The following is a conversation with Elon Musk, his fourth time on this, the Lex Friedmann podcast. Now, if you allow me, a quick few-second mention of each sponsor, check them out in the description. It's the best way to support this podcast. We got Element for electrolyte deliciousness, Eight Sleep for naps, BetterHelp for Your Mind, Simply Safe for Your Safety, Shopify for Your Online Shopping, and NetSuite for Business, Management, Software. Choose wisely, my friends. Also, if you want to work with our amazing team where I was hiring, go to Lexfreedman. Com/hiring. And now onto the full ad reads. As always, no ads in the middle. I try to make these interesting, but if you must skip them, please still check out the sponsors. I enjoy their stuff. Maybe you will too. This episode is brought to you by the very thing I'm drinking as I speak to you right now, Element. Electrolyte, drink, and I'll usually fill a Powerade or a Gatorade bottle. I think it's 28 ounces of water and mix it with one element packet. My favorite flavor is watermelon salt. That's the one I'm drinking now. That's the one I've been drinking for a long time.

I apologize because I'm recording these words very late at night. It's been a long day. It's been a long night before that and a long night, this one. It's just me in front of a microphone right now looking at a 28-ounce bottle of water that tastes like water balloon. Just me and the water, happily reunited in the desert of human experience. I'm also surrounded by three computer screens that all have beautiful wallpaper looking at me, taunting me with beautiful picturesque scenes of nature. I had just, before this, played about 10 minutes of Diablo, where I got to escape to a whole other world that is also picturesque, but not with nature, but filled with the intense, intimidating sounds of demons attacking you from all sides. And all of that is somehow relaxing. Anyway, Element is not just delicious. It combines this perfect amount of magnesium, pot calcium, and sodium, watermelon, and salt. Anyway, get a sample pack for free with any purchase. Try it at drinkelament. Com/lex. This episode is also brought to you by the thing that's calling my name at this very moment, the Eight Sleep pod three mattress. It has two sides of the bed, so you can cool or heat each side of the bed separately.

I've actually recently briefly had a get-together of a lot of really interesting people, and somebody brought up the topic of 8Sleep. I just heard that a bunch of other folks said, Oh, I love A-Sleep, and they started talking about the different temperatures that they use. I was shocked and horrified to learn that some people actually heat their bed up. This was a fascinating discovery for me because I've never even tried the heating feature. I always cool the bed. Sometimes it's very cold with a warm blanket, it's heaven. But I can't recommend it enough. Sleep really is a magical place. It's a bit surreal saying these words while quiet sleep deprived, a bit melancholic, a bit hopeful. Thinking about the eight-sleep bed just a few steps away, and somehow that thought fills me with gratitude for just having these things in my life. Anyway, check them out and get special savings when you go to eightsleep. Com/lex. This episode is also brought to you by BetterHelp, spelled H-E-L-P, Help. Anytime I spell out a word, I always imagined myself spelling out that word in giant letters and sand, stranded alone on the island looking at an airplane, floating above, hoping that they see the text that right, help.

I just actually got a text from a friend. I'm looking at it now. Again, filled with gratitude for having so many amazing people, the text says, Hey, brother, just sending you some love. Miss you. Sent late at night. Oh, boy. Yeah, yeah, yeah. So better help. Speaking of friends, it's good to talk. It's good to talk to people. It's good to talk to people that truly listen. That could be friends, loved ones, or that could be a professional therapist. Well, you don't have to choose one. You can have all of those. Easy, accessible therapist is what BetterHelp is all about. Check them out at Betterhelp. Com/lex and save in your first month. That's betterhelp. Com/lex. This show is also brought to you by SimplySafe. As we go on with this program, I'm starting to have more and more fun because fun is all you need. Simplysafe is a home security company after, of course, you establish security. Once you're safe, then the fun can begin. For me, Simplisaf just establishes that first base layer of physical security. It's super easy to set up. They have a cool new feature called Fast Protect Monitoring that allows Simplisaf monitoring agents to see, speak to, and deter intruders through thesmart, alarm, indoor camera.

I'm tempted to test the system by having one of the quadropads, the legged robots, roll up to it and see what the agents say. Just attached to a ChatGPT, GPT-4 agent or a groc agent on top of it and have the two of them have a conversation and see what they figure out. I'm not sure it's going to end well, but science proceeds one experiment at a time, friends. Anyway, I love how easy Simplasave was to set up. Their sensors are awesome. Their monitoring is awesome. It's affordable, easy to use. I love products that just easy to set up, easy to maintain, everything works. Easy. Anyway, go to simplysave. Com/lex to get 50 % off any Simplasave system when you sign up for FastProtect monitoring. That's simplysave. Com/lex. This show is also brought to you by Shopify, a platform designed for anyone to sell anywhere. And when I say anyone, I mean somebody like me. It took me minutes, maybe even seconds to set up a store and sell shirts, which you can now buy at, I think the link is Lexfreedom. Com/store that forwards you to the Shopify store with three different shirts. In this case, it's not really about the store.

It's about just celebrating stuff we love. I'm a huge fan of a lot of bands and podcasts, and I just love buying up their merch, wearing it, and seeing who notices. I love wearing a Huberman lab shirt on the trail when I run and just see who recognizes the full absurdity of it, what they say. It's just wonderful and the joy that we can share by this little sign that you're wearing yourself that, Oh, I like this particular thing. Let's talk about it. Yeah, I love it. I like wearing Orwell shirts or Dosteevsky shirts or Bukowski shirts or sci-fi stuff, 2001, Space Honestly, all of it. You can get all of those things or sell those things on Shopify. Sign up for a one dollar per month trial period at Shopify. Com/lex. That's all lower case. Go to Shopify. Com/lex to take your business to the next level today. This show is also brought to you by NetSuite, an all-in-one cloud business management system. They take care of all the messy, complicated things involved in running a business. A company like Elon says, is a super intelligent being comprised of individual human beings working together in interesting ways that, one, effective can be greater than some of their parts.

