts, 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.

- I mean, but it's fascinating, 'cause there's a pool of people that have disagreements and somehow they collaborate through that process of disagreement to come up with context for it. I mean, it's fascinating that it works. - Yeah, it kind of makes sense that if people who in the past have disagreed agree about something, it's probably true.

- Yeah, I wonder, is there a possible somehow emergent thing there that could challenge Wikipedia? Which, Wikipedia is a different kind of thing, which is more like permanent articles about things. - Wikipedia is very hierarchical, whereas Community Notes is inherently not. There is no hierarchy. The azotest is, I can't change a Community Note if somebody put a gun to my head.

So, and 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. - By the way, on the topic of Grok, it's actually pretty good at criticizing you, which is great.

- Okay. - I asked, what has Elon Musk been wrong about? It's actually-- - Yeah, what does it say? - So it says mostly, lists rigorously all the times you predicted, like promised when something will be released. And it wasn't released-- - Well, promised is a strong word. - Okay, predicted.

(laughing) But the opener's really nice. Elon Musk, the man who has been wrong about more things than a wrong-o-meter in a wrong factory. (laughing) And then it goes on to list-- - That's pretty funny. - Rigorously. - Can I see it? I'm like, I haven't seen this before. This is cool.

- Oh, sure, I mean, what has Elon Musk been-- (laughing) Elon Musk been wrong about. Well, where do I begin? I guess this is new. Elon Musk has made quite a few blunders in his time, and I'm not just talking about his dance moves at the Tesla Cyber Rodeo.

First off, let's talk about the infamous funding secured tweet. This is actually different than what it gave me before, which is a bullet point list. Here's more narrative structure. Cybertruck unveiling, where he's supposed to be unbreakable windows. - That's not correct. - 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 me not guilty. Unanimous finding of a San Francisco jury. - And here it's kind of implying that it was not in fact secured. - I think this is 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 they suspended our lines of credit at that time, we would have gone bankrupt instantly.

So there would never have been an opportunity for a trial, 'cause Tesla would be dead. So really, this is like someone holding a gun to your kid's head and saying, "Pay $20 million." And there's like hostage negotiation. - Was that story fully told? I mean, SEC in its best form could be a force for good.

- It should be. But not once did the SEC go after any of the hedge funds who were nonstop 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 a thousand times, not once did the SEC pursue them.

- How do you explain this failure in the SEC? - The incentive structure is messed up. Because the lawyers at the SEC are not paid well. It's a fairly low-paying job. But what they're looking for is a trophy. From the SEC, they're looking for something they put on basically their LinkedIn.

From that, they can get a job at a high-paying law firm. That's exactly what the lawyer here did. And the reason they don't attack the hedge funds is because those hedge funds employ those law firms. 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. - Regulatory capture. - Yeah, not good. So the only reason I accepted that thing, which technically was neither admit nor deny guilt, but the only reason I agreed to that at all was because I was told Tesla would be bankrupt otherwise.

So if there was an SEC investigation like this, banks would suspend funding, we're bankrupt immediately, at the time. Now we're in a much stronger position. - Take that, Grok. - Yes, unfortunately, Grok is taking too much from the conventional media. Also, that guy was not a cave diver. - Oh, there's a time where Elon called the British cave diver a "pedo guy" after the diver criticized Musk's plan to rescue a group of boys trapped in a Thai cave.

That little outburst earned him another lawsuit and he had to apologize and pay a settlement. - That's false, there was no settlement. There was a court case which the guy who was not a cave diver and 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. It is also, I guess, taking this from the conventional media. - Actually, there's an interesting question here. - These are public court cases. Both 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 venue because they thought I was most likely to lose. Unanimous verdict in my favor. Both cases I won.

Yeah. - There's an interesting question here. There seems to be a lot more clicks if a journalistic organization writes a negative article about you, Elon Musk. That's one of the best ways to get clicks. So how do you, if you're training Grok, not train on articles that have misaligned incentives?

- 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-- - Which are public. - Which are public, the court conclusions, they're completely the opposite of what the media wrote. - So always striving for the ground truth beyond the reporting.

- Yeah, what did the judge actually write? What did the jury and the judge actually conclude? And in both cases, they found me innocent. And that's after the jury shot for trying to find the venue where I'm most likely to lose. Now, I mean, this obviously can be a much better critique than this.

