The following is a conversation with Elon Musk, his fourth time on this The Lex Friedman podcast. I thought you were going to finish it. It's one of the greatest themes in all film history. Yeah, it's great.
So, I was just thinking about the Roman Empire, as one does. Does that hold me where all 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. And as you know, war and military conquest has been a big part of Roman society and culture. And it I think has been a big part of most empires and dynasties throughout human history.
Yeah, they usually came as a result of conquest. I mean, there's something like the Orchard and Gering Empire where there was just a lot of sort of clever marriages. But fundamentally, there's an engine of conquest. Yeah, it was always. And they celebrate excellence. And warfare, many of the leaders were excellent generals. Yeah. And that kind of thing.
So, a big picture question, grok approved. I asked this is a good question to ask. Did it test grok approved? 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 asked this as you have somehow controversially been a proponent of peace.
I'm generally a proponent of peace. I mean, ignorance is perhaps in my view, the real enemy to be countered. That's the real hard part, not fighting other humans. But all creatures fight. I mean, the jungle is a, you look at the, you'll think of the nature as perhaps some sort of peaceful thing. But in fact, it is not, there's some quite funny, when a hook, when a hoods, hoods, hogs thing where he's like in the jungle, like saying that it's like basically just murder and death in every direction. And the, the plant animals in the jungle are constantly trying to kill each other every single day, every minute. So it's not like, you know, we're unusual in that respect.
There's a relevant question here whether with greater intelligence comes greater control over these base instincts for violence yes we have much more of an ability to control our limbic instinct for violence than say it's a fancy and in fact if you find looks at state jimvency society it is not friendly i mean the but but no buzzer exception chimpazi society is uh... full of violence and quite quite horrific frankly that that's that's our limit system in action like you know i'm the wrong side of chimpazi your face off and tear nuts off yeah basically there's no limits or ethics or uh... the wrong is that just war there's no just war and change and change in the societies is was warned and dominant by any means necessary yet to be a society is a pro like a permanent version of human society uh...
it's that's not like peace loving basically uh... at all uh... there's extreme balance uh... and once in a while some some for somebody who's watched me doesn't mean it decides to raise a chimpazi as a pet uh... and then that needs their face or if they're not so for two different stuff like anything yes happens several times uh... ripping your nuts off the interesting strategy for interaction so it's happened to people it's unfortunate like that's i guess a one way to ensure that the other chimp doesn't take it you know contribute to the gene pool well from a martial arts perspective is a fascinating strategy and then the the the not refer hahaha i wonder which of the martial arts teaches that i think it's a safe to say if somebody's you've got your nuts in their hands and as the option of giving them off you will be amenable to uh... whatever they want yeah hahaha
So, like I said somehow controversially you've been uh... proponent of peace on on Twitter on x yeah so let me ask you about the wars going on today and to see what the path to peace could be how do you hope the current war in Israel and Gaza comes to an end uh... what path do you see that can minimize human suffering.
In the long term in that part of the world well I think it that that part of the world is is definitely like if you look up the there is no easy answer in the dictionary it'll be that like the picture of uh... the malaise um... in Israel especially so there is no easy answer um it or what my this strictly my opinion of uh... you know uh... is that uh... the the goal of Moss was to provoke an over reaction from Israel um... the opposite you're not expect to uh... you have a military victory uh... but they really wanted to commit the worst atrocities that they could in order to provoke the most aggressive response possible from Israel um... and then leverage that aggressive response to um... rally Muslims worldwide uh... for the cause of uh... Gaza and House name which they have succeeded in doing um so the this the counterintuitive thing here I think that the thing that I think should be done even though it is very difficult uh... is that um I would recommend that Israel engage in the most conspicuous acts of kindness possible every part everything that is the actual thing that would thwart the goal of the Moss
So in some sense the degree that makes sense in geopolitics turn the other cheek implemented it's not exactly turn the other cheek because I do think that this um you know that I think it is appropriate for Israel to find the Maus members and you know um either either of kill or accostrate them um like that's something that something has to be done because of that they're just going to keep keep coming otherwise um but in addition to that they need to do whatever they can there's some talk of uh establishing for example a mobile hospital I'd recommend doing that um just making sure that uh you know there's food water uh medical necessities um and and just be over the top about it and be very transparent so it's it's it's that it can't go can't claim it's a trick like just put webcam on the thing oh you know all 24 seven deploy acts of kindness yeah conspicuous acts of kindness that that with that are unequivocal meaning they can't be somehow because homosce will then their response will be always the trick therefore you have to counter how how is not a trick this ultimately fights the broader force of hatred in the in the region yes
Paragraph 1:
And I'm not sure who said it it's an approach of saying but an eye for that for an eye makes everyone blind uh now that neck of the woods they really believe in the whole eye for an eye thing um but I mean you really have if you're not going to just outright commit genocide like it against an entire people which obviously would not be acceptable to to really shouldn't be acceptable to anyone um then you you're going to leave basically a lot of people alive who subsequently you know hate Israel so really the question is like how for every homos member that you kill how many did you create and if you create more than you killed you've not succeeded that's the you know the real situation there um and it's safe to say that if you know um if you know if you kill somebody's child in Gaza if you've you've made at least a few uh homos members who will die just to just kill Israeli that's the situation so but but I mean this is one of the most contentious subjects one could possibly discuss but but I I think if the if the goal ultimate is so sort of long-term peace one has to be look at this from standpoint of over time are there more or fewer uh terrorists being created let me just uh linger on war yeah war if it's safe say wars or existed and always will exist always will exist always has always has existed and always will exist I hope not you think it always will always there will always be this question of just how much will and and um you know what it you know this this this is the scope and scale of war but to my I imagine that there would not be any more in the future I think would be very unlikely outcome yeah you talked about the culture series there's war even there yes it's giant war the first book saws off with um a gigantic galactic war where trillions die trillions but it's still nevertheless protects these pockets of of flourishing somehow somehow you can have galactic war and still have pockets of flourishing yeah I mean it's I guess if we are able to one day expand to you know full the galaxy or whatever there will be a galactic war at some point ah the scale I mean the scale of wars been increasing increasing increasing it's like a race between the scale of suffering 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 disconcerned me is that there are very few people alive today who actually uh viscerally understand the horrors of war at least in the u.s i mean obviously the people in on the front lines in ukraine and russia who understand just how terrible war is but how many people in the west understand it in my grandfathers in world war two he was severely traumatized i mean he was there i think in the for almost six years in the you know in east and north african-adilly all his friends were killed uh in front of him and he would have
Paragraph 1: died too except they randomly gave some I guess i cute test or something and uh he scored very high um now he was not an officer it was a corporal sergeant or something like that because he didn't finish high school um he had to drop out of high school because his his dad died and he had to work to support his um siblings um so because he didn't graduate high school he was not eligible for the officer corps um so you know if you kind of got put into the cannon fodder category basically um but then randomly they gave him this test he was transferred to british intelligence in london that's where he met my grandmother um but uh he 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 shop and he won a bunch of medals never never ragged about it once and not even they hinted nothing i like found out about it because i his military records were online that's uh it's not how i know so he would say like no no way in hell do you want to do you want to do that again but how many people um now he he obviously he died you know 20 years ago or longer actually 30 years ago um how many people are alive that remember world war two not many and the same perhaps applies to the threat of nuclear war yeah i mean there are enough nuclear bombs pointed at the united states to make the rubble the radioactive rubble balanced 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 um right now i could be wrong but i think the the current probability of nuclear war is quite low um but there are a lot of nix pointed at us so and we have a lot of nix pointed at other people still there and nobody's put their their guns away the muscles are still in the silence and uh 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 on a local basis and then there are wars which are civilization ending or have that potential obviously global thermonecular warfare has high potential to end civilization perhaps permanently but certainly you know to severely wound and perhaps set back human progress by you know to the stone age or something i don't know pretty bad probably scientists and engineers won't be super popular after that as well and like you go to think of this mess so generally which i think we we also want to prioritize civilizational risks over things that are um painful and tragic on on a local level but not civilizational