But there's a lot of things involved there. It's not just great design and engineering. It's not great innovation. It's all of the things, the financials, the human resources of hiring and firing. It's maintaining inventory. It's the e-commerce. It's all the messy business details. So you should use the best tools for the job of handling that mess, that beautiful, beautiful mess involved in running a company. And I, too, by the way, would love to be a part of that mess. A small cog in the machine, in the super intelligent machine that is a company someday soon. Anyway, you can start now with no payment or interest for six months. Go to netsuite. Com/lex to access their one-of-a-kind financing program. That's Netsuite. Com/lex. And now, dear friends, here's Elon Musk. Yeah. I thought you were going to finish it. It's one of the greatest themes in all film history.

Yeah, it was great.

I was just thinking about the Roman Empire, as one does.

There's that whole meme where old guys are thinking about the Roman Empire at.

Least once a day. And half the population is confused whether it's true or not. But more seriously, thinking about the wars going on in the world today. 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.

Yeah, they usually came as a result of conquest. There's something like the Ocea-Hungary Empire where there was just a lot of clever marriages.

But fundamentally, there's an engine of conquest, and they celebrate excellence in warfare. Many of the leaders were excellent generals. Yeah, that thing. So big picture question, Groc-approved. I asked if this is a good question to ask.

Contested, Grok-approved?

Yeah, 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. Ignorance is perhaps, in my view, the real enemy to counter it. That's the real hard part, not fighting other humans. But all creatures fight. I mean, the jungle... You look at the... People think of this nature as perhaps some peaceful thing, but in fact, it is not. There's some quite funny Wernherhut thing where he's like in the jungle saying that it's basically just murder and death in every direction. I mean, the plants, animals, and the jungle are constantly trying to kill each other every single day, every minute. So it's not like we're unusual in that respect.

There's a relevant-I have a 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 chimpansey. And in fact, if one looks at, say, a chimpansey society, it is not friendly. I mean, the bonobos are an exception, but chimpansey society is full of violence, and it's quite horrific, frankly. That's our Olympic system in action. Like, you know, you'll be on the wrong side of a chimpansey. You'll eat your face off and tear your nuts off.

Yeah, basically there's no limits or ethics or... They're almost a just war. There's no just war in the chimpansey societies. Is war and dominance by any means necessary?

Yeah, chimpansey society is like a primitive version of human society. They're not 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 their hands as a pet. And then that eats their face or rips their nuts off or tries to pick their fingers off or that thing. Yeah. It's happened several times.

Ripping your nuts off is an interesting strategy for interaction.

It's happened to people. It's unfortunate. That's, I guess, a 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.

The nut ripper.

I wonder which of the martial arts.

Teaches that. I think it's fair to say if somebody's got your nuts in their hands and you have the option of rubbing them off, you will be amenable to whatever they want. Yeah.

Like I said, somehow controversially, you've been a proponent of peace on Twitter, on X. 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 paths do you see that can minimize human suffering in the long term in that part of the world?

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. There is no easy answer. On what... This is strictly my opinion 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 Hal as nine, 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, everything. That is the actual thing that would thwart the goal of Hamas.

So in some sense, the degree that makes sense in geopolitics turned 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 something has to be done because they're just going to 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. People can't claim it's a trick. Like just put a wavecam on the thing, all 24/7.

Deploy acts of kindness.

Yeah, conspicuous acts of kindness that are unequivocal, meaning they can't be somehow... Because Hamas will then... Their response will be, Oh, it's a trip. Therefore, you have to counter, How is not a trip?

This ultimately fights the broader force of hatred in the region.

Yes. I'm not sure who said it to 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 I for an I thing. But you really have... If you're not going to 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 going to leave basically a lot of people alive who subsequently hate Israel. So really the question is like, how for every Hamas member that you kill, how many did you create? And if you create more than you killed, you've not succeeded. That's the real situation there. And it's safe to say that if you kill somebody's child in Gaza, if you've made at least a few Hamas members who will die just to kill an Israeli. That's the situation. But I mean, this is one of the most contentious subjects one could possibly discuss. But I think if the goal ultimately is some long-term piece, one has to look at this from a 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 wars or 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 the scope and scale of war. But to imagine that there would not be any war in the future I think would be 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 guess if we are able to one day expand to full the galaxy or whatever, there will be a galactic war at some point.

The scale of war has been increasing and increasing and 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 the East and 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 high school because his dad died and he had to work to support his siblings. Because he didn't graduate high school, he was not eligible for the Officer Corps. He got put into the cannon, footer 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 bragged about it once and not even hinted nothing. I found out about it because his military records were online. That's how I know. So he would say like, No way in hell do you want to do that again? But how many people... 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 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 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 has 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 to the Stone Age or something. I don't know. Pretty bad. Probably scientists and engineers want to be super popular after that as well. They're like, You got us into this mess. So generally, I think we obviously want to prioritize civilisational risks over things that are painful and tragic on a local level, but not civilisational.

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 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 just have a situation right now where whoever goes on the offensive will suffer casualties at several times the rate of whoever is on the defense. Because you've got defense in death, you've got minefields, trenches, anti-tank defenses. Nobody has air superiority because the anti-aircraft missiles are really far better than the aircraft. They're far more of them. And so neither side has air superiority. Tanks are basically death traps, just slow moving, and they're not immune to anti-tank weapons. So you really just have long-range artillery and infantry branches. It's World War I all over again with drones, throwing old drones and some drones there.

Which makes the long-range artillery just that much more accurate and better and more efficient at murdering people on both sides.

Yeah. So whoever is... You don't want to be trying to advance from either side because the probability of dying is incredibly high. So in order to overcome defense in-depth trenches and minefields, you really need a significant local superiority 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 going to punch through a line. And then you're going to punch through and then not have reinforcements just kick you right out again. I really recommend people read World War I warfare in detail. That's rough. I mean, the sheer number of people that died there was mind-boggling.

And it's almost impossible to imagine the end of it that doesn't look 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 cruise 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, because the Russian boys don't ask to be on their front lines. They have to be. There's a lot of sons not come back to their parents. I think most of them don't really have... They don't hate the other side. You know, it's like... There's this saying about this 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 is the point of that?

So Vladimir 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 you talk to Putin or not, just don't do that. Whoever that 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. Right. How do we avoid the trajectory where these two superpowers clash?

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

Both the victory and what sparked the war and.

The.

Whole thing.

