Elon Musk: War, AI, Aliens, Politics, Physics, Video Games, and Humanity | Lex Fridman Podcast #400

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.

以下是与埃隆·马斯克（Elon Musk）的对话，这是他第四次出现在The Lex Friedman播客中。我还以为你会完成它。这是所有电影史上最伟大的主题之一。是啊，它太棒了。

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.

所以，我刚刚在想罗马帝国，正如人们所做的。这是否意味着每个人每天至少会考虑一次关于罗马帝国的事情？一半的人对此是否感到困惑不解？但更严肃地说，我正在思考当今世界上正在进行的战争。正如你所知道的，战争和军事征服一直是罗马社会和文化的重要组成部分。我认为这在人类历史上的大多数帝国和王朝中都扮演了重要角色。

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.

是的，它们通常是由征服的结果产生的。我指的是，像乌尔查德和格灵帝国这样的地方，有很多聪明的婚姻。但从根本上说，征服是一个推动力。是的，它一直都是。他们崇尚卓越。而且战争中，很多领导者都是出色的将军。是的，就是那种情况。

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.

所以，一个大的问题，grok 批准了。我觉得这是一个很好的问题。它是否经过了 grok 的批准测试？至少在有趣的模式下。你认为战争在多大程度上是人类本性的一部分，而不是人类社会结构的结果？我问这个问题是因为你在某种程度上有争议地支持和平。

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.

我通常是和平主义者。我的意思是，如果从我的观点来看，无知可能是真正的敌人。这才是真正困难的地方，而不是与其他人战斗。但是所有生物都会争斗。我的意思是，在丛林里，你看起来会认为自然是一种和平的东西。但事实上并非如此，有一些有趣的地方，就像是丛林中的一种生物，他说丛林基本上是无处不杀戮和死亡。而丛林中的植物和动物每天、每分每秒都在不断地互相残杀。所以并不像我们在这方面那么不寻常。

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...

在这里有一个相关的问题，即智力是否愈发聪明，我们对这些本能暴力行为的控制也愈发强大。是的，我们要比其他动物更能够控制我们大脑边缘系统中的暴力本能，也就是说，相比之下，猿类社会并不友好，充满暴力，实际上相当可怕。这就是我们边缘系统在发挥作用，可以想象我和一只野猿打一个翻脸，并撕下它的坚果。基本上，没有限制、道德或者对错，只有正义战争。而猿类社会的变化则是通过任何必要手段来实现统治。然而，人类社会则是一种相对永久的人类社会版本。

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

这不太像和平爱好者，基本上...一点也不...存在着极端的平衡...偶尔有些人觉得他们可以把黑猩猩养作宠物...然后就被它们抓住了脸，或者他们喜欢不同的东西，这样的事情确实发生了几次...把你的家伙撕掉，这是一种有趣的互动策略，有些人就是这么倒霉...我猜这是确保另一只黑猩猩不会在基因池中做出贡献的一种方法，从武术的角度来看，这是一种令人着迷的策略，不过，那个...不是真的哈哈哈，我想知道哪种武术教这一点，我想可以肯定的是，如果有人把你的家伙握在手里，还给你一个选择，你会很愿意接受他们的要求，哈哈哈。

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.

所以，就像我之前有点引起争议地说的，你一直是支持和平的倡导者，而且在Twitter上也发表了一些相关的观点。现在我想问你关于目前以色列和加沙的战争，你希望这场战争如何结束，你认为有什么路径可以最小化人类的痛苦？

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

从长远来看，在那个地区，我认为那个地区绝对是如此。如果你查字典上的答案，并不容易，它将是那个地区的图像，比方说......以色列尤其如此，没有简单的答案。或者说，严格来说，那是我个人的意见。摩斯（Hamas）的目标是激起以色列的过度反应。他们不期望军事胜利，而是真正希望犯下尽可能多的暴行，以激发以色列做出最激进的回应，并利用这种激进的回应来在世界各地召集穆斯林支持加沙和哈马斯。他们已经成功地做到了这一点。因此，这里有一个违反直觉的事情，我认为应该做的事情，尽管非常困难，那就是我建议以色列尽可能展示最明显的善举，每一个方面，每一个行动都应该是摩斯的目标所阻止的实际行动。