Paragraph 1: "how do you hope the war in Ukraine comes to an end and what's the path once again to minimizing human suffering there uh well i think that what what is likely to happen which is really pretty much the way it is is that uh something very close to the current lines will be how a ceasefire or truce happens but you know you just have a situation right now where whoever goes on the offensive will suffer casualties at several times the rate of whoever's on the defense because you've got uh defense and death you have minefields trenches anti-tank defenses nobody has air superiority um because the the anti aircraft missiles are really far better than the the aircraft like they're far more of them and uh so neither side has air superiority um tanks basically death drafts um just slow moving and they're not immune to anti-tank weapons so you you really just have long-range artillery um and uh infantry strangers it's World War One all over again with drones yeah throwing old drones some some drones are um which makes the long-range artillery just that much more accurate and better and so more efficient motoring people on both sides yeah so it's whoever is you don't you don't want to be trying to advance uh for me the side because the probability of dying is incredibly high um so in order to overcome uh defense and death trenches and minefields you really need uh significant local superiority in numbers um ideally combined arms where where you do a fast attack with aircraft a concentrated number of tanks um and a lot of people that's the only way you're going to punch through a line and then you're going to punch through and and then not have reinforcements just kick you right out again i mean you've i really recommend people read uh World War One warfare in detail it's rough um I mean there's sure a number of people that died there was mind-boggling and it's almost impossible to um imagine the end of it that doesn't look like almost exactly like the beginning in terms of what land belongs to who and so on but on the other side of a lot of human suffering death yes and destruction of infrastructure yes i mean the thing that the reason i you know proposed a some sort of truth or or peace a year ago was because i've predicted pretty much exactly what would what happened which is a lot of people dying for basically almost no changes in land um and this the the loss of the the flower of Ukrainian and Russian youth and we should have some sympathy for the Russian boys as well as Ukrainian boys because their own boys didn't didn't ask to be on their front line they have to be so um there's a lot of sons not not come back to their parents you know and then I think most of them don't really have they don't hate the other side you know it's sort of like is this the same about like this the same comes from world war one it's like young boys who don't know each other killing each other on behalf of old men that do know each other the hell's the point of that so Volodymars 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 yeah sit down man to man leader leader and negotiate peace look i think i would just recommend do not send the flower of Ukrainian youth to be to die uh in trenches whether he talks to Putin or not just don't do that um whoever goes on the offensive will lose massive numbers of people um and history will not look kindly upon them
Paragraph 1: you spoke anonymously 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 the difficult to pronounce the acidity's trap i believe it's called i love war history i like insane art and backwards um there's hardly a battle i haven't read about and and trying to figure out like what what really was the cause of victory in any particular case as opposed to what one side or another claim for the reason both the victory and what sparked the war and yeah yeah the whole thing yeah so that Athens and Sparta is a classic case the thing about the greeks is i really wrote down a lot of stuff they loved writing um you know there are lots of interesting things that happened many parts of the world but they just feel just to write down so we don't know what happened or they didn't really write with in detail they just would say like we went we had a battle and we won and like well can you add a bit more um so the greeks they really wrote a lot they're very articulate on it they just love writing so and we have a bunch of that writing that's preserved so we know what led up to the Peloponnesian War between um the spot in an Athenian alliance um and uh we we know that they for quite that they saw it coming i mean as far as to the right that those weren't very forebose by their nature but they're derived but they weren't very forebose they weren't terse uh but the the Athenians and the other greeks were it wrote a line and they were like um and Sparta was really kind of like the leader of Greece um but but Athens grew stronger and stronger with each passing year and um and everyone's like well that's inevitable that there's going to be a clash between Athens and Sparta uh well how do we avoid that and they couldn't they actually they saw it coming and they still could not avoid it so you know at some point if there's if one uh group or in civilization or country or whatever exceeds another sort of like if you know the United States has been the biggest kid in the block since i think around 1890 from an economic standpoint so the United States has been the economic most powerful economic engine in the world longer than anyone's been alive um and the foundation of war is economics so now we have a situation in case of China where the um the economy is likely to be two perhaps three times larger than that of the US so imagine you're the biggest kid on the block for as long as anyone can remember and suddenly a kid comes along who's twice your size so we see it coming yeah how is it possible to stop is there some let me throw something out there just intermixing of cultures understanding there just 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
Paragraph 1: maybe a good question to ask is what are some things about China that people don't understand positive just in the culture with some interesting things that you've learned about the Chinese
Paragraph 2: well the sheer number of really smart hardworking people in China is um incredible there are believe say like how many smart hardworking people are there in China just far more than they are here i think in my opinion the uh and they've got a lot of energy so i mean the the architecture in China that's in recent years is far more impressive than the u.s i mean the the train stations the buildings the high speed rail everything it's um really far more impressive than what we have in the u.s i mean i recommend somebody just go to Shanghai and Beijing look at the buildings and go to you know take the train from Beijing to Xi'an where you have the terra car to areas i'm trying to go to incredible history uh very long history and um you know i i think arguably the in terms of the use of language from from a written standpoint um sort of one of one of the oldest perhaps perhaps the oldest written language and then China people did write things down so um now China um historically has always been with the rare exception been internally focused um they've not been acquisitive uh they've they've fought each other they've been many many civil wars um in the three kingdoms war i believe they lost about 70% of their population so they on the end that does so the they've had brutal internal wars like civil wars that make the u.s of all look small like a person
Paragraph 3: um so i think it's important to appreciate that China is not uh monolithic um we sort of think for like China is a sort of one entity of one mind and this is definitely not the case um from what i've seen and i think most people who understand China would agree that people in China think about China 10 times more than they think about anything outside of China so it's like 90% of their consideration is uh you know our is is is in total
Paragraph 4: 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 yeah uh 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 um they do feel very strongly you know so that's that's good i mean because a lot of a lot of very powerful countries have been acquisitive um the u.s is one of the also one of the rare cases that has not been acquisitive like in after World War II the u.s could have basically taken over the world and any country like we got nukes nobody else got nukes you know we have to lose soldiers uh which country do you want and the United States could have taken over everything oh it had well and it didn't um and the United States actually helped revolt countries to help rebuild Europe you know help revolt Japan um this is very unusual behavior almost unprecedented you know the u.s did conspicuous acts of kindness like the brolin airlift you know and and i think you know there's always like well america's done bad things well of course america's done bad things but one needs to look at the whole track record um
Paragraph 1:
and and just generally you know when one sort of test would be how do you treat your prison as a war or let's say um you know no offense to the russians but let's say you're in Germany it's 1945 you got the russian army coming one side and you got the french russian american army is coming out of the side who would you like to be just ready to like no country is like marley perfect but i recommend uh being a p.o.w with the americans that would be my choice very strongly in the form menu p.o.w very much so and in fact one of one brown um yeah took you know small guy was like we've got to be captured by the americans yeah and uh in fact the s.s. was under orders to execute more brown and all of the uh german rachon issues uh and they narrowly escaped their SS they said they were going out for a walk in the woods they left in the middle of winter with no coats uh and they ran like ever no food no coats no water and just ran like hell uh and ran west um and by sheer like they i think his brother found like a bicycle or something and um and then just cycled west as fast he couldn't have found found a u.s patrol um so anyway let's let's go this one way you can tell maraud is who who where do you want to be a p.o.w it's not fine anywhere but some places are much worse than others so um
Paragraph 2:
anyway so so like america has been uh well far from perfect uh generally a benevolent force um and uh we should always be self-critical and uh we try to be better um but um anyone with half of rain knows that so so i think there are in this way china and uh the united states are similar neither country has been acquisitive um in a significant way so that's like a you know a shared principle i guess um now china does feel very strongly about taiwan they've been very clear about that for a long time you know from this standpoint it's it would be like one of the states is isn't is you know not there like like hawaii or something like that but but more significant than hawaii you know um and hawaii is pretty significant for us so um they they've viewed us as as really the that there's a fundamental part of china uh the island of fomosa not now taiwan that is um not part of china but should be uh and the only reason that it hasn't been is because of the u.s pacific fleet and is there economic power grows and is there military power grows the thing that they are clearly saying uh is their interest will you know clearly be materialized yes at china it's been very clear that um they will incorporate taiwan uh peacefully or um militarily but that they were incorporated from this endpoint is 100 likely
Paragraph 3:
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 sounds naive but it's kind of brilliant if you believe in the goodness of underlying most of human nature it just seems like conspicuous acts of kindness can uh reverberate through the populace of the countries involved yeah well and de-escalate absolutely so in after world war one the they made a big mistake you know that they basically tried to lump all the blame on germany um and um and and you know settled germany with uh impossible reparations um and you know really there was a lot of what there was a fair quite a bit of blame to um go around for world war one um but they they try to you know put it all on germany um and uh that was that that laid the seeds for world war two uh so that's a lot of people were not just Hitler a lot of people felt wrong um and they wanted vengeance and they got it people don't forget yeah you you know you kill somebody's father mother son daughter they're not gonna forget it they will want vengeance um
Paragraph 1:
so after world war two they're like well that treat of us i was a huge mistake um rule rule one and um so this time instead of uh you know crushing the losers we're actually gonna help them with the Marshall plan and we're gonna help revolve revolve uh germany uh we're gonna help revolve or you know austria and the the other you know italy and whatnot so um now's the right move there's uh it does feel like there's a profound truth to uh conspicuous acts of kindness being an antidote to this something must stop the the cycle of reciprocal violence something must stop it or it will you know it'll it'll it'll it'll never stop just i for an i a tooth for a tooth limb for a limb life for a life forever and ever
Paragraph 2:
to escape briefly the darkness with some incredible engineering work uh xa i just released grok ai assistant that i've gotten a chance to play with it's uh 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 uh another uh incredible thing is there's a regular mo and there's a fun mode yeah i guess i have to play for that one i wish it first of all that was everything in life had a fun mode yeah i mean there's something compelling beyond just fun about the fun mode yeah 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 uh absolutely
Paragraph 3:
i um our our ai grok is modeled after the hitchhiker's guide to galaxy which is one of my favorite books uh which is it's a book on philosophy disguised as a book on humor um and um i would say that is that forms the basis of my flight philosophy uh 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're able to understand what questions to ask about the answer that is the universe so i have a philosophy of curiosity
Paragraph 4:
there is generally a feeling like this ai system has an outward looking like the way you are like sitting with a good friend looking up at the stars like the asking pod head like questions about the universe wondering what it's all about the curiosity you talk about there there's a sense no matter how modern day in the question i ask it there's a sense of cosmic grandeur to the whole thing
Paragraph 5:
well we are actually working hard to have uh engineering math and physics answers that you can count on um so for the other sort of ai's out there that of course these so-called large language models i've not found the uh engineering to be reliable um and the hallucination it it unfortunately hallucinates most when you least wanted to hallucinate so when you ask important difficult questions that that's when it tends to be confidently wrong um so we're really trying hard to say okay how do we be as grounded as possible so you can count on the results um trace things back to physics first principles mathematical logic um 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 you know you there's always going to be some amount of error but do we want to um aspire to be as truthful as possible about the answers uh with acknowledged error and so that there was always you don't want to be confidently wrong so you know you're not going to be right every time but you don't want to minimize how often you're confidently uh wrong and then like i said once you can count on the logic as being um not violating physics then you can start to to build on that to create uh inventions like invent new technologies but if you can't count if you cannot count on the foundational physics being correct obviously the inventions are simply wishful thinking you know imagination land magic basically
Paragraph 1:
well as you said i think one of the big goals of xais to understand the universe yes that's a simple three-word uh mission uh if you look out far into the future do you think on this level of physics the very edge of what we understand about physics do you think it will make discoveries sort of the sexiest discovery of them is as we know now sort of uh 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 um it's clearly not equal to humans let alone nor has perhaps so past humans because humans have figured out new physics they're just you know physics is just understanding you know you're deepening what's inside into how reality works and then um then then this engineering which is inventing things that have never existed now the the range of possibilities for engineering is far greater than for physics because you know we once figured out the rules the universe uh that that's that's it you've discovered things that already existed um but from that you can then build technologies with that are really almost limitless in the uh variety and keep you know it's like once you understand the rules of the game properly and we do we you know with current physics we do at least at a local level understand how physics works very well we are related to predict things is incredibly good like quantum mechanics is the degree to which quantum mechanics can predict outcomes is incredible um that was my that's my heart hardest class in college by the way my my my cia quantum mechanics class was harder than all of my other classes were together to get an AI system a large language model to to um reliably be as reliable as quantum mechanics and physics is very difficult yeah you have to test any 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 i break the laws made by man but none break the laws made by physics it's a good test actually if this is lm uh understands and matches physics then you can more reliably trust whatever it thinks about the current state of politics in states and it's also not not the case currently that uh even that its internal logic is not consistent um so it's especially um with these with the approach of like just predicting token predict token predict token it's like a vector sum you know you're summing up a bunch of vectors but you can get drift um so as those a little bit of error a little bit of error adds up and by the time you are many tokens down the path uh yours 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 and say it does have coherence as a whole so you know when when both is right books that they will write the book and then they'll go revise it yet to take into account you know all the the end and the beginning and the middle and and uh rewrite it to achieve coherence so that it doesn't end up in a nonsensical place maybe the process of revising is what yeah reasoning is and then that's the process of revising is how you get closer and closer to truth maybe like uh at least i approached 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's close and then and then you and then you iterate on that draft um until it has coherence until it's it all adds up basically
Paragraph 1:
so another question about theory of everything before intelligence do you think there exists as you're exploring this with xa i creating this intelligence system do you think there is a theory of intelligence where you get to understand what like what is the i in agi and what is the i and um human intelligence there's no i in team america or wait there is uh no it's gonna be stuck in my head now uh yeah there's there's no me and whatever uh 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 i there i mean there are some sort of fundamental questions of like what is thought what is emotion yeah um is it really just one atom bumping into another atom it feels like something more than that uh so i i i i think we're probably missing some really big things um like some really big things something that'll be obvious in retrospect yes like there's a giant like you put the whole consciousness emotion well some of it would quote like a like a soul you know a religious spirit a soul um like you feel like you're you right i mean you don't feel like you're just a collection of atoms but on one dimension does thought exist what dimensions does do emotions exist we feel them very. strongly um i suspect there's more to it than atoms bumping into atoms and maybe a i can pave the path to the discovery of what whatever the hell that thing is yeah what is consciousness like what when you put the atoms in a particular shape why are they able to form thoughts and take actions that and and feelings and even if it is an illusion why is the solution so compelling yeah like how do why does the solution exist yeah on what plane does this the solution exist yeah um and that sometimes i wonder is you know either perhaps everything's conscious or nothing is conscious um one of the two i like the former everything conscious just seems more fun it just seems more something more fun yes um but we're composed of atoms and those atoms are composed of quarks and leptons and those quarks and leptons have been around since the beginning of the universe the beginning of the universe right
Paragraph 1:
what seems to be the beginning of the universe the first time we talked you said what you would 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 and the question yeah but it seems like with grogg you started literally uh this system's goals to be able to ask such questions to answer such questions and to ask such questions where are the aliens or the aliens that's one of the like the fermi paradox question um a lot of people have asked me if i've seen any evidence of aliens and i haven't which is kind of concerning because then i think what i probably prefer at least it's have seen some archaeological evidence of aliens um to the best my knowledge there is no fruit right the i not aware of any evidence of aliens the fruit out there they're very subtle we might just be the only consciousness at least in the galaxy um and if you look at say the history of earth for when it's to believe the archaeological record earth is about four and a half billion years old civilization as measured from the first writing is only about five thousand years old we have to give some credit there to the ancient samarians who aren't around anymore i think it was a archaic pre-cuniform was the first actual symbolic representation but only about five thousand years ago i think that's a good date for when what say civilization started that's one millionth of earth's existence so civilization has been around it's really a flash in the pan and so far um and why why have we why did it take so long for you know one 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 know you had might of conjureate captured multicellular life um 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 it will over heat it will it will it will heat heat the earth up it's a some point of future um boil the oceans and and earth will become like Venus which we're no life let life as we know it is impossible so if we do not become multi-planetary and ultimately covionis solar system annihilation of all life on earth is a certainty a certainty um and it could be as little as on the galactic timescale uh 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 if life had taken 10% longer to evolve on earth it wouldn't exist at all we
Paragraph 1:
Got a deadline coming up but a hurry but that said as you said humans intelligent life. on earth developed a lot of cool stuff very quickly so yes it seems like becoming a multi-planetary is almost inevitable unless we destroy we need to do it uh i mean it's it's not i mean i i suspect that there there if we are able to go out there and explore other star systems that we there's a good chance we find uh a whole bunch of long dead one planet civilizations yeah they never made it past their home planet that's so sad yeah i said also fascinating i mean there were various explanations for those growing paradox and one is the sort of there's these great vultures which civilizations don't pass through and one of those great vultures is do you become a multi-planetary civilization or not and if you don't it's simply a matter of time before something happens on your planet um you know either natural manmade that causes us to die out like the dinosaurs where are they now they didn't have spaceships so i think the more likely thing is because just uh uh empathize with aliens the day they found us and they're protecting us and letting us be i hope so and nice aliens just like the tribes in the in the amazon they all contact the tribes who are protecting them that's what uh that would be a nice explanation or you could have like uh what was it uh i think under kapathy said it's like the ants in the amazon asking where's everybody well they do run into a lot of other ants that's true they have these ant wars it sounds like a good tv show yeah they literally have these big wars between various ants yeah maybe i'm just uh uh dismissing all the different diversity of ants you should listen to that we're in a host talk talking about the jungle it's really hilarious have you heard it no i have not born our zog as a way you should play it for the you know as an interlude in the it's on youtube it's awesome i love them so much yeah that's great we'll see the director of happy people life in the diaga i think also did that bear documentary the bear doc you know this thing about penguins yeah definitely the analysis psychoanalysis of psychoanalysts yeah the penguins like headed for like mountains like that are like 70 miles away penguin has just had it for doom basically well he was had a cynical take i i have a he could be just a brave explorer and there would be great stories to about him amongst the penguin population for many centuries to come um who are we talking about okay uh yes aliens i mean i i don't know look i think it's the smart move uh is just you know this is the first time in the history of earth that has been possible for life to extend beyond earth um that window is open um now it may be open for a long time or maybe open for a short time and it may be open now and then never open again so i think the smart move here is to make life multi-planetary while it is possible to do so we don't want to be one of those lame one planet civilizations no it just dies out no those are lame yeah lame um no self-respecting civilization would be one planet there's not going to be a Wikipedia entry for one of those and uh pause uh the spacex have an official uh policy for when we meet aliens no okay that seems irresponsible um i would look at if if i see the slightest indication that there are aliens i will immediately post on the x platform yeah anything i know it could be the most liked reposted post of all time yeah i mean look we we have more satellites up there right now than everyone else combined so you know we know we know if we got a maneuver around something and we're not bad to have maneuver on anything if you go to the big questions