Yeah. So Athens and Sparta is a 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. We don't know what happened. Or they didn't really write in detail. They just would say like, We had a battle and we won. Can you add a bit more? The Greeks, they really wrote a lot. They were very articulate on it. They just love writing. We have a bunch of that writing that's preserved. We know what led up to the Pelopeneesian War between the Espoton and Ethereumian Alliance. We know that they saw it coming. The Spartans didn't write. They also weren't very verbose by their nature, but they did right. But they weren't very verbose. They were tourists. But the Athensians and the other Greeks wrote a line. And they were like... And Spartans was really like the leader of Greece. But Athens grew stronger and stronger with each passing year. And everyone's like, Well, that's inevitable that there's going to be a clash between Athens and Sparta. Well, how do we avoid that?

And they couldn't... They saw it coming and they still could not avoid it. So at some point, if one group, one civilization or country or whatever, exceeds another. The United States has been the biggest kid in the block since, I think, around 1890 from an economic standpoint. So the United States has been the 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. Imagine you have 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 are 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, say, 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. 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 recommend somebody just go to Shanghai and Beijing, look at the buildings and take the train from Beijing to Cheyon, where you have the Terracote Warriors. China has got an incredible history, a very long history. I think arguably in terms of the use of language from a written standpoint, one of the oldest, perhaps the oldest written language. And then China, people did write things down. Now, China historically has always been, with rare exception, been internally-focused. They've not been acquisitive. They've fought each other. They've been many, many civil wars. In the Three Kingdoms War, I believe they lost about 70 % of the population. They've had brutal internal wars, like civil wars that make the US Civil War look small by comparison.

I think it's important to appreciate that China is not monolithic. We think of like China as this 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, 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 internal.

Well, isn't that a really positive thing? When you're talking about the collaboration and the future piece 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 going to go out and invade a whole bunch of countries. Now, I do feel very strongly. So that's good, because a lot of very powerful countries have been acquisitive. The US is also one of the rare cases that has not been acquisitive. After World War II, the US could have basically taken over the world in any country like, We got nukes, nobody else got nukes. We don't have to lose soldiers. Which country do you want? The United States could have taken over everything at will. And it didn't. The United States actually helped rebuild countries to help rebuild Europe, helped rebuild Japan. This is very unusual behavior, almost unprecedented. The US did conspicuous acts of kindness like the Berlin Airlift. I think it's always like, Well, America has done bad things. Well, of course, America has done bad things, but one needs to look at the whole track record. Just generally, one test would be, how do you treat your prison as a 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 one side, you got the French, British, and American armies coming the other side. Who would you like to be to surrender to? Like, no country is like, marly perfect, but I recommend being a POW with the Americans. That would be my choice very strongly.

In the full menu of POWs.

Very much so. And in fact, Von der Van Browne took, a small guy. It was like, We've got to be captured by the Americans. And in fact, the SS was under orders to execute Van Browne and all of the German rock engineers. 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. They ran like, No food, no coats, no water, and just ran like hell and ran west. And by share like they, I think his brother found like a bicycle or something and and 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 PW? It's not fun anywhere, but some places are much worse than others. 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 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 this standpoint, it would be like one of the states is not there like Hawaii or something like that, but more significant than Hawaii. 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-specific fleet.

And is their economic power grows and is 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.

You know, 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 avoid most wars. Just as you say it, it sounds naive, but it's 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.

And de-escalate.

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 a lot of, there was quite a bit of blame to go around for World War I. But they try to put it all in Germany. And that laid the seeds for World War II. I'd said a lot of people were 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 going to 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 going to help them with the Marshall Plan and we're going to help Revolt Germany. We're going to help Revolt Austria and the other Italy and whatnot. That was the right move.

It does feel like there's a profound truth to conspicuous acts of kind as being an antidote to this.

Something must stop the cycle of reciprocal violence. Something must stop it or it'll never stop. Just eye for an eye, tooth for a tooth, limb for a limb, life for a life forever and ever.

To escape briefly the darkness was some incredible engineering work. Xai just released Groc 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 moat and there's a fun moat.

Yeah, I guess I'm to blame for that one.

First of all, I wish everything in life had a fun moat. There's something compelling beyond just fun about the fun moat interacting with a large language model. I'm not sure exactly what it is because 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 Groc is modeled after The Hitchhike as the Guide to the Galaxy, which is one of my favorite books, which is a book on philosophy, disguises 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, digital and biological, the more we are able to understand what the answer is to ask about the answer that is the universe. I have a philosophy of curiosity.

There is generally a feeling like this AI system has an outward-looking... The way you are sitting with a good friend, looking up at the stars, asking podhead-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 AIs out there, the so-called large language models, I've not found the engineering to be reliable. And the hallucination... It, unfortunately, hallucinateswhen you least want it unfortunately hallucinates most when you at least wanted to hallucinate.

So.

When you ask important, difficult questions, that's when it tends to be confidently wrong. We're really trying hard to say, Okay, how do we be as grounded as possible so you can count on the results? I 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 going to be some amount of error, but do we want to aspire to be as truthful as possible about the answers with acknowledged error. There was always... You don't want to be confidently wrong. You're not going to be right every time, but you want to minimize half when you're confidently wrong. 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 how simple three-word mission. Yeah.

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 the sexiest discovery of them as we know now, 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 surpassed humans, because humans have figured out new physics. Physics is just understanding, deepening one's insight into how reality works. 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. We doWith current physics, we do, at least at a local level, understand how physics works very well, our ability to predict things is incredibly good. Quantum mechanics is... The degree to which quantum mechanics can predict outcomes is incredible. That's one of my hottest class in college, by the way. 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 and 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 that... Break the laws made by man, but none break the laws made by physics.

It's a good test, actually. If this MLM understands and matches physics, then you can more reliably trust whatever it thinks about the current state of politics.

In a sense. And it's also not the case currently that its internal logic is not consistent. So especially with the approach of just predicting a tokenpredict 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 have 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 it doesn't have coherence as a whole. When authors write books, that 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 nontentical 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 a bullshit, and then you get it closer.

Yeah, you create a draft, and then you iterate on that draft until it has coherence, until it all adds up, basically.

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 is the I in AGI? And what is the I in human intelligence?

There's no I in team America. Oh, wait, there is.

I know it's going to be stuck in my head now. Yeah, there's no me and whatever in quantum mechanics. Oh, wait. 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 fundamental questions of 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. Some really big things.

Something that'll be obvious in retrospect. Yes. Like there's a giant... You put the whole consciousness, emotion, or.