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

所以从某种意义上讲，合乎地缘政治逻辑的做法是对自己转过脸去执行这个原则，但并不完全是转过脸去执行，因为我认为以色列找到Maus成员并逮捕他们或者杀掉他们是合适的，不然他们会继续来袭。但除此之外，他们还需要尽一切可能，比如建立一个流动医院，我建议这样做。确保有食物、水、医疗用品等，而且要过分强调并且非常透明，这样他们就不能说这是一个伎俩，只需在设备上安装摄像头，让人们随时能看到善行，大张旗鼓地进行，这些善行要明确无误，不能给他们以任何诡计的理由，否则他们的回应总是认为这是一个伎俩，因此你必须反击，证明这并非伎俩，最终这会与整个地区的仇恨势力进行斗争。是的。

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

我不确定是谁说的，这是一种说法，但是“以眼还眼”会让每个人都变瞎。在那个地方，他们真的相信“以眼还眼”的观点。但是，如果你不打算像对待整个民族那样彻底屠杀，这显然是不可接受的，不应该被任何人接受，那就意味着你会让很多人活着，而这些人随后会对以色列产生仇恨。所以，真正的问题是，为了每一个你杀害的哈玛斯成员，你创造了多少个？如果你创造的比你杀死的还要多，那么你并没有成功，这就是真实的情况。可以肯定的是，如果你在加沙杀死了某人的孩子，你至少创造了几个哈玛斯成员，他们会为了杀死以色列人而牺牲自己。但是，我想这是一个最有争议性的话题之一，但是，我认为如果最终的目标是实现长期和平，我们必须从长远的角度来看待这个问题，是否会创造更多或更少的恐怖分子。让我再谈谈战争，如果可以说战争一直存在，并将永远存在，我希望不会，你认为它永远会存在吗？将一直存在这个问题，总是存在一个问题，即究竟会有多少意愿和这次战争的规模，尽管规模、范围和频率正在增加，但是在我的想象中，未来不会有更多的战争，这种可能性很小。你谈到了文化系列，即使在那里也有战争，是的，巨大的战争。第一本书以一个巨大的银河战争开始，数万亿人死亡，但仍然保留了一些茁壮成长的领域。是的，我想如果我们有一天能够扩展到整个星系或其他地方，总会有一场银河战争。战争的规模一直在增加，好像是一场苦难和蓬勃发展规模之间的竞赛。很多人似乎利用这场灾难来鼓吹战争，满足军事工业复合体的需求，你对此是否担忧？担忧的是，如今很少有人真正从内心理解战争的恐怖，至少在美国，我是说，很明显，在乌克兰和俄罗斯前线上，那些深刻理解战争可怕程度的人是多数，但是在西方有多少人理解呢？我的祖父参加过第二次世界大战，他受到了严重的创伤，他在那里服役将近六年，所有的朋友都在他面前牺牲了。