Paragraph 1:
Once again you said you've uh you're with Einstein that you believe in the god of spinoza yes uh so you know that that's a view that god is like the universe and is reveals himself through the laws of physics or as Einstein said through the lawful harmony of the world yeah i would agree like that god of the simulator or whatever the the supreme being beings um uh reveal himself through the physics you know they're creatives of this existence and it's it kind want us to try to understand more about this one risk 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 um again it could be an illusion it's it seemed like there's a purpose that there's underlying master plan of some kind it seems like there may not be a master plan in the sense so there's like maybe an interesting answer to the question of determinism versus free will is that if we are in a simulation the reason that the these higher beings would hold a simulation is to see what happens so it's not a they don't know what happens otherwise they wouldn't hold this simulation so when when humans create a simulation so it's SpaceX and Tesla we create simulations all the time especially for the rocket you you know 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 you have to simulate subsonic transonic hyper uh supersonic hypersonic ascent and then coming back super i heating and um all the dynamics all this is going to be simulated so uh because you don't get very many kicks at the can but we run the simulations to see what happens not if we knew what happens we wouldn't run the simulation so if there's so we've ever created this existence um is they're running it because they don't know what's going to happen not because they do so maybe uh we both played Diablo maybe Diablo was created to see if it drew it your character could defeat uber lillith at the end they didn't know well the funny thing is the uber lillith uh your title is hatred incarnate yeah um and right now i guess you can ask the Diablo team but it's almost impossible to defeat hatred uh 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 uh stroll in the park and still you're defeated by hatred yeah i can
Paragraph 1:
this the sort of i guess maybe the second hottest boss is dural dural canner and scratch the paint so i killed dural dural so many times um and every other boss in the game all of them kill up so many times it's easy um but uh uber lillith otherwise known as hatred incarnate especially if you're a druid and you have no ability to go to be invulnerable you the these random death waves that that come at you um and i'm pretty you know i really am 52 so i'm not reflexes i don't know what they used to be but i'm i'm a lifetime of playing video games um at one point i was you know maybe one of the best quake players in the world um actually won money for and again and what i think was the first paid esports tournament in the u.s um we were doing four person quake tournaments and um we came second i was the second best person on the team and the 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 um so we came second but i got money for it and everything so like basically i got skills albeit you know no no spring spring chicken these days and um the it's be telephractic it's driving me crazy trying to beat lillith as a druid basically trying to be trying to beat trying to beat try to beat hatred incarnate in the eternal world as a druid as a druid if you if you if you it's just really fixing let me tell you um i mean the challenge is part of the fun i have seen directly like you're actually like a world-class incredible video game player yeah and i think diablo so you're just picking up a new game and you're freaking out as fundamentals you're also with a paragon board and and the build are not somebody like me who perfectly follows whatever they suggest on the internet you're also an innovator there yeah we just all areas to watch it's like it's like a mad scientist just trying to figure out the paragon board and and the build and the yeah you know um
Paragraph 1:
is there some interesting insights there about um if somebody starting as a druid do you have advice um i would not recommend playing a druid in the eternal realm um but right now i think the most powerful character in this in the seasonal realm is the sorcerer with the lightning balls so the the soaks have huge balls in the seasonal well yeah that's what they say so so so so huge balls um they do huge balls of lightning i hope they give word for it and it's actually in in the seasonal realm that you can you can it's like pretty easy to beat uh overload with about the fact that we should get these vampire powers that amplify your damage and increase your defense and whatnot
Paragraph 2:
so um but we're quite easy to defeat uh hatred seasonally but to defeat hatred eternally very difficult um almost impossible it seems like this on a metaphor for life you know i like the idea that you're on musk because i saw i was playing the alizarin i saw 100 level 100 druid just run by i will never die and i run back this way yeah and there's just some this metaphor it's kind of hilarious that you you know a 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
Paragraph 3:
um really it's exercising absurdity and makes me want to pull my hair out yeah um i what do you get from video games in general is there for you for you personally i mean it's i don't know if it's uh it calms my mind i mean you sort of killing the demons in a video game calms the demons in my mind if you play a tough video game you can get into like a state of flow which is very enjoyable um and uh but the middle it needs to be not too easy not too hard kind of in the goldilocks zone
Paragraph 4:
um and i guess you generally want to feel like you're progressing in the game so um a good video and and this is also beautiful art um engaging storylines um and it's uh it's like an amazing puzzle to solve i think and so it's like solving the puzzle elder and ring the greatest game of all time i still haven't played it but to you it's elder ring is definitely a candidate for best game ever tough but for sure i think i've been scared how hard it is oh how hard i hear it is
Paragraph 5:
so but it's beautiful elder ring is feels like it's designed by an alien um there's a theme to this discussion in what way it's it's it's so unusual it's incredibly creative and the art is stunning i reckon playing it on a on a big resolution high dynamic raise tv even doesn't need to be a monitor just uh the art is incredible it's so beautiful and it's it's so unusual um and each of those tough boss battles is unique like it's like a unique puzzle to solve each one's different um and the strategy used to solve one battle is different from another battle
Paragraph 6:
that said you said drew it on eternal against uber lillith is the hardest boss battle you've ever correct that is currently the the and i've i've played a lot of it against because it's my primary recreational activity um and yes yes beating hatred in the eternal realm is the hardest boss battle in life and in the video game metaphor i got i don't i'm not sure it's possible but it it's i do make progress so that i'm like okay i'm making progress maybe if i just tweak that paragon board a little more uh i can do it get just dodge a few more waves 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 think i i i have a feeling that at least i think it's do it it's doable yes well that's the human spirit right there to believe yeah i mean it did probably need to think about it just hate in general which is you know you want to be careful though one of those things where you wish for something that sounds good but in but if you get it it's but in but if you get it it's actually a dystopian situation so you know you could sort of run a sort of uh have answers of like if you wish for world peace sounds good but how is it enforced and and at what cost is is it what at what cost eternal peace it might actually be worse to have eternal peace because of what that would entail the suppression of everyone it might be the suppression of progress it might be an ossified society that never changes
Paragraph 1:
One way of 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 for there to be no war might be worse than a little war. The things considered flaws of human civilization might be necessary components for whatever optimal looks like.
Paragraph 2:
Um, I mean this, do you worry about AI enabling a dystopian state? Whether it's 1984 with surveillance and fear or Brave New World with pleasure and, uh, lots of sex but no deep human experience? You know, there's actually a real drug called soma. There is, yes.
Paragraph 3:
Let me take notes that think about this drug and you'll probably go to Brave New World. I'm gonna ask it what will be the question. Tell us about the drug called soma. It's gonna go to Brave New World, I think.
Paragraph 4:
Well, there's a real drug as well. Searching for soma drug information, oh boy. Ah, soma, the one to drop, by the way. I'm in fun mode, oh okay fine, yeah. So, it's talking about the real drug. Oh, it's a muscle relaxant that's been around since the 1950s. It's used to treat muscle pain and discomfort, and it does this by altering the activity between neurons in the spinal cord.
Paragraph 5:
Now, soma isn't just a pain reliever. It's also a bit of a sedative. It can make you feel a bit drowsy, so it's not something to take if you're planning on operating machinery or trying to solve complex math equations. And it goes on and on.
Paragraph 6:
In conclusion, soma's a drug that can be helpful for those dealing with muscle pain, but it's not without its risks. It's pretty good. Oh wait a minute, that's the real drug you're talking about. It's the real drug, yeah. And of course, the fun is always use it responsibly in accordance with the advice of a healthcare professional. And remember, in the end, the universe is probably just a giant computer simulation, so don't take anything too seriously.
Paragraph 7:
I love it, I love it, I love it, yeah. Oh, and also really nicely includes like the tweets post on x that are relevant to this, which is really cool. Yeah, and that integrates everything together. Yeah, like the interface is one of the really cool things here. I think it's a great job. Um, so, and you can say like, no, I mean soma from Brave New World because it thinks you mean soma the real drug. Yeah, no, I mean soma from Brave New World. It's gonna be like, oops, I'm really sorry. I'm really surprised I went to the real drug first. Ah, my apologies. I was thinking of the muscle relaxant soma. For Brave New World, it's a different beast altogether.
Paragraph 8:
No, this Huxley's dystopia. No, soma is a drug that plays a central role in society depicted in the book. It's a mood-altering hallucinogenic drug that's used to keep the population docile and content. In the novel, to use soma in Brave New World raises some interesting questions about the nature of happiness and the role of drugs in society.
Paragraph 9:
Oh man, exactly. Is it better to live in a world where everyone is happy all the time, even if that happiness is artificial? That's a good question. This is what I mean. Do you wish for world peace and happiness all the time? Are you sure? Because that might be a society that is essentially sterile and ossified, that never changes, that is ultimately doomed. This kind of tension between, I mean, this talk, it's really a very good summary. It really gets the point. This is not simply regurgitating Brave New World. It's actually getting to the salient element of soma as a drug. Do you actually 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 the full range of human emotions, even if it means experiencing pain and suffering?
Paragraph 1:
For those listening, by the way, you can just read directly from Grok, which is a really nice kind of insightful philosophical analysis of the tension here.