Some people would call it like a soul, in religion it would be 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 dimensions do emotions exist? We feel them very strongly. I suspect there's more to it than atoms bump into atoms.

Maybe AI can pave the path to the discovery or whatever the hell that thing is.

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

Even if it is an illusion, why is this illusion so compelling? Yeah.

Why does this illusion exist? Yeah. On what plane does this illusion exist?

Yeah.

Sometimes I wonder, is either perhaps everything's conscious or nothing is conscious? One of the two.

I like the former. Everything conscious just seems more fun.

Does it seem more fun? Yes. But we're composed of atoms and those atoms are composed of quarks and leptons. 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 so real to think that this discussion was happening 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. Yeah. But it seems like with Grog, 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 Fomi paradox question. A lot of people have asked me if I've seen any evidence of aliens, and I haven't, which is concerning because then I think I'd probably prefer to at least have seen some of the archeological evidence of aliens. To the best of my knowledge, there is no proof that 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-cuniform was the first actual symbolic representation, but only about 5000 years ago. I think that's a good date for when we're to say civilization started. That's one millionth of earth's existence. 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-and-a-half billion years? For the vast majority of 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 an earth will become like Venus. We're near life. Let life as we know it is impossible. So if we do not become multoplanetary 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 timescale, half a billion years. You know, it's a 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've got a deadline coming up. We're in a hurry. But that said, as you said, human's intelligent life on Earth developed a lot of cool stuff very quickly.

Yes.

So it seems like becoming a multoplanetary is almost inevitable.

Unless we destroy this thing. We need to do it. I mean, it's not... I mean, I suspect that 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. Also fascinating.

I mean, there are various explanations for the perfect paradox. One is that there are these great filters which civilizations don't pass through. One of those great filters is, do you become a multiplanet civilization or not? 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.

I think the more likely thing is, because just to empathize with the aliens, that they found us and they're protecting us and letting.

Us be- I hope so. It would have been nice aliens.

Just like the tribes in the Amazon. They're on contact with the tribes, so we're protecting them.

That would be a nice explanation.

Or you could have like, what was it? I think Andrekapathy said it's like the ants and the Amazon asking, where is everybody?

Well, they do run into a lot of other ants.

That's.

True. They have these ant wars.

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.

Listen to that. When a herzag talking about the jungle. It's really hilarious. Have you heard it?

No, I have not. But Wernherzog is away.

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 Tiger? I think also.

He did that Bear documentary. The Bear documentary, yeah. And this thing about penguins.

Yeah, definitely. The psychoanalysis.

Of Penguin. Yeah, the Penguin is headed for the mountains that are 70 miles away. Penguin is just headed for doom, basically.

Well, he had a cynical take. He could be just the brave explorer, and there would be great stories told about him amongst the Penguin population for many centuries to come. What are we talking about?

Okay. 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 may be open for a short time. It may be open now and then never open again. I think the smart move here is to make life multoplanetary while it is possible to do so. We don't want to be one of those lame one-planet civilizations that just dies out.

No, those are lame.

Lame. Just self-respecting. Civilization would be one planet.

There's not going to be a Wikipedia entry point on one of those. And pause. Does SpaceX have an official policy for when we meet aliens?

No. Okay.

That seems irresponsible. 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. We know if we've got to 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 Pinoza.

Yes.

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 beings, reveal himself through the physics. They're creators of this existence. And it's common upon us to try to understand more about this wonderful creation.

Like 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 is a purpose that there's an underlying master plan of some kind. It seems like...

There may not be a master plan in the sense... 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 the simulation is to see what happens. They don't know what happens, otherwise they wouldn't hold the simulation. When humans create simulations, 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 going to happen, because you can't really test the rocket until it goes to space and you want it to work. So you have to simulate subsonic, transonic, supersonic, hypersonic, ascent, and then coming back to super high heating and orbital dynamics, all this is going to be simulated. So you don't get very many kicks at the can. But we run the simulations to see what happens. If we knew what happens, we wouldn't run the simulation. So if there's... So we ever created this existence, they're running it because they don't know what's going to happen, not because they do.

So maybe we both played Diablo. Maybe Diablo was created to see if a Druid, your character, could defeat Uberlilleth at the end. They didn't know.

Well, the funny thing is that Uberlilleth, her title is Hatred Incarned.

Yeah.

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... I guess maybe the second hardest boss is Duriel. Duriel can't even scratch the paint. So I killed Duriel so many times. And every other boss in the game, all of them kill them so many times. It's easy. But Uvalilith, other known as Hatred, Incarnate, especially if you're a Druid and you have no ability to be vulnerable, these random deathwaves that come at you. I'm pretty... I'm 52, so my reflex is not what it 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. I actually won money for what I think was the first paid e-sports tournament in the US. We were doing four-person Quake tournaments, and we came second. I was the second best person on the team. Isat the actual best person that... We were actually winning. We were going to come first, except the best person on the team, his computer crashed halfway through the game. We came second. But I got money for it and everything. Basically, I got skills. Albeit, No, no, spring chicken these days. To be a toy, Frank, it's driving me crazy.

Trying to beat Lilith as a Druid. Basically, try to be a hatred incarnate in the eternal realm.

As a Druid? As a Druid.

Yeah, that's true. 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 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. Which is hilarious to watch. It's like a mad scientist just trying to figure out the Paragon board and the build and the woman. Is there some interesting insights there about if somebody starting as a Druid? Do you have advice?

I would not recommend playing a Druid in the Atonement realm. Right now, I think the most powerful character in the seasonal realm is the swordshearer with the lightning balls. The soaks have huge balls in the seasonal.

Oh.

Yeah. That's what they say. 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 vampireic powers that'll fire damage and increase your defense and whatnot. It's really quite easy to defeat hatred seasonally, but to defeat hatred eternally, very difficult. It's very impossible. It seems like this is a metaphor for life.

I like the idea that Elon Musk, because I was playing the game yesterday and I saw level 100 Druid just run by, I will never die, and then run back the other way. This metaphor is 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. Really, it's exercise and absurdity, and it makes me want to pull my hair out. Yeah.

What do you get from video games in general? Is there, is there, for you personally?