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

第一段：除了随机进行了一些测试之外，他死后也得到了一些，我猜是一种可爱的测试或者其他什么，他的分数非常高。现在他不是官员，只是一个下士或者类似的军士长，因为他没有完成高中学业。他不得不辍学，因为他父亲去世了，他不得不工作来养活他的兄弟姐妹。因为他没有高中毕业，他不能成为军官。所以你知道，如果你被归类为炮灰的话，基本上你就完了。但是后来他被随机选中参加了这个测试，他被转到了伦敦的英国情报部门，在那里他遇到了我的祖母。但是他患有极度的PTSD，我是说完全极度的，几乎不说话，如果你尝试和他交谈，他只会告诉你停止说话，他赢得了很多奖章，从未吹嘘过，甚至没有暗指过什么。我是从上网查看他的军事档案得知这些的。他总是说，不，他绝对不想再经历那个，但是还有多少人现在还记得二战呢？不多，也许对核战争的威胁也一样。是的，我指的是有足够多的核弹瞄准着美国，以至于使瓦砾成为辐射瓦砾的可能远远超过多次，现在有两场主要战争正在进行中，所以你之前也谈到了AGI的威胁，但是现在我们与日俱增的冲突，你担心核战争吗？我认为我们不应忽视核战争的可能性，它是一种对文明的威胁。现在我可能错了，但我认为当前核战争的可能性相当低，但是有很多核武器对准了我们，而我们也对其他国家有很多核武器，而且没有人把他们的枪放下，部队还在沉默中，而且领导人似乎不是拥有核武器的人在相互对话。有些战争是悲剧性的，对当地而言也很艰难，然后有些战争是以文明灭亡或可能文明灭亡为终点的，显然，全球核战争有很大的潜力来结束文明，或者至少严重地削弱并追溯人类进步到石器时代或其他什么。我不知道，非常糟糕，很可能在那之后科学家和工程师也不会受到太多欢迎，你可以想象这种混乱。所以总的来说，我认为我们也应该优先考虑对文明的威胁，而不是一些在当地层面上是痛苦和悲剧的事情。

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

第一段：你希望乌克兰战争如何结束，以及最小化人员伤亡的途径是什么？我认为可能会发生的情况，也基本上是目前的局势，就是接近目前防线的地方可能会出现停火或休战，但目前的情况是无论哪一方发起攻势，伤亡人数都会远远高于防守方，因为你会面临防御和死亡，有地雷、战壕和反坦克防御措施，双方谁也没有空中优势，因为防空导弹比飞机好得多且数量更多，所以从战术上来说，坦克基本上是“死亡陷阱”，移动缓慢且无法免疫反坦克武器的攻击，所以你只能依靠远程火炮和步兵。这就好像是重返一战时期，有些无人机参战，有些无人机很老旧，但这使得远程火炮的精确度和效率更高，使双方的人员伤亡更加严重，所以无论哪一方试图推进阵线，都会有极高的死亡概率。因此，为了克服防御、死亡、战壕和地雷，你确实需要在人数上有显著的地面优势，最好是采用合成作战，即快速突袭+集中数量的坦克+大量士兵。这是你唯一能够突破阵线的方式，然后不让对方有机会重新增援，否则你很快就会被赶出去。我真心建议人们详细阅读一战的战争情况，这非常艰难。我是说非常多人死亡，让人难以想象的是，很难想象出现的结果与开始时几乎完全相同，包括土地归属等方面。但是，付出的代价是人类的苦难、死亡和基础设施的破坏。我之所以一年前就提出某种形式的停火或和平，是因为我几乎准确地预测出了即将发生的事情，即很多人为了基本上没有改变土地局势而死亡，还有乌克兰和俄罗斯年轻人中的精英损失。我们应该对俄罗斯的年轻人持同样的同情态度，因为他们的孩子也不是自愿上前线的，而是不得不去的。很多儿子都不能回到父母身边，我认为他们中的大多数人并不真的憎恨对方，这就像一战一样，不认识对方的年轻人在老人的指挥下相互残杀，这究竟有什么意义呢？所以莫斯科将军（乌克兰总统弗拉基米尔·泽连斯基）曾经表示他不愿直接与普京对话，你认为他应该坐下来，以领导人之间的方式进行谈判和平吗？我认为我只能建议不要将乌克兰年轻人中的精英送入战壕死去，无论他是否与普京会面，都不要这样做。不管谁发起攻势，都会造成大量人员伤亡，历史不会对他们仁慈。