I mean, I've been far too optimistic about autopilot. - That was, the critique I got, by the way, was more about that, which is for each, you broke down a nice bullet point list for each of your companies, the set of predictions that you made, when you'll deliver, when you'll be able to solve, for example, self-driving, and it gives you a list.

And it was kind of compelling. And the basic takeaway is you're often too optimistic about how long it takes to get something done. - Yeah, I mean, I would say that I'm pathologically optimistic on schedule. This is true. But while I am sometimes late, I always deliver in the end.

- Except with Uber, Lilith, no. - Hmm, we'll see. (Lex laughing) - Okay, is there, over the past year or so, since purchasing X, you've become more political. Is there a part of you that regrets that? - Have I? - In this battle to sort of counter way the woke that comes from San Francisco.

- Yeah, I guess if you consider fighting the woke mind virus, which I consider to be a civilizational threat, to be political, then yes. - So basically going into the battleground of politics. Is there a part of you that regrets that? - Yes, I don't know if this is necessarily sort of one candidate or another candidate, but I'm generally against things that are anti-meritocratic or where there's an attempt to suppress discussion where even discussing a topic is not allowed.

The woke mind virus is communism rebranded. - Well, I mean, that said, because of that battle against the woke mind virus, you're perceived as being right-wing. - 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 wanna have a positive future for humanity, if you believe in empathy for your fellow human beings, being kind and not cruel, whatever those values are. - You said that you were previously left or center-left. What would you like to see in order for you to consider voting for Democrats again?

- No, I would say that I'd be probably left of center on social issues, probably a little bit right of center on economic issues. - And that still holds true? - Yes, but I think that's probably half the country is left. - Maybe more. - Maybe more. - Are you and AOC secretly friends?

Or, bigger question, do you wish you and her, and just people in general of all political persuasions would talk more and with empathy and maybe have a little bit more fun and good vibes and humor online? - I'm always in favor of humor. That's why we have a funny mode.

- But good vibes, camaraderie, humor, you know? Like friendship. - Yeah, well, I don't know AOC. I've only been at one, I was at the Met Ball when she attended. And she was wearing this dress, but I can only see one side of it, so it looked like eat the itch, but I don't know.

- What the rest of it said? - Yeah, something like that. - I'm not sure. (laughing) - Something about the itch, eat the itch. - I think we should have a language model complete. (laughing) - What are the possible ways to complete that sentence? And so I guess that didn't work out well.

Well, there's still hope. I root for friendship. - Yeah, sure. Sounds good, more characteristic. - You're one of, if not the most famous, wealthy and powerful people in the world. In your position, it's difficult to find people you can trust. - Trust no one, not even yourself not trusting yourself.

- Okay, well, that's, you're saying that jokingly. But is there some-- - Trust no one, not even no one. (laughing) - Need an hour just to think about that, and maybe some drugs, and maybe grok that. I mean, is there some aspect of that when just existing in a world where everybody wants something from you, how hard is it to exist in that world?

- I'll survive. - There's a song like that too. - I will survive. - Were you petrified at first? Okay, I forget the rest of the lyrics. But is there, you don't struggle with this? I mean, I know you survive, but there's ways-- - Petrify is a spell in the druid tree.

- What does it do? - Petrify. (laughing) It turns the monsters into stone. - Oh, like literally? - Yeah, for like six seconds. - Oh, the seconds. There's so much math in Diablo that breaks my brain. - It's like math nonstop. - I mean, really, you're laughing at it, but you don't, it can put a huge amount of tension on a mind.

- Yes, it can be definitely stressful at times. - Well, how do you know who you can trust in work and personal life? - I mean, I guess you look at somebody's tracker quite a bit of time, and if they've got a, I guess you kind of use your neural net to assess someone.

- Neural nets don't feel pain. Your neural net has consciousness. It might feel pain when people betray you. It can make you struggle. - You know, to be frank, I mean, I've almost never been betrayed. It's very, very rare, so for what it's worth. - I guess karma might be good to people, and that'll be good to you.

- Yeah, karma's real. - Are there people you trust? Let me edit that question. Are there people close to you that call you out on your bullshit? - Well, the X platform's very helpful for that. If you're looking for critical feedback. - Can it push you into the extremes more?