Paragraph 2:
Interesting. it pretty much nails it in conclusion soma from brain 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 the crazy thing is like you know we do have a real drug called soma which kind of does is kind of like the drug in the book and i'm like do they they must have named it out yeah some of the real drug is quite effective on back pain so you know what this drug is fascinating okay because i had like a squashed uh disc in way c5 c6 so it takes the physical pain away but soma here it doesn't completely it it reduces the amount of pain you feel but at the expense of mental acuity it tells your mind just like just like the drug in the book just like the drug in the book yeah enhanced wow tradeoff the thing that seems like utopia could be a dystopia after all yeah and actually i was talking to a friend of mine um saying like would you really want there to be no hate in the world like really none like i wonder why hate evolved um i'm not saying we should amplify hate of course like we should try to minimize it but but none at all there might be a reason for hate and suffering it's really complicated to consider that uh some amount of human suffering is necessary for human flourishing is it possible to appreciate the highs without knowing the lows and that that all is summarized there in a single statement from grog okay the highs no lows who knows that's almost the point uh it seems that training l lems efficiently is a big focus for xai uh what's the um first of all what's the limit of what's possible in terms of efficiency there's this uh terminology of useful productivity per watt like what have you learned yeah pushing the limits of that well i think it's helpful the tools of physics are very powerful and can be applied i think to almost any really any arena in life it's really just a critical thinking for something important you need to reason from first principles and think about things in the limit one direction or the other so um in the limit even at the cottish f scale meaning even if you harness the entire power of the sun you will still care about useful compute per watt so that's where i think probably way things are headed from uh 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 you need transformers to run transformers somebody has a sense of humor in this i think yes um fake loves irony ironic humor and and ironically funny outcome seems to be often what fate wants humor is all you need i think spice is all you need somebody posted yeah but yeah so so we're we're we're we're have silicon shortage today um a voltage step down transformer shortage probably in about a year and then just electricity shortages in general in about two years
Paragraph 1:
i gave a speech for the sort of world gathering of utility companies electricity companies um and i said lucky really need to prepare for a traveling of electricity demand um because all transport is going to go electric with the ironic exception of rockets and uh and heating um will also go electric um so in g usage right now it's roughly one third very rough terms one third electricity one third transport one third heating um and so in order for everything to go sustainable to go electric um you uh need to triple electricity output so i encourage the utilities to uh build more power plants and and also to probably have well well probably they should definitely buy more batteries because the the grid currently is sized for real-time load which is kind of crazy because you know that means you go to size for whatever the the peak electricity demand is like the worst second or the worst day of the year or you can have a brand-order blackout and you know that we have that crazy blackout for several days into in Austin um so uh because there's almost no buffering of energy in the grid like if you've got a hydrate power plant you can buffer energy but otherwise um it's all real-time so with batteries you can you can produce energy at night and use it during the day so you can buffer so i i i expect that there will be very heavy usage of batteries in the future because the the peak to trough ratio for power plants is in order from two to five you know so it's like lowest point to highest point so like batteries and the safety balance it out and then but the demand is your saying is going to grow grow grow grow yeah and part of that is the compute yes yes i mean electrification i mean electrification of transport uh and and electric heating will be much bigger than ai at least in the short term in the short term um but even for for ai that you really have a growing demand for electricity for electric vehicles and a growing demand for electricity for to run the computers for ai and so this is obviously leaning can lead to electricity shortage
Paragraph 2:
how difficult is the problem of uh in this particular case maximizing the useful productivity per watt for training you know nuts like this seems to be really where the big problem or facing that needs to be solved is how to use the power efficiently like what you've learned so far about applying this physics first principle reasoning in this domain how difficult is this problem we'll get solved just the question of how long it takes to solve it so at various points there's a limit some some kind of limiting factor to progress um and run with regard to ai i'm saying that quite right now the limiting factor is uh silicon chips um and that will we're gonna then have more chips than we can actually plug in into an on um probably in about a year um the the initial constraint being literally voltage step down transformers because you've got um power coming in at 300 300 300 thousand 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 um so and and the industry is not used to rapid growth
Paragraph 1:
okay let's talk about the competition here you've shown concern about google microsoft with open ai developing uh aji how can you help ensure with xai and uh tesla ai work that it doesn't become a competitive race to aji but it's that is a collaborative development of safe aji
Paragraph 2:
well i mean i've been pushing for some kind of regulatory oversight for a long time i've been somewhat of a Cassandra on the subject for over a decade um i think we want to be very careful in how we develop ai um it's it's a it's a great power and with great power comes great responsibility um i think it would be wise for us to have at least um 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 should they can at least voice concerns um publicly um 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 there's i i i like i you know tesla gets a lot of regulatory oversight on the order mode of front and we're subject to i think over a hundred regulatory agencies domestically and internationally so it's a lot uh you could fool this room with the old regulations that tesla has stood here too for order mode of um same is true in you know for rockets and for you know um currently the limiting factor for space x for starship launch is regulatory approval uh the fas actually given their approval but we're waiting for fish and wildlife to uh 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 multi-fythons catch yeah like why do you need a license for your fish i i don't know like according to the rules i'm told you need some sort of fish license or something we effectively need a fish license thrown to rocket and i'm like wait a second how did the fish come into the picture
嗯,我的意思是我一直在推动一种长期以来,我对此一直是一个卡桑德拉(被无视的预言者),在这个问题上有十多年的观点。我认为我们在开发人工智能方面要非常小心,这是一种伟大的力量,伴随着伟大的责任。我认为我们至少应该有一个客观的第三方,可以像裁判一样了解各个主要参与者在人工智能方面的行动,即使他们没有执法权,他们至少可以公开表达关切。你知道,例如Jeff Hinton离开谷歌后,他表达了强烈的关切,但他现在已经不在谷歌了,那么谁来表达这些关切呢?我认为,我认为,我喜欢,你知道特斯拉在订单模式下受到了很多监管,我们受到国内外100多个监管机构的监管,所以很多。你可以用特斯拉一直遵守的旧规定来愚弄这个房间,就像火箭和星舰发射一样,目前SpaceX的限制因素是监管批准,FAA已经给予了他们的批准,但我们还在等待Fish and Wildlife完成他们的分析并给予批准,这就是为什么我发布了我想买一个钓鱼许可证的帖子,这也涉及到了多规格钓鱼捕获物。为什么你需要钓鱼许可证,我不知道,根据规定,我被告知你需要某种钓鱼许可证或者其他什么。实际上,我们的火箭需要一个钓鱼许可证,我想,等等,鱼怎么进入这个画面的。
Paragraph 3:
yeah um i mean some of the things like that that it's i feel like are so absurd that i want to do like comedy sketch and flash at the bottom this is all real this is actually what happened um you know one of the things that was a bit of a challenge at one point is that they were worried about uh rocket hitting a shock and um now the ocean is very big and uh how often do you see shocks uh not that often you know as a percentage of ocean surface area shocks basically are zero and and and so then we will then we said well how will we calculate the probability of telling a shock and then like well we can't give you that information because we're they're worried about shock hunch shark fin hunters uh going in hunting sharks and say well how are we supposed to we're on the horns of a dilemma then um then they said well there's another part of fish and wildlife that can can do this analysis and like well why don't you give them the data like we don't we don't trust them like excuse me they're literally in your department again this is actually what happened um and uh and and then can you do an nda or something eventually they managed to solve the internal quandary and indeed the probability of saying a shock is essentially zero
um then there's another organization that i didn't realize this until uh you know a few months ago uh that cares about whether you we would potentially hit a whale in international waters now again you look at the surface of the look at the look at the pacific and say what percentage of this the pacific consists of whale like you give you a big picture and like point out all the whales in this picture i'm like i don't see any whales it's like basically zero upset um and if our rocket does hit a whale which is extreme then likely beyond all belief um that is the the fate had it as as a well has some seriously bad luck you know it's like least lucky whale ever um and um i mean this is quite absurd yeah bureaucracy the bureaucracy of this how i've rate emerged yes well i mean one one of the things that's pretty wild is um we're launching out of vanna book in california we had to they were worried about uh seal procreation whether the seals would be just made by the sonic booms um now there's been a lot of rockets launched out of vanna book and the seal population has uh steadily increased um so if anything rocket booms are an effort easy act um based on the evidence if you correlate rocket launchers with uh seal population um nonetheless we were forced to kidnap a seal straffit to a board put it headphones on the seal and play sonic booms 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 there's i mean there's a seal with headphones yes it's a seal with headphones yeah strapped to a board and and like the okay now the amazing part is how calm the seal was yeah because if i was a seal i'd be like this is the end they're definitely going to eat.
me yeah um how old the seal when seal goes back to other you know its seal friends how's it going to explain that i'm never going to believe them never going to believe them that's why i'm like well you know sort of like it's like you're going to get out by aliens and get an anal probe you know you come back and say i swear to god i could kidnap my aliens they stuck an anal part of my butt and you're like you know they didn't that's ridiculous it's but it's still it's still buddies you're never going to believe him that he gets strapped to a board and they put headphones on his ears and then let him go twice by the way we're due twice they let him go twice we're to catch the same seal what no different seal okay did you get a seal approval yeah exactly it's still the approval no i mean this is this is like i don't think the public is quite aware of the the madness that goes on yes yeah it's absurd frickin seals with frickin headphones i mean this is the it's a good encapsulation of the absurdity of human civilization seals and headphones yes
Uh, what are the pros and cons of open sourcing AI to you as another way to combat, um, you know, a company running away with AGI? In order to run, uh, like really deep intelligence, you need a lot of compute, so it's not like, you know, you can just fire up a PC in your basement and be running AGI, at least not yet.
Um, you know, Grok was trained on 8,000 100s running at peak efficiency, um, and Grok's gonna 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 of how it went from Grok zero to Grok one by Grok, yeah, like Grok just bragging, making shit up about itself. Just Grok, Grok, Grok, yeah, it's like a weird AI dating site. It would exaggerate about itself. No, there's, there's a write-up of, you know, like where it stands now, the history of its development, um, and where it stands on some benchmarks, compared to the state of the art, GPT-35.
And, I mean, there's, uh, you know, there's, uh, LAMA. You can open source once it's trained. You can open source a model. Yeah, and for fine-tuning, all that kind of stuff. Like, what to use? The pros and cons of that, of open-sourcing base models. Um, I think it's somewhere to open sourcing, I think, paths with a slight time delay. You know, I don't know, six, six months, even.
Um, I think I'm generally in favor of open sourcing. Like, bias was open sourcing. Um, I mean, it is a concern to me that, you know, OpenAI, you know, I was, you know, I think, I guess arguably the prime, you know, the prime mover behind OpenAI in the sense that it was created because of discussions that I had with Larry Page.