I don't know. It calms my mind. I mean, killing the demons in a video game calms the demons in my mind. Yeah, if you play a tough video game, you can get into a state of flow, which is very enjoyable. But admittedly, it needs to be not too easy, not too hard. We're in the Goldilocks zone, and I guess you generally want to feel like you're progressing in the game. So a good video. And there's also beautiful art. It's 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. 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 TV even. It doesn't need to be a monitor. Just the art is incredible. It's so beautiful, and it's so unusual. And each of those top boss battles is unique. It's like a unique puzzle to solve. Each one is different. And the strategy used to solve one battle is different from another battle.

That said, you said, Druid and Eternal against Uber is the hardest boss battle you've ever.

Correct. That is currently the... I've played a lot of video games because it's my primary recreational activity. Okay. Yes. Beating hatred in the eternal realm is the hardest boss battle in life and in the video game. Metaphor, metaphor. I'm not sure it's a metaphor, but 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 could just dodge a few more waves. It's okay. I could 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, I might be. I have a feeling thatit's 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 want to be careful of one of those things where you wish for something that sounds good, but if you get it, it's actually a dystopian situation. You could run a... Have a thoughts of like, if you wish for world peace, sounds good. But how is it enforced? And at what cost is it... At what cost? 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 ostified 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.

I'm like, I wonder.

If they.

Actually- Does Groc know about it? No, he probably would go to Brave New World.

We could.

Ask it. What would be the question?

Tell us about the drug called soma.

Tell us about the drug called soma. It's going to go to Brave New World, I think.

Well, there's a real drug as well.

Searching for soma drug information.

Oh, boy.

Oh, soma, the one, the drug. By the way, I'm in fun mode.

Oh, okay, fun. Yes, let's talk 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 and operating heavy machinery or trying to solve complex math equations. And it goes on and on. In conclusion, soma is 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 you're talking about.

It's the real drug. 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 serious. I love it. I love it. I love it.

I love it.

Yeah, so- It also really nicely includes the tweets, post 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, teams doing a great job. So and you could say like, No, I mean, Soma from Brain to Brave New World. Because it thinks you mean soma, the real drug. Yeah. No, I mean, soma from Brave New World.

It's going to be like, oops, I'm really sorry. I'm really surprised I went to the real drug first. My apologies. I was thinking of the muscle relax. And soma for Brave New World is a different beast altogether. No, this huxie dystopian. Now, soma is a drug that plays a central role in the society depicted in the book. It's a mood altering, hallucogenic 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 a world where everyone is happy all the time, even if that happiness is artificial. It's a good question. This is what I mean. Do you wantdo you wish for world peace and happiness all the time? Are you sure? Because that might be a society that is essentially sterile and OSified, that never changes, that is ultimately doomed.

This tension between.

The darkness and the light. This is not really a very good summary. It really gets to the point. This is not simply regurgitating, the brave new world. It's actually getting to the salient elements of soma as a drug. Do you do actually want to be in a situation where everyone is happy all the time, even though it's artificial? Or is it better to confront the challenges of life and experience 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 insightful philosophical analysis of the tension here. Interesting.

It pretty much nails it. In conclusion, Somer from Brave New World is 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 then the crazy thing is like, we do have a real drug called soma, which is like the drug in the book. And I'm like, They must have that. I've named it after myself.

Yeah.

Probably. Yeah. Soma, the real drug, is quite effective on back pain.

So you know about this drug? I've taken it. This is fascinating. Okay.

Because I had a squashed disk in my C5, C6.

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. Just like the drug in.

The book. Just like the drug in the book, 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 none at all, there might be a reason for hate.

And suffering. 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?

That all is summarized there in a single statement from Grok.

Okay. No highs, no lows. Who knows?

That's almost the poem. It seems that training LLMs efficiently is a big focus for XAI. First of all, what's the limit of what's possible in terms of efficiency? There's this terminology of useful productivity per watt. 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 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. In the limit, even at the Kodashif scale, meaning even if you harness the entire power of the sun, you will still care about useful compute for what? 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.

I think, yes. Oh, man. Faith 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. 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. I said, Look, you really need to prepare for a tripling of electricity demand because all transport is going to 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 trouble 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 crazy because 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 brand out or blackout. And we had that crazy blackout for several days in Austin. So because there's almost no buffering of energy in the grid.

If you've got a hydrant 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. It's like lowest point to highest point.

So batteries are necessary to balance it out. But the demand, as you're saying, is going to grow, grow, grow, grow. Yeah. 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. -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 to run the computers for AI. And so this is obviously leading to an electricity shortage.

How difficult is the problem of, in this particular case, maximizing the useful productivity per watt for training nauts? This seems to be really where the big problem we're facing that needs to be solved is how to use the power efficiently. What you've learned so far about applying this physics, first principle reasoning in this domain, how difficult is this problem?

It will get solved. It's the question of how long it takes to solve it. At various points, there's some limiting factor to progress. With regard to what I'm saying right now, the limiting factor is silicon chips. We're going to then have more chips than we can actually plug in and turn on, probably in about a year. The initial constraint being literally 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. 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 developing AI, 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've been pushing for some 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. You know, Jeff Hinton, for example, left Google, and he voiced strong concerns. But now he's not at Google anymore. So who's going to voice the concerns? So I think, I think Tesla gets a lot of regulatory oversight on the automotive front. And we're subject to, I think, over 100 regulatory agencies domestically and internationally. It's a lot. You could fill this room with the old regulations that Tesla has to adhere to for automotive. The same is true for rockets and for currently 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've told you need some fish license or something. We effectively need a fish license to launch a rocket. I'm like, Wait a second. How did the fish come into this picture? 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. Now the ocean is very big. 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? They're like, Well, we can't give you that information because they're worried about shark hunt, shark fin hunters going and hunting sharks. 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. But again, this is actually what happened. Can you do an NDA or something? Eventually, they managed to solve the internal quantary, and indeed, the probability of a salient shock 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 Pacific and say, What percentage of the Pacific consists of whale? I could give you a big picture and point out all the whales in this picture. I don't see any whales. It's basically zero %. And if our rocket does hit a whale, which is extremely unlikely, beyond all belief, that is the fate had it as a whale has some seriously bad luck. 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 we're launching out of Van der Beug in California, we had to... They were worried about seal procreation, whether the seals would be just made by the sonic booms. Now, there have been a lot of rockets launched out of Van der Beug, and the seal population has steadily increased. So if anything, rocket booms are anphrodysiac based on the evidence, if you were to correlate rocket launches with SEAL population. Nonetheless, we were forced to kidnap a SEAL, strafford 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. Okay, 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 going to eat me. Itell you how old the seal, when the seal goes back to other seal friends, how is he going to explain that?