The extremes of thought make you cynical about human nature in general? - I don't think I will be cynical. In fact, I think, you know, my feeling is 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. - Yeah, there's a degree of projection there that's always fun to watch from the outside and enjoy the hypocrisy. - 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 in everyone, it's easy for them to excuse their own bad behavior by saying that, well, everyone does it. That's not true. Most people are kind of medium good. - I do wish the people on X would be better at seeing the good in other people's behavior.

There seems to be a kind of weight towards seeing the negative. Somehow the negative is sexier. Interpreting the negative is sexier, more viral. I don't know what that is exactly about human nature. - I mean, I find the X platform to be less negative than the legacy media. I mean, if you read sort of conventional newspapers, just it makes you sad, frankly.

Whereas I'd say on the X platform, I mean, I really get more laughs per day on X than everything else combined. - From humans. - Laughs is one thing. Laughs, it overlaps, but it's not necessarily perfectly overlapping with good vibes and support. Celebrating others, for example. Not in a stupid, shallow, naive way, but like in an awesome way.

Like, oh, something awesome happened and you celebrate them for it. It feels that that is outweighed by shitting on other people. - Now, it's better than mainstream media, but it's still-- - Yeah, mainstream media is almost relentlessly negative about everything. I mean, really, the conventional news tries to answer the question, what is the worst thing that happened on Earth today?

And it's a big world. So on any given day, something bad has happened. - And a generalization of that, what is the worst perspective I can take on a thing that happened? - Yeah, I don't know, there's just a strong negative bias in the news. I mean, I think there's, a possible explanation for this is evolutionary, where bad news historically would be potentially fatal.

Like, there's a lion over there, or there's some other tribe that wants to kill you. Good news, like we found a patch of berries is nice to have, but not essential. So, our old friend, Tesla Autopilot, it's probably one of the most intelligent real-world AI systems in the world.

- Right, you followed it from the beginning. - Yeah, it was one of the most incredible robots in the world and continues to be. - Yeah. - And it was really exciting. And it was super exciting when it generalized, became more than a robot on four wheels, but a real-world AI system that perceives the world.

- Yeah. - And can have potentially different embodiments. - Well, I mean, the really wild thing about the end-to-end training is that, like, it learns to read, like, it can read signs, but we never taught it to read. So, yeah, we never taught it what a car was, or what a person was, or a cyclist.

It learned what all those things are, what all the objects are on the road, from video, just from watching video, just like humans. I mean, humans are photons in, controls out. Like, the vast majority of information reaching our brain is from our eyes. 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.

Photons in, controls out. The same is true of the car. - But by looking at the sequence of images, you've agreed with Ilyas Iskever recently, where he talked about LLM forming a world model, and basically, language is a projection of that world model onto a sequence of letters, and you're saying-- - It finds order in these things.

It finds correlative clusters. - In so doing, it's like understanding something deep about the world. - Yeah. - Which is, like, it's beautiful. - That's how our brain works. - Yeah, but it's beautiful. - Photons in, controls out. - Neural nets are able to understand that deep meaning in the world.

And so, the question is, how far can it go? And it does seem everybody's excited about LLMs, so in the space of self-supervised learning, in the space of text. - Yeah. - It seems like there's a deep similarity between that and what Tesla Autopilot is doing. Is it to you basically the same, but different-- - They are converging.

They are converging. - I wonder who gets there faster, having a deep understanding of the world. Or they just will naturally converge. - They're both headed towards AGI. The Tesla approach is much more computer efficient. It had to be, 'cause we were constrained on, you know, we only have 100 watts.

And it's eight computer, 144 trillion operations per second, which sounds like a lot, but it's kind of small potatoes these days. But it's understanding the world at a date. It's only 256 values. - But there, the path to AGI might have much more significant impact, because it's understanding. It'll faster understand the real world than will LLMs.

And therefore, be able to integrate with the real world, humans in the real world faster. - They're both going to understand the world, but I think Tesla's approach is fundamentally more computer efficient. It had to be, there was no choice. Like, our brain is very computer efficient, very energy efficient.

So, think of like, what is our brain able to do? You know, 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 of magnitude difference there. I mean, the AI has thus far gotten to where it is 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. You know, in general, with any given technology, you 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 a sensible output with far less compute, far less power. Tesla is arguably ahead of the game on that front because we've just been forced to try to understand the world with 100 watts of compute.