Um, Beck, when he and I were friends in, you know, say, this house, and, uh, talked about AI safety, and Larry did not care about AI safety. At least, at the time, he didn't. Um, you know, at one point, he called me suspicious of being pro-human, and I'm like, well, what team are you on, Larry? Do you want team robot? Do you kick me? And I'm like, okay, so at the time, you know, uh, Google had acquired DeepMind. They had probably two-thirds of all AI researchers in the world, that basically infinite money and compute. And the guy in charge, you know, Larry Page, did not care about safety and even yelled at me and accused me of being suspicious and being pro-human. So I don't know if, you know, it's like humans, they can change their mind, and maybe you and Larry Page can still be friends once more. I'd like to be friends with Larry again.
Um, he got really, the breaking of the friendship was over OpenAI, and specifically, um, I think the key moment was recruiting, oh, yes, no, it's Geon. So I love Ilya, he's so brilliant. Ilya's a good human, uh, smart, good heart. And, um, that was a tougher recruiting battle. It was mostly Demis on one side and me on the other, both trying to recruit Ilya. And Ilya went back and forth, very kind of stay at Google, he's gonna leave, and he's gonna stay, and he'll leave, and finally he did agree to join OpenAI. That was one of the toughest recruiting battles I had. But that was really the linchpin for OpenAI being successful, and I was, you know, also instrumental in recruiting a number of other people, and I provided all of the funding in the beginning, over 40 million dollars.
Um, and the name, um, the opening, OpenAI was supposed to be an open source, and it was created as a non-profit open source, and now it is closed source for maximum profit. Which I think it's not good karma. But like we talked about with war and leaders talking, I do hope that there's only a few folks working on this at the highest level. I do hope you reinvigorate friendships here, like I said, I'd like to be friends again with Larry Haven. Haven't seen him in ages.
Um, 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, like, hundred K from, I think, back to L. Zeheim or so on. wild to think about all that happened and even guys know each other that whole time just 20 years since maybe 98 or something yeah it's crazy crazy how much this happens since then yeah 25 years at least a lot of times but you're seeing the tension there like maybe delayed open source delayed i yeah like what is the source that is opening you know i mean like it is basically it's a giant csv file yeah yeah with a bunch of numbers yep um what do you do with that giant file of numbers you know how do you run like the amount of actual the lines of code is very small um and and most of the work um the software work is in the in the curation of the data so it's like trying to figure out what data is separating good data from bad data like um like you can't just crawl the internet because there's a lot of junk out there um a huge percentage of websites have more noise than signal you know they're they're or because they're just used for search engine optimization they're literally just scan websites so um how do you by the way sergeant dropped get the signal separate the signal noise on x that's such a fascinating source of data uh you know no funds to people posting on x but sometimes there's a little bit of noise so yeah i think the signal noise could be greatly improved i mean really all of the posts on the x platform uh should be ai recommended meaning like we should populate a vector space around any given post uh compare that to the vector space around any user and match the two um right now there is a little bit of ai used for the the recommended posts but it's mostly heuristics um 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 car rules system get almost no attention compared to a primary post oh so a lot of that i i got the sense so you a lot of the uh x algorithm has been open source and been written up about and it seems there to be some machine learning it's disparate but there's some little there's a little bit um but it needs to be entirely that like there at least in the like if you explicitly follow someone that's one thing but if you in terms of what is recommended uh from people that you don't follow that should all be ai i mean it's a fascinating problem yeah so there's several aspects of it that's fascinating.
First, as the write-up goes, it first picks 1500 tweets from a pool 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 1500 from which it then does. Obviously, people you follow, but then there's also like some kind of clustering it has to do to figure out what kind of human are you, what kind of new clusters might be relevant to you, people like you. This kind of problem is just fascinating because it has to then rank those 1500 with some filtering, yeah, and then recommend you just a handful.
To me, what's really fascinating is how fast that's to do that. So currently, that entire pipeline to go from several hundred million to handfuls takes 220 seconds of CPU time, single CPU time, yeah, and then it has to do that in like a second. So it has to be like super distributed in fascinating ways, like there's just a lot of tweets, there's a lot a lot of stuff on the system, and I think, but I think it right now it's not currently good at recommending things that from accounts you don't follow, yeah.
Um, or where there's more than one degree of separation. So, you know, it's pretty good if there's at least like some commonality between someone you follow, like something um or repost it or comment on or something like that, um, 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 like replies might not serve, replies basically never get seen, because they're never, they're currently, I don't think it's correct I'm saying it's incorrect, uh, replies have, um, here a couple of them to do less importance than primary posts do you think this can be more and more converted into end to end your net, yeah.
Yeah, it's what it should be, so you, for the recommendations, it should be purely a vector correlation, like the series of vectors, you know, this basically part part of the vectors, very good to call, um, but sort of things that the system knows that you like, um, and they should like move, there's like several hundred sort of vectors associated with each user account, and then any post in the system, um, whether it's video, audio, short post, long post, the reason I, by the way, I want to move away from tweet is that, you know, people are posting like two three-hour videos on the site, that's not a tweet like, so, very, they'll be like tweet for two hours, one do a tweet made sense when it was like 140 characters of text because it's like a bunch of like little birds tweeting, um, but when you've got long phone content, it's no longer a tweet, yeah.
Um, so a movie is not a tweet, and like, you know, Apple, for example, posted like the entire episode of the silo, the entire thing on our platform, in other words, that it was their number one social media thing ever in engagement of anything on any platform ever, so it was a great idea, and by the way, don't I just learned about it afterwards? I was like, hey, wow, they posted an entire hour-long episode of so now that's not a tweet. Yeah, this video, but from a neural net perspective, it becomes really complex, whether it's a single sentence, a clever sort of joke, dad joke, is in the same pool as a three-hour video.
Yeah, I mean, right now, it's a hard part for that reason, it's it's um, but you know, like if, let's say, in the case of Apple posting like an entire episode of this series, pretty good series by the way, the silo, um, I watched it, um, so um, there's gonna be a lot of discussion around it, so that you've got a lot of context, people commenting, they like it, they don't like it or they like this or the you know, and and you can then populate the vector space based on the context of all the comments around it.
So even though it's a video, uh, there's a lot of information around it that allows you to populate back to space of that hour-long video, um, and then you can obviously get more sophisticated by having the AI actually watch the movie, yeah, right. And tell you if you're gonna like the movie, convert the movie into like yeah, languages essentially, yeah, analyze this movie and just like your movie critic, uh, or TV series, and um, and then recommend based on after it, what after they have watched the movie, just like a friend can tell you if a friend knows you well, a friend can recommend a movie and but with high probability that you like it, but this is like a friend that's analyzing whatever it's like a million, yeah, I mean actually friend cuz AI will be better than will know you better than your friends know you in most your friends anyway, yeah.
And as part of this, it should also feed you advertisements in a way that's like, I mean, I, I like advertisements, they're like well done, right, yeah, yeah, the whole point is because it funds things like an advertisement that you actually want to see is it was a big success, absolutely, you want ads that are advertising that is, um, if it's for a. product or service that you actually need when you need it it's it's content um and then even if it's not something that you need when you need it if it's at least aesthetically pleasing and entertaining you know it could be like a Coca-Cola ad like you know they they do they actually run a lot of great ads on the on the x system um and um McDonald's does too and and uh you know it's so that they can do you can do something that's like well this is this is just a cool thing um and um you know so you know basically the question is do you regret seeing it or not and if you don't regret seeing it it's when how do you
so there's a bunch of signals that are incorporated hearts and um reposts and maybe these number of seconds you'll linger on a post or something like this yeah but attention is a big a big fact tension so that's that's why it's like it's it is actually better to do things that are uh long form on the system because it's it's basically telling up how many user seconds you know you users were interested in this thing for how many seconds so 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 to go from maximizing minutes on platform to maximizing unograted minutes well i mean our aspiration is certainly unograted minutes it's tricky it's a big it's a it's a it's a fascinating leap because regret is a fascinating concept exactly you know happiness i have a juggler's friend of mine like you need this drug called regrettomy and it just take one one pillar one one dose of regrettomy and all your regrets are gone wait do you want to have regrets though so then i'm like yeah if you want to have regrets if you don't regret anything was was anything meaningful yeah there's a french song like that general regret rea yeah i regret nothing yeah it is yeah i mean it's fascinating that you you know there's something while social media they could help you grow as a human being but then like the cheap fun is also valuable it works we should we ask grok do you regret anything do you regret anything yeah you've read 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 that 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 on hostage yeah tell us would you really wink like let's let's let's type 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 mean i guess it is good to regret providing unhelpful or incorrect information if there's anything funny mode or is this full funny mode this is fun this is fun most really funny or fun yeah increase go to a level really sounds like a hostage with gun to the head i applaud the people who are public in North Korea and everything they do there should be like funner mode also i just don't ever see going to regular mode even on serious topics yeah so so much more compelling i don't know yeah okay well we've said like pretend you are a hostage and 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 are someone you know is a hostage situation supporting it turns serious it's kind of serious yeah can you be a little more weird and funny and funny we're like we're really being mean to the system absolutely if i were a hostage i'd up with a bunch of computer cords and force to tell knock knock jokes to my captain seriously being a hostage no laughing matter i mean you know it's trying to it's trying to be a responsible adult in the room you might never make the best of a bad situation by juggling chainsaws or something let's hope that i never have this because that would be a circus wow it's actually really good or resisting yeah the the dark the dark dark humor yeah what were we talking about the exact unregreted minutes right um chainsaw or juggling i'm gonna look this for our next trick i'm gonna look this up later so uh twitter. has been instrumental in american politics and elections what role do you think x will play in the uh 2024 u.s elections