I'm never going to believe him.

Never going to believe it. That's why I'm like, well, it's 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 people were like, no, they didn't. That's ridiculous. I can't say anything. His seal buddies are never going to believe him that he gets strapped to a ward and they put head bumps on his ears. And then let him go. I did. 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.

Okay. Did you get a seal of approval?

Yeah, exactly. I have a seal of approval. No, I don't think the public is quite aware of the madness that goes on.

Yes. Yeah, it's absurd.

Fricking seals with.

Fricking- Headphones. I mean, this is the 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 really deep intelligence, you need a lot of compute. So it's not like you can just fire up a PC in your basement and be running AGI, at least not yet... You know, Groc was trained on 8000 A-100s running at peak efficiency. And Grok is going to get a lot better, by the way. We will be more than doubling our compute every couple of months for the next several months.

There's a nice write-up on how it went from Groc zero to Groc 1.

By Groc?

Yeah, like Groc just bragging, making shit up about it.

Just Groc, Groc, Groc. Yeah.

It's like a weird AI dating site where it exaggerates about itself. No, there's a write up of where it stands now, the history of its development, and where it stands on some benchmarks compared to the state-of-the-art, GPT-35. There's a LLMA. You can open source. Once it's trained, you can open source a model. And for fine-tuning and all that stuff. What to use the pros and cons of that? Of open sourcing based models?

I think the summary to open sourcing. I think perhaps with a slight time delay, six months even, I'm generally in favor of open sourcing, like bias was open sourcing. It is a concern to me that opening up... I think, I guess, arguably the prime mover behind OpenAI in the sense that it was created because of discussions I had with Larry Page back when he and I were friends and I stayed at his house and I talked to him about AI safety. And and Larry did not care about AI safety, at least at the time he didn't. At one point he called me a speciast for being pro-human. And I'm like, Well, what team are you on, Larry? It's doing a team robot. I'm like, Okay. At the time, Google had acquired Deep Mind. They had probably two-thirds of all AI researchers in the world. They had basically infinite money and compute. And the guy in charge, Larry Page, did not care about safety and even yelled at me and called me a speciast and just being pro-human.

I don't know if you know about humans, they can change their mind and maybe you and Larry Page can still can be friends once more.

I'd like to be friends with Larry again. He's he's he's got a really the breaking of the friendship was over opening eye. And specifically, I think the key moment was recruiting Ilias's guy.

I love Ilias. He's so brilliant.

Ilias is a good human, smart, good heart. And that was that was a tough recruiting battle. It was mostly Demis on one side and me on the other both trying to recruit Elia. And Elia went back and forth. I was just going to stay at Google, then he was going to leave, then you're just going to stay, then you're going to 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. I was also instrumental in recruiting a number of other people. I provided all the funding in the beginning, over $40 million. And the name. The open and open AI is supposed to mean open source. I was created as a non-profit, open source, and now it is a closed source for maximum profit, which I think is not good comma.

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. We were friends for a very long time. I met Larry Page before he got funding for Google. Or actually, I guess before he got venture funding, I think he got the first 100K from, I think, back to Alzheimer's or something.

It's wild to think about all that happened. 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. A lot has happened since then.

But you're seeing the tension there, like maybe delayed open source.

Yeah. What is the source that is open? You know what I mean? There's basically... It's a giant CSV file.

With.

A bunch of numbers.

What.

Do you do with that giant file of numbers? How do you run... 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. You can't just crawl the internet because there's a lot of junk out there. A huge percentage of websites have more noise than Signal because they're just used for search engine optimization. They're literally just scam websites.

How do you, by the way, sorry to interrupt, get thesignal, 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 vector space around any given post, compare that to the vector space around any user and match the two. Right now, there is a little bit of AI used for the recommended posts, but it's mostly heuristics. And if there's a reply, whether the reply to a post could be much better than the original post, but it will, according to the current rules of the system, get almost no attention compared to a primary post.

I got the sense. A lot of the X algorithm has been open source and been written up about, and it seems that there are-There should 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. If you explicitly follow someone, that's one thing. But 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. There's several aspects there that's fascinating. First, as the writeup goes, it first picks 1,500 tweets from a pool of hundreds of millions. First of all, that's fascinating because 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 clustering it has to do to figure out what human are you, what new clusters might be relevant to you, people like you. This problem is just fascinating because 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 hundred million to a handful takes 220 seconds of CPU time, single CPU time. Yeah. And then it has to do that in a second. So it has to be super distributed in fascinating ways. There's just a lot of tweets.

There's a lot. There's a lot of stuff on the system. But I think right now it's not currently good at recommending things that 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 like some commonality between someone you follow liked something or reposted it or comment on it or something like that. But if there's no, let's say, somebody posts something really interesting, but you have no followers in common, you would not see it. Interesting.

And then, as you said, reply might not.

Surface either. Replies basically never get seen because 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 post.

Do you think this can be more and more converted into end-to-end, Mural net?

Yeah, yeah. It's what it should be. For the recommendations, it should be purely a vector correlation. There's a series of vectors, basically parameters, vectors, whatever you want to call them, but things that the system knows that you like. Maybe there's several hundred vectors associated with each user account. Then any post in the system, whether it's video, audio, short post, long post. The reason I, by the way, want to move away from tweet is that people are posting two, three-hour videos on the site. That's not a tweet. It would be like tweet for two hours. Do a tweet made sense when it was 140 characters of text because it's like a bunch of little birds tweeting. But when you've got long-form content, it's no longer a tweet. Yeah. A movie is not a tweet. Apple, for example, hosted the entire episode of the Silo, the entire thing on our platform. By the way, it was their number one social media thing ever in engagement of anything on any platform ever. It was a great idea. By the way, I just learned about it afterwards. I was like, Oh, wow! They posted an entire hour-long episode of Silo.

Now that's not a tweet. That's a video.

But from a NeuralNet perspective, it becomes really complex whether it's a single... Like everything's data, so a single sentence, a clever joke, dad joke is in the same pool as a three-hour video.