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

第一段：如果在台湾问题和一个中国政策等问题上找不到外交解决办法的话，你匿名的谈到了美中长期可能发生战争的可能性，对吧。我们怎样才能避免这两个超级大国发生冲突的轨迹呢？读一下那本难以发音的"酸性陷阱"吧，我相信它叫这个名字。我热爱战争历史，喜欢疯狂的艺术和颠倒的事情。我几乎读遍了所有的战役，试图弄清在任何特定情况下真正导致胜利的原因，与任何一方声称的胜利和战争起因有所不同。雅典和斯巴达是一个经典案例。关于希腊人的事情是，他们真的写了很多，他们喜欢写作。世界上的许多地方发生了很多有趣的事情，但只有希腊人才写下来，所以我们不知道发生了什么，或者他们并没有详细写下来，他们只是说像我们去了，进行了一场战斗，而我们赢了，我们能多写一点吗？希腊人真的写了很多，对此他们非常口若悬河。而我们保留了很多这样的文字，所以我们知道了导致斯巴达与雅典联盟之间的伯罗奔尼撒战争的原因，我们知道他们很早就预见到了它的发生。也就是说，虽然他们的文字没有很长，但它们并不复杂。但是，雅典人和其他希腊人写得很详细。雅典变得越来越强大，每年都在增强，每个人都说，那是不可避免的，雅典和斯巴达之间必将发生冲突。嗯，我们怎样才能避免呢？然而，他们无法避免，他们甚至已经看到了这一点。所以你知道，要是在某个时刻，如果有一个群体、文明或国家等超过了另一个，那就像是，你知道，自从我记事起，从经济角度来看，美国一直是世界上最大的经济实力。美国已经成为世界上最强大的经济引擎比任何人的寿命都要长了，而战争的基础是经济。所以现在我们有了中国这样的情况，中国的经济很可能比美国大两倍甚至三倍。想象一下，你在整个街区中一直是最大的孩子，没有人记得有一个时刻你不是最大的，突然有一个孩子出现他的体型是你的两倍大，所以我们看到了这一点。是什么可能阻止它的发生呢？让我提出一个观点，国际文化交融，相互理解，这只是在彼此之间存在着巨大的文化差异，你是一个有趣的案例，因为你显然是美国人，在美国做了很多令人难以置信的生产，但你也和中国合作，我在中国花了很多时间，并会见了领导人很多次。

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

也许一个很好的问题是，关于中国有哪些人们对文化中的一些正面事物还不太理解的地方？你对中国人的一些有趣的发现是什么？

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

中国有大量非常聪明勤奋的人，实在是令人难以置信。据说在中国的聪明勤奋的人比我们这里多得多，我认为他们有很多能量。中国近年来的建筑相比美国更令人印象深刻，火车站、建筑物、高铁等等，都比我们在美国拥有的要好得多。我建议有人去上海和北京看看建筑物，还可以乘火车从北京去西安参观兵马俑地区，那里有着令人难以置信的历史，非常悠久。从书面语言的角度来看，中国也许是最古老的文字之一，中国人确实写下了很多东西。历史上，中国一直以来都以内向为主，除了个别例外，他们并不是寻求扩张的。他们曾发生过许多内战，例如三国时期的战争，据说中国失去了约70%的人口。这些内战非常残酷，使得美国看起来相对较小，就像一个个人一样。

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

第三段：嗯，所以我认为重要的是要意识到中国并不是一个单一的整体。我们有时候会认为中国是一个统一思维的实体，但事实并非如此。根据我所见和大多数了解中国的人的看法，在中国，人们对中国的思考比对任何其他事情的思考多出十倍，这就相当于他们考虑的90%是关于中国自身的。

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

第四段：当谈到超级大国之间的合作和未来时，这难道不是一个非常积极的事情吗？当你内向时，意味着专注于改善自己而不是通过军事力量改善别国，好消息是中国历史表明中国并不贪得无厌，意味着他们不会去侵略其他国家。他们对此非常有信心，这是一件好事，因为很多强大的国家都具有贪得无厌的特征。美国也是罕见的没有贪得无厌的例子之一，二战后美国本可以主宰世界，而且聚拢多么不平衡，我们有核武器，而其他国家没有，你只需选一个国家，美国就可以占领所有。但是，美国并没有这样做，事实上，美国帮助重建了欧洲和日本，这是非常不寻常的行为，几乎是前所未有的。美国进行了一些显著的善行，比如布鲁林空运，当然美国也做过坏事，但人们需要看整个历史记录。