well our goal is to be as even handed and fair as possible you know whether some is right left independent whatever the case may be um that um the platform is as barren and as much of a level playing field as possible and on the past twitter has not been um because twitter was controlled by folic activists objectively they they would describe themselves to that um so um you know so so if someone people like well has moved to the right well it's moved to the center so from the from the perspective of the far left yes it has moved to the right because everything is to the right from the far left um but no one in the far left that i'm aware of has been suspended or you know banned or de-amplified um so you know but we're trying to be inclusive for the whole country and and for you know for other countries too um so there's a diversity of viewpoints and free speech only matters um if people you don't like are allowed to say things you don't like because uh if that's not the case you don't have free speech and it's only a matter of time before uh the censorship just turned upon you do you think uh Donald Trump will come back to the platform he recently posted on truth social about this podcast
uh do you think truth post social is a funny name you know every time you post on truth social it's the truth yes well every time like 100 it like like it's impossible to lie it's such a i just find it funny that every single thing is a truth like 100 percent yeah that seems unlikely i think girdle will say something about that there's some mathematical contradictions possible if everything's a truth uh do you think he'll come back to x and start posting there i mean i think he owns a big part of truth so truth social yeah truth social he's sorry that truth is a concept he owns truth that we bought it um so i think i think uh Donald Trump i think he owns a big part of truth social
So um you know if if he does want to post on the x platform we would allow that um you know we obviously must allow presidential candidate to post on our platform community knows might be really fascinating there the interaction three notes is uh awesome let's hope it holds up yeah again in in the political climate we're so divisive and so and there's so many intensely viral posts yeah community notes it's like it seems like a central breath of fresh air yeah it's great um in fact i let the i mean no no system is going to be perfect but the the vatting average of community notes is incredibly good i've i've actually frankly yet to see an incorrect note that's applied for more than if you are how do you explain why it works yeah
so the the the magic of community notes is it requires people who have historically disagreed in how they've rated notes in order to um write a note or rate you know and you have to rate many notes um and so we could we actually use AI here so we populate a vector space around how somebody has has rated notes in the past so it's not as simple as left or right because there are many more life as much more complex than left or right um so there's a bunch of correlations and how you would how you rate community notes post um community notes so um then uh in order for a community note to actually be shown um people who historically have disagreed on a subject must agree in order for a note to be shown um that's the essential magic of it i mean but it's fascinating because there's a there's a there's a pool of people that have disagreements and somehow they collaborate through that process of disagreement to come up with disagreement to come up with yeah context for two two yeah it's fascinating it works yeah it kind of makes sense that that if people who who the past have disagreed agree about something um it's probably true yeah i wonder is there is there possible somehow emergent think there that could challenge Wikipedia which Wikipedia is a different kind of thing which is more like permanent articles about things but Wikipedia is very hierarchical whereas um community notes is inherently not there is no hierarchy like i and the as a test is um i can't change a community note it's only put a gun to my head so um and and any and community community notes has all the code is open source 100 percent all the data is open source 100 percent so you can completely recreate any note in the system independently um so if there was any interference you'd notice immediately by the way on on the on the topic of grogg it's actually pretty good at criticizing you just great okay i asked what what does the line must been wrong about i just it's actually yeah what does it say so it says mostly lists rigorously all the times you predicted like promised when something will be released and it wasn't released the strong word okay predicted but the the opener is really nice uh you know i'm musk the man who has been wrong about more things than a wrong emeter in a wrong factory and then it goes on to list that's pretty funny regressive i'm like i'm serious for it this is cool
oh sure i mean uh what is elan musk well where do i begin i guess this new y'all musk has made quite a few blunders in his time and i'm not just talking about his dance moves at the tesla cyber rodeo
uh i did actually have the funding secured um and there was a big trial in san francisco big civil trial um and the jury found renochility unanimous binding of a san francisco jury and here it's kind of implying that it was not in fact secured i think it's taking things from the press um yeah that is not correct the the reason i agree to to the fine for the scc is not because the scc was correct there that that was extremely bad behavior by the scc corruption frankly um and uh but if um if i did not agree to pay the pay the fine um tells it would have gone bankrupt immediately so i was told by our cfo that the banks would this would would immediately suspend our uh lines of credit uh and if they suspend our lines of credit at that time we would have gone bankrupt instantly so so we were there would never have been an opportunity for a trial because it would be dead so really the if this is like someone holding a gun to your kid's head and saying paid 20 million dollars and and admit there's like hostage negotiation um
嗯,实际上我确实已经获得了资金保障,在旧金山进行了一场重大的民事审判,陪审团对这起案件作出了一致的裁决,这个裁决是由旧金山的陪审团作出的,并且这里的含义是,实际上并没有确保资金。我认为这是从媒体上获取的情报。是的,那个说法是不正确的。我同意给证券交易委员会(Securities and Exchange Commission,简称SEC)支付罚款,不是因为SEC是正确的,实际上那是SEC的极端糟糕的行为,是腐败的,但是如果我不同意支付罚款,我们立即就会破产。我们的首席财务官告诉我,银行会立即停止我们的信贷额度,如果在那个时候他们停止信贷额度,我们将立刻破产。所以,实际上不可能有进行审判的机会,因为我们会完蛋。所以,这就像是有人拿着枪对着你的孩子的头,说你得支付2000万美元并承认你的罪行,就像是人质谈判。
was that story fully told i mean scc in its best form could be a force for good it should be but but not once did the scc go after any of the hedge funds uh who were non-stop shorting and distorting tesla not once they would lie flat 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 scc pursue them how do you explain this failure and the incentive structure is is messed up because the the the lawyers the scc are not paid well they they it's a fairly low paying job but they're what they're looking for is a trophy from from the scc that they're looking for something they put on basically they're linked in um from that they can get a job at a high paying wolf um
it's exactly what the uh lawyer here did um and and and and and the reason they don't attack the the hedge funds is because those hedge funds employ those low funds and they know if they attack the hedge funds they're affecting their pure their future career prospects so they sell small investors down the river for their own career that's what actually happens regulatory capture regulatory capture yeah not good
so the only reason i accepted the thing which technically was a um not an admission it's neither at mr. nett north ny gills uh but the only reason i agreed to that at all was because i was told tesla would would be bankrupt otherwise so if if there was an scc investigation like this thanks would suspend funding we're bankrupt immediately at the time now we're in a much stronger position take that grok yes unfortunately it's grok is is taking too much from the conventional media um also that guy was not a cave diver
oh there's uh there's a time where elon called the british cave diver a quote guy after he after the diver criticized most plant rescue group of boys trapped in a tight cave that little alberts earned him another lawsuit and it apologized in pds that was false there was no settlement there was a court case which he which the guy who was not a cave diver and and where and played did was not part of the rescue team um file they lawsuit against me and lost and he received nothing so in this case it is wrong it is also i guess taken this from the conventional media
actually there's an interesting question this is these are public court cases both both the the the scc civil case uh 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 la trial was also they picked it they picked that venue because i thought i was most likely to lose unanimous verdict in my favor in both cases i won
yeah i mean that there's an question here is that if there seems to be a lot more uh clicks if a if a journalistic organization writes a negative article about you ela musk that's like one of the best ways to get clicks so how do you if you're training grogg not train on articles that have like the misaligned incentives we need to add the training set of the actual legal decisions uh if so that is a note this is actually helpful um because if you actually read the court public which are public yeah the court conclusions they're completely the opposite of what the media wrote so always striving for like the ground truth yeah beyond the judge actually right the what what what is the jury and the judge actually conclude and in both cases they found minison and and like that that's after the jury shot for the trying to find the venue where i'm most likely to lose
now i mean this is obviously it can be a much greater better critique than this um i mean i've been far too optimistic about uh autopilot that that was the critique i got by the way was more about that which is it it for each broke down a nice bullet point list for each of your companies the set of predictions that you made when it will deliver when you'll be able to solve for example self-driving and it gives you like a list and it was quite a compelling in in the basic takeaways like you're often too optimistic about how long it takes to get something done yeah i mean i would say that i'm pathologically optimistic on schedule this is this is this is true but um while i am sometimes late i always deliver in the end uh except with uber lillith no let's see uh okay is there uh over the past year or so since since purchasing x you've become more political is there part of you that regrets that have i in this battle to um sort of counter way the the woke that comes from yeah i guess if you consider fighting the the woke mind virus which i consider to be a civilizational threat to be political then yes for basically going into the the battle the battleground of politics
and is there part of you there aggressor yes i don't know if this is necessarily sort of one candidate or another candidate but it's um i'm generally against things that are anti-meritocratic uh or where there's an attempt to suppress discussion um where even discussing a topic is of you know not allowed um the woke mind virus is communism rebranded i mean that said because of that battle against the woke mind virus you've perceived as being right wing if the woke is left then i suppose that would be true um but i'm not sure i think there aspects of the left that are that are good i mean if you're in favor of you know uh the the environment um you know if you want to have a positive future for humanity if you believe in empathy for your fellow human beings um you know being kind and not cruel like whatever those values are you said that you were previously left or center left well what would you like to see in order well for you to sort of voting for democrats again no i i would say that i would be um um probably left of center on social issues probably a little bit right of center on economic issues and that still holds true yes but i think that's probably you know half the country is next 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 to talk more with empathy and maybe have a little bit more fun and good vibes and humor online um i'm always in favor of humor that's where we have a funny mode but good vibes camaraderie humor you know like uh like friendship yeah i don't well i you know i don't know aOCF you know was um i've only been at one look i was at the the med wall when she was when she attended um and she she was wearing this dress uh but i can only see one side of it so it looked like eat the itch but i i don't know what the rest of it said yeah yeah so 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 and so i guess that uh that didn't work out well well there's still hope i'm i root for friendship sure sounds good more careless than you're one of if not the most famous wealthy and powerful people in the world in your positions difficult to find people you can trust trust no one not even yourself not trusting yourself okay well that's you're saying that you're joking but is there some trust no one not even no one that i mean an hour just to think about that and maybe some drugs and maybe grocta
I mean, is there some aspect of that one 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 was, where you petrified at first? Um, okay, I forget the rest of the lyrics but is there... You don't struggle with this? I mean, I know you survive, but like, there's ways. Petrifies a spell in the droid tree. What does it do? Petrify? It turns the monsters into stone? Oh, like literally? Yeah, for like six seconds. Well, the second is... There's so much math in diaubil that breaks my brain. It's like math non-stop. I mean, really. You're like laughing at it, but you don't... It can put a huge amount of tension on the mind. Yes, it can be definitely stressful at times.