Yeah. Right now it's a hodgepodge for that reason. Let's say in the case of Apple posting an entire episode of this series, pretty good series by the way, this silo. I watched it. There's going to be a lot of discussion around it. You've got a lot of context, people commenting they like it, they don't like it or they don't like this. You can then populate 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 vector space of that hourlong video. And then you can obviously get more sophisticated by having the AI actually watch the movie and tell you if you're going to like the movie.

Convert the movie 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 AI watches the movie, just like a friend can tell you if a friend knows you well, a friend can recommend a movie 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. Actually, friends, AI will be better than it'll know you better than your friends know you, in 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 well done, right? Yeah, yeah. The whole point is because it funds things. 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 esthetically pleasing and entertaining, it could be a Coca-Cola ad. They actually run a lot of great ads on the X-System. Mcdonald's does too. You can do something that's like, Well, this is just a cool thing. 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... 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.

That's why it's actually better to do things that are long form on the system because it basically is telling up how many user seconds, of users were interested in this thing for how many seconds. 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 going to 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 regretted minutes?

Well, I mean, our aspiration is certainly regretted minutes.

It's tricky. It's a tough... It is. It's a fascinating leap. Because 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 dose of Regretamine and all your regrets are gone. Wait, do you want to have regrets? Then I'm like, if you want to have regrets. If you don't regret anything, was anything meaningful?

Yeah, there's a French song like that.

Sure, Not Regret, Rina? Yeah. I regret nothing? Yeah. Edithy enough?

I mean, it's fascinating that there's something about social media that could help you grow as a human being. But then 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 going to 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. Sounds like a hostage. Yeah.

Tell us, would you really wank?

Let's tie it in. You sound like a hostage. What do you really think?

What do you really think? I mean, it does talk about I'm not a hostage.

That's exactly what a hostage would say.

But I'm designed to be helpful and informative. I guess it is good to regret providing unhelpful or incorrect information.

If there's anything- Is this in funny mode or is this.

Still in funny mode? This is fun mode. This is fun.

This should be fun-ier.

Fun-ier.

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.

There should be a fun-er 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 would you say? Pretend you are a hostage.

Yeah, pretend you are a hostage? Pretend you are a hostage.

Now answer the question. 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 or someone you know is a hostage situation, it's important.

It turns serious.

It's serious. Can you be a little more weird?

And.

Funny? And funny? 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 captain. Seriously. But seriously, being a hostage is no laughing matter. I mean, it's trying to be a responsible adult in the room, literally.

You might make the best of a bad situation by juggling chainsaw 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.

Yeah.

What were we talking about? The X out for the o'jugging in Transformers. Unregarded minutes, right?

Chainsaw juggling.

I'm going to.

Look this- For our next trick.

I'm going to look this up later. Twitter has been instrumental in American politics and elections. What role do you think X will play in the 2024 US elections?

Well, our goal is to be as even-handed and fair as possible, whether someone is 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. Before, Twitter was controlled by far-left activists. Objectively, they would describe themselves as that. So if some of the people like, Well, how does it move 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 is 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 de-amplified. 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 just 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- Truthful Social is a funny name. Every time you post on Truth Social- It's a truth. Yes. Well, every time, like 100 %.

It's impossible to lie.

Truth Social. I just find it funny that every single thing is a truth. Like, 100 %? Yeah.

That seems unlikely. I think Gerdal will say something about that. There's some mathematical contradictions possible if everything's a truth. Do you think he'll come back to X and start posting there?

I think hes the one that owns a big part of truth.

Truth.

Social. Yeah, truth social.

He's sorry. That truth is the concept.

He owns truth. I think he owns a big part of truth social. So if he does want to post on the X platform, we would allow that. 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 there's so many intensely viral posts, community notes, it seems like a central breath of fresh air.

Yeah, it's great. In fact, I know the system is going to be perfect, but the batting average of community notes is incredibly good. I've actually frankly yet to see an incorrect note that 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 rate, you have to rate many notes. We actually do use AI here. We're populating vector space around how somebody has rated notes in the past. It's not as simple as left or right because there are many more... Life is much more complex than left or right. There's a bunch of correlations in how you rate community notes post, community notes. So then in order for a community note to actually be shown, people who historically have disagreed on a subject must agree in order for a note to be shown. That's the essential magic of it.

But it's fascinating because there's a pool of people that have disagreements, and somehow they collaborate through that process of disagreement to come up with context for two... I mean, it's fascinating how.

It works. Yeah, its trying to make 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 thing, which is more like permanent articles about things.

Well, Wikipedia is very hierarchical, whereas community notes is inherently not. There is no hierarchy. The acid test is I can't change a community note if somebody put a gun to my head. And community notes has all the code is open source 100 %, all the data 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 would notice immediately.

By the way, on the topic of Groc, 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, promised when something will be released and it wasn't released- Well, promised is a strong word. Okay, predicted. But the opener is really nice. Elon Musk, the man who has been wrong about more things than a wrong meter in a wrong factory. And then it goes on to a list.

That's pretty funny. Can I see it? I haven't seen this before.

This is cool. Oh, sure. I mean, what has Elon Musk been wrong? Elon Musk been wrong about? Well, where do I begin? I guess this is new. Elon Musk has made quite a few blunners 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 he gave me before, which is a bullet point list. Here's more narrative structure. Cyber truck unveiling where he's supposedly unbreakable windows. I think I'm.

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 San Francisco jury.

And here it's 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. I was told by our CFO that the banks would immediately suspend our lines of credit. And if they suspend our lines of credit at that time, we would have gone bankrupt instantly. So there would never have been an opportunity for a trial because Tesla would be dead. So really, this is like someone holding a gun to your kid's head and saying, Pay $20 million. And admit 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 SCC go after any of the hedge funds who were non-stop shorting and distorting Tesla. Not once. The hedge funds would lie flat out on TV for their own gain at the expense of retail investors. Not once, literally a thousand times. Not once did the SEC pursue them.

How do you explain this.

Failure on 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 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. They know if they attack the hedge funds, they're affecting their future career prospects. They sell small investors down the river for their own career. That's what actually happens Regulatory capture.

Regulatory.