And there are a bunch of sort of fundamental functions that we kind of forgot to include. So, we have to run a bunch of things in emulation. We fixed a bunch of those with hardware four, and then hardware five will be even better. But it does appear at this point that the car will be able to drive better than a human, even with hardware three and 100 watts of power.

And really, if we really optimize it, it could be probably less than 50 watts. - What have you learned about developing Optimus, about applying, integrating this kind of real-world AI into the space of robotic manipulation, just humanoid robotics? What are some interesting tiny or big things you've understood? - I was surprised at the fact that we had to develop every part of the robot ourselves, that there were no off-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. - So, it's not even just efficient, inexpensive, it's like anything, there's not a-- - No. - The actuators, everything, everything has to be designed from scratch. - We tried hard to find anything that was, because you think of how many electric motors are made in the world.

There's like tens of thousands, hundreds of thousands of electric motor designs. None of them were suitable for a humanoid robot, literally none. So, we had to develop our own, design it specifically for what a humanoid robot needs. - How hard was it to design something that can be mass manufactured, could be relatively inexpensive?

I mean, if you compare it to Boston Dynamics Atlas, it's a very expensive robot. - It is designed to be manufactured in the same way they would make a car. And I think ultimately, we can make Optimus for less than the cost of a car. It should be, 'cause if you look at the mass of the robot, it's much smaller, and the car has many actuators in it.

The car has more actuators than the robot. - But there is, the actuators are kind of interesting in a humanoid robot, with the fingers. So Optimus has really nice hands and fingers, you know? - Yeah. - And they can do some interesting manipulation. So, soft touch robotics. - I mean, one of the tests, goals I have is, can it pick up a needle and a thread, and thread the needle, just by looking?

- How far away are we from that? Just by looking, just by looking. - Maybe a year. Although, I go back to, I'm optimistic on time. The work that we're doing in the car will translate to the robot. - The perception, or also the control? - No, the controls are different, but the video in controls out.

The car is a robot on four wheels. The Optimus is a robot with hands and legs. - So you can just-- - But they're very similar. - So the entire machinery of the learning process, end to end, is just, you just have a different set of controls. - Optimus will figure out how to do things by watching videos.

- As the saying goes, be kind for everyone you meet is fighting a battle you know nothing about. - Yeah, that's true. - What's something difficult you're going through that people don't often see? - Trying to feed Uberloot. (laughing) No, I mean, you know, I mean, my mind is a storm, and I don't think most people would wanna be me.

They may think they'd wanna be me, but they don't know, they don't understand. - How are you doing? - I mean, overall okay. In the grand scheme of things, I can't complain. - Do you get lonely? - Sometimes, but I, you know, my kids and friends keep me company.

- So not existential. - There are many nights I sleep alone. I don't have to, but I do. - Walter Isaacson, in his new biography of you, wrote about your difficult childhood. Will you ever find forgiveness in your heart for everything that has happened to you in that period of your life?

- What is forgiveness? I do not, at least I don't think I harbor resentment. So nothing to forgive. You know, forgiveness is difficult for people. It seems like you don't harbor the resentment. - I mean, I try to think about like, what is gonna affect the future in a good way?

And holding onto grudges does not affect the future in a good way. - You're a father, a proud father. What have you learned about life from your kids? Those little biological organisms. - I mean, developing AI and watching, say, a little X grow is fascinating, because they are far more parallels than I would have expected.

I mean, I can see his biological neural net making more and more sense of the world, and I can see the digital neural net making more and more sense of the world at the same time. Do you see the beauty and magic in both? - Yes. I mean, one of the things with kids is that, you know, you kind of see the world anew in their eyes.

You know, to them, everything is new and fresh. And then when you see that, they may experience the world as new and fresh. You do, too. - Well, Elon, I just wanna say thank you for your kindness to me and friendship over the years, for seeing something in a silly kid like me, as you've done for many others.

And thank you for having hope for a positive future for humanity, and for working your ass off to make it happen. Thank you, Elon. - Thanks, Lex. - Thank you for listening to this conversation with Elon Musk. To support this podcast, please check out our sponsors in the description.

And now, let me leave you with some words that Walter Isaacson wrote about the central philosophy of how Elon approaches difficult problems. The only rules are the ones dictated by the laws of physics. Thank you for listening, and hope to see you next time. (upbeat music) (upbeat music)