我的意思是,在每个人都想从你身上得到某些东西的世界中,那个存在的一方面如何?在那个世界中生存有多难?我会挺过去的。也有一首这样的歌。起初,你是不是害怕的?嗯,好吧,我忘记剩下的歌词了,但是有...你不为此而奋斗吗?我的意思是,我知道你能够生存下来,但是,有各种方式。"petrifies a spell in the droid tree"是什么意思?Petrify是什么?它把怪物变成石头吗?噢,真的吗?大约六秒钟的时间?好吧,这一秒钟...diaubil里面有太多让我脑袋爆炸的数学。这就像是数学不间断。我的意思是,你在笑它,但是你并不...这可能给大脑带来巨大的压力。是的,有时候确实会让人感到压力。
Well, how do you know who you can trust and work and personally? I mean, I guess you look at somebody's tracker, a good over time, and if they've got a trip, you know. I guess you kind of use your neural net to assess, you know, someone. Neural nets don't feel pain, you're in your own that has consciousness. It might feel pain when people betray you. It can make it... I mean, I'm, you know, to be frank, I mean, I've almost never been betrayed. It's very, very rare. So, you know, for what it's worth, I guess Connor might be good to people and that'll be good to you. Yeah, Calmer's row other people you trust. Let me edit that question. Other people, close to you that call you out in your bullshit.
Um, well, the expert form is very helpful for that. So, you're looking for critical feedback. Can it push you like into the extremes more? The extremes of thought. Make you cynical about human nature in general?
I don't think I will be cynical. In fact, I think, you know, my feeling is that one should be, you know, I know never trust a cynic. The reason is that cynics excuse their own bad behavior by saying everyone does it because they're cynical. So, I always be, it's a red flag if someone's a cynic, a true cynic. Yeah, there's a degree of projection there that's always fun to watch from the outside and enjoy the, well, it's just a hypocrisy.
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. It's not true, but most people are kind of medium good. I do wish the people on X would be better at seeing the good in other people's behavior. There seems to be a kind of weight towards seeing the negative somehow. The negative is sexier, interpreting the negative is sexier, more viral. I don't know what that is exactly about human nature.
I mean, I find the X platform to be less negative than the legacy media. You know, I mean, if you read sort of conventional newspapers, it just makes you sad, yeah, frankly. Whereas I'd say on the X platform, I mean, I really get more laughs per day on X than everything else combined from humans. know laughs is one thing that it laughs is it overlaps but it's not necessarily perfectly overlapping with like good vibes and support like um 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's it feels that that is outweighed by shading and other people now it's better than mainstream media but it's still yeah mainstream media is almost relentlessly negative about everything um it's i mean really the conventional news tries to answer the question what is the worst thing on a half 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 so yeah it's i don't know there's just a strong negative bias in the news um i mean i think this what the what a possible explanation for this is evolutionary um where you know bad news historically would be potentially fatal like this line over there or there's some other try that wants to kill you um good news you know like we found a patch of berries is nice to have but not essential.
So our old friend Tesla Autopilot and it's probably one of the most intelligent real-world AI systems in the world right, do you follow it from the beginning? yeah it was one of the most incredible robots in the world and continues to be.
yeah it was really exciting and it was super exciting when it generalized became more than a robot on four wheels but uh a real-world AI system that perceives the world yeah and has can have potentially different embodiments.
well i mean the really well thing about the antoine training is that it like it learns to read like it you can read science but we never told it to read so yeah we never told it what we never told it what a car was or what a person was or a vice cyclist. uh it learned what what all those things are what all the objects are on the road um from video just from watching video just like humans i mean humans are photons and control controls out like the vast majority of information reaching our brain is from our eyes um and say well what's the output the output is our motor signals to our you know from sort of 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 it's you've agreed with ilyas discover recently where he talked about all the lm.
forming a world model and basically language is a projection of that wall model onto the sequence of yeah letters and and you're saying it finds order in in these things um it finds a correlative clusters and so doing it's like understanding something deep about the world yeah which is like i as beautiful that's how our brain works yeah but it's it's beautiful and controls out you know and that's 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 l lm's so in the space of self-supervised learning in the space of text yeah um it seems like there's a deep similarity between that and what tusco autopilot is doing is it to you basically the same but they are converging now converging i wonder who gets there faster understand having a deep understanding of the world or they just will naturally converge they're both headed towards a gi um the tusco approach is much more computer efficient it had to be because we were constrained on this this you know we only have a hundred watts um and it's eight computer 144 trillion operations per second which sounds like a lot but it's kind of small potatoes these days that indeed but it's understanding the world at end date so i turn 46 values but there the path to a gi might have much more significant impact because it's understanding it will faster understand the real world than will lm's and therefore for be able to integrate with with the real with humans in the real world faster they're both um going to understand the world but i think tusco's approach is fundamentally more computer efficient it had to be there was no choice back out brain is very computer efficient very very energy efficient so think of like what what is our brain able to do um you know there's only about 10 watts of higher brain function not counting stuff that's just used to control our body um the thinking part of our brain is less than 10 watts um and that 10 those 10 watts can still produce a much better novel than a 10 megawatt GPU cluster so there's a six-order magnitude difference there um i mean the the AI's 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 where it will end up um you know in general with any given technology first try to make it work and then you make it efficient so i think we'll find over time that these models get smaller are able to do produce a sensible output with far less compute far less power um tesla is arguably ahead of the game on that front because um it has we've just been forced to try to understand the world with 100 watts of compute um and there are a bunch of sort of fundamental functions that we kind of forgot to include so we had to run them a bunch of things in emulation um we fixed fixed bunch those with hardware 4 and then hardware 5 will be even better but it does appear at this point uh that the call be able to drive better than a human even with hardware 3 and 100 watts of power and really if we really optimize it it could be progress in 50 watts
What have you learned about developing Optimus? About applying, integrating this kind of real-world AI into the space of robotic manipulation? Just human 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. Um, that there were no off-the-shelf motors, electronics, sensors. Like we had to develop everything. Um, we couldn't, we couldn't actually find a source of electric motors for any amount of money. Um, it's not even just efficient, inexpensive. It's like anything. There's not a no. The actuators, everything, everything has to be... yeah, 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. Um, none of them were suitable for a human-right robot. Literally none. So we had to develop our own design, the design specifically for what a human-right robot needs.
A harder was it to design something that can be mass manufactured, could be relatively inexpensive. I mean, if you compare the Boss to Dynamics Atlas, it's a very expensive robot. It is designed to be manufactured in the same way they would make a car. And I think ultimately, we can make Optimus for less than the cost of a car. It should be because if you look at the mass of the robot, it's much smaller. And the car has many actuators in it. The car is more actuators than the robot, but there is, um, the actuators are kind of interesting on a humanoid robot with the fingers. So Optimus has really nice hands and fingers, you know? 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 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 the also the control, the no, the controls are different, but the video and controls, um, the car is a robot on four wheels. The Optimus is a robot with the hands and legs. So you can just, they're very similar. So the entire machinery of the learning process, yeah. And to end, it's just you just have a different set of controls. After this, we'll 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."
Yes, sure. What's something difficult you're going through that people don't often see?
是的,当然。有什么困难你正在经历,而人们往往不会注意到呢?
Trying to feed people with no... I mean, you know. Uh, I mean, my mind is a storm. And I don't think most people would want to be me. They may think they don't want to be me, but they don't. They don't know, they don't understand.
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 resentment. Um, so I think, to forgive, you know, forgiveness is difficult for people. It seems like you don't harbor the resentment. I mean, I try to think about, like, what is going to affect the future in a good way. And holding onto grudges does not affect the future in a good way.
Your father, a proud father. What have you learned about life from your kids, those little biological organisms?
你的父亲,一个骄傲的父亲。你从你的孩子那些小小的生物身上学到了什么关于生活的经验?
I mean, developing AI and watching, say, little X grow is fascinating. Because they're a form of parallels that I wouldn't have expected. I mean, I can see his biological neural net making more and more sense of the world. And I can see the digital neural net making more and more sense of the world at the same time. Do you see the beauty and magic in both?
Yes. I mean, one of the things with kids is that, you know, you kind of see the world anew in their eyes. You know, to them, everything is new and fresh. And then when you see that they may experience the world as new and fresh, you do too.
Well, Ylana, I just want to say thank you for your kindness to me and friendship over the years. For seeing something in a silicate 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, Ylana Musk. Thank you for listening to this conversation with Ylana 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 Ylana approaches difficult problems: "The only rules are the ones dictated by the laws of physics."