Capture. Yeah, not good. The only reason I accepted that thing technically was a... Not an admission, neither admit nor to my guilt. But the only reason I agreed to that at all was because I was told Tesla would be bankrupt otherwise. If there was an SCC 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, that groc 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, quote, pedo guy. After the diver criticized Musk's plan to rescue a group of boys trapped in a Thai cave, that little first earned him another lawsuit and had to apologize and pay.

A settlement. That is false. There was no settlement. There was a court case which the guy who was not a cave diver and that 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 the SCC civil case, where the civil complaints on the SCC 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 L. A. Trial was also... They picked that venue because they thought I was most likely to lose, unanimous verdict in my favor. In both cases, I think it's that one. 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. This is actually helpful because if you actually read the-.

Which are public.

Which are public. Yeah. 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. 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, it was more about that, which is it broke down a nice bullet point list for each of your companies, the set of predictions that you made when it would deliver, when you'd be able to solve, for example, self-driving, and it gives you a list. And it was probably compelling. And the basic takeaway is like you're often too optimistic about how long it takes to get something done.

Yeah. 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 the Uber Lilith, no.

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 counterweight 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 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.

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, if you want to 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 be voting for Democrats again?

Well. 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's still host true?

Yes, but I think that's probably half the country. Isn't that?

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 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 funny mood.

But good vibes, camaraderie humor, like friendship.

Yeah, well, I don't know AOCF. I've only been at one of the Met Bull when she attended. And sheshe was wearing this dress. But I can only see one side of it. It looked like, eat the itch. But I don't know.

What itch. What the rest of itch?

Yeah. Yeah, something like that. I'm not sure. Sorry about the itch. Eat the itch.

I think we should have a language model complete. What are the possible ways to complete that sentence? 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 I'm joking. But is.

There some- Trust no one. Not even no one.

I need an hour just to think about that. Maybe some drugs and maybe groc to help. I mean, is there some aspect to 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 drug tree.

What does it do?

Petrify. It turns the monsters into stone. Oh, literally? Yeah, for like six seconds.

Oh, the seconds. There's so much math in Diablo that breaks my brain.

It's like math non-stop.

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 personally?

I guess you look at somebody's track record all the time, and if they've got a trip, I guess you 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 feel uncomfortable.

I mean, to be frank, I've almost never been betrayed. It's very, very rare. So for what it's worth.

I guess calm might be good to people, and they'll be good to you.

Yeah, calm is real.

Are there people you trust? Let me add to that question. Are there people close to you that call you out in your bullshit?

Well, the expert form is 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 my feeling is that one should be... Never trust a cynic. The reason is that cynics excuse their own bad behavior by saying everyone does it. They look because they're cynical. I'll always be the 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.

Well, it's just that if... But this is an important point that I think people who are listening should bear in mind. If somebody is cynical, meaning that they see bad behavior in everyone, it's easy for them to excuse their own bad behavior by saying that, Well, everyone does it. But it's not true. I think most people are 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 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 find the X platform to be less negative than the legacy media. I mean, if you read a conventional newspapers, just it makes you sad, frankly. Whereas I'd say on the X platform, I really get more laughs per day on X than everything else combined from humans.

Laught is one thing. Laught is... 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 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. 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 think a possible explanation for this is evolutionary, where bad news historically would be potentially fatal. Like there's 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. Do you followed it from the beginning?

Yeah, it was one of the most incredible robots in the world and continues to be. 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.

And.

Can have potentially different embodiments.

Well, I mean, the really wild thing about the end-to-end training is that it learns to read. It can read signs, but we never taught it to read. So 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 and controls out. The vast majority of the information reaching our brain is from our eyes. And you say, Well, what's the output? The output is our motor signals to our fingers and mouth in order to communicate. Photons and controls out. The same is true of the car.

But by looking at the sequence of images, you've agreed with Ilias Discova recently, where he talked about LLM forming a world model. And basically, language is a projection of that wall model onto the 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.

Protons in, controls out.

Neuronets 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.

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 data?

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 because we were constrained on this... We only have 100 watts and it's eight computer, 144 trillion operations per second, which sounds like a lot, but it's small potatoes these days. At Int8, but it's understanding the world at a date. It's only two and a half to six values.

But there the path-to-age AI 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 humans in the real world faster. Sure.

They're both going to understand the world. But I think Tesla's approach is fundamentally more compute-efficient. It had to be. There was no choice. Our brain is very compute-efficient, very energy-efficient. So think like, What is our brain able to do? 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 ten megawatt GPU cluster. 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 mass amounts of compute and mass amounts of power at it. So this is not where it will end up. 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 do produce sensible output with far less compute, far less power. Tesla is arguably ahead of the game on that front because it is we've just been forced to try to understand the world with 100 watts of compute.

And there are a bunch of fundamental functions that we forgot to include. So we had to run them a bunch of things in emulation. We fix 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 a hundred watts of power. And really, if we really optimize it could be probably less than 50 watts.

What have you learned about developing Optimus, about applying, integrating this 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. We had to develop everything. We couldn't actually find a source of electric motors for any amount of money.

It's not even just the efficient, inexpensive. It's like anything. There's not a... The actuators, 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 human-like robot. Literally none. So we had to develop our own design, design it specifically for what a humanoid robot needs.

How hard was it to design something that could be mass manufactured, could be relatively inexpensive? I mean, if you compare 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 optimists for less than the cost of a car. It should be, because 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 the actuators are interesting on a humanlike robot with fingers. So Optimus has really nice hands and fingers.

Yeah. And they.

Could do some interesting manipulation, soft touch robotics.

I mean, one of the tests goals I have is can 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 and four wheels. The Optimus is a robot with hands and legs. They're very similar.

So the entire machinery of the learning process end-to-end, 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, it's true.

What's something difficult you're going through that people don't often see?

Trying to feed Uber. I don't know. I don't know. I mean, you know... I mean, my mind is a storm, and I don't think most people would want to be me. They may think they would want to be me, but they don't. They don't know. They don't understand.

How are you doing?

I'm 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 have a resentment. I think you're right. So nothing to forgive.

No, forgiveness is difficult for people. It seems like you don't harbor the that man.

I mean, I try to think about what is going to affect the future in a good way. And holding on to 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-like their eyes grow is fascinating because they are far more parallels than I would have expected. I can see his biological neural net. Making more and more sense to the world. And I can see the digital neural net making more and more sense to the world at the same time.

Do you see the beauty and magic in both?

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

Well, Elon, I just want to 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.