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

总的来说，你知道当一个测试是如何对待你的监狱，就像是战争一样。不冒犯俄罗斯人，但假设你在1945年的德国，一边是俄罗斯军队，另一边是法国和美国的军队，你希望成为哪一方准备好的人？没有一个国家是完美的，但我强烈推荐和美国一起成为战俘，那是我的选择。事实上，布朗是个小个子，他说我们必须被美国人俘虏。纳粹党卫军接到命令处决更多的布朗和所有德国犹太人，他们侥幸逃脱了党卫军的追捕。他们称他们要去树林散步，却并没有带上冬天急需的外套，他们没吃的没喝的，只是拼命地逃跑，向西方跑去。机缘巧合，我想是他的兄弟找到了一辆自行车，然后迅速向西方骑去，偶然遇到了一支美军巡逻队。总之，你可以从战俘选择中看出人们的品德，你想在哪里成为战俘，这并不是说哪里都好，但有些地方比其他地方更糟糕。

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

无论如何，美国一直远离完美，总体上是一股善良的力量，我们应始终保持自我批评并努力变得更好。但是，任何稍有理智的人都知道，中国和美国在某种程度上是相似的，两国都没有在重大程度上表现得贪婪，这是一个共同的原则。但中国对台湾非常重视，他们长期以来一直对此持明确立场。从这个角度来看，这就像一个州不存在，有点类似夏威夷但更为重要。对我们而言，夏威夷已经相当重要了。他们认为台湾是中国的一部分，台湾不是中国的一部分只是因为有美国太平洋舰队的存在。随着中国的经济实力和军事实力的增长，他们明确表示他们的利益将会实现。中国已经明确表示他们将通过和平或军事手段将台湾纳入中国管辖，从我的观点来看，这种纳入非常有可能。

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

关于“显眼的善举作为一种地缘政策”的说法，它似乎有些幼稚，但我敢说这可能是未来的道路，它可以避免大多数战争，就像你说的那样，它听起来很天真，但却非常聪明，如果你相信人类本性中的善良。这样显眼的善举似乎可以在涉及的国家民众中产生回响，是的，而且可以缓和紧张局势。在第一次世界大战之后，他们犯了一个大错误，他们试图把所有的责任都推到德国身上，并对德国施加了不可能承受的赔款，实际上，对于第一次世界大战而言责任是有很多要分摊的，而他们试图把责任完全归咎于德国，这为第二次世界大战埋下了伏笔，许多人不止是希特勒，很多人都感到委屈，他们想要报复，并且他们得到了。人们不会忘记，你要是杀了别人的父母子女，他们是不会忘记的，他们会想要报复。

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

所以二战后，他们就像是，好吧，我们对待我们的那种方式是一个巨大的错误，规则一，这一次，我们不再压倒失败者，而是通过马歇尔计划帮助他们，我们将帮助解决德国问题，解决奥地利问题以及其他国家的问题。现在是正确的举措，似乎对于醒目的善举有一种深刻的真理，作为对互相暴力的解药，一些东西必须制止这种循环，否则它永远不会停止，只有以牙还牙，眼还眼，以肢体换肢体，以命还命，永远永远。

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

为了暂时逃离黑暗，一些令人难以置信的工程成果将推出。我刚刚发布了Grok AI助手，我有机会玩一下，它令人惊叹的地方在很多方面。首先，令人惊叹的是，一个相对较小的团队在相对较短的时间内能够开发出接近最先进的系统。另一个令人难以置信的事情是，它既有常规模式又有趣味模式。是的，我得玩一下那个模式了，我希望生活中的一切都有一个有趣的模式，我是说，除了有趣之外，还有一种令人着迷的东西，与这个有趣模式互动的大型语言模型，我不确定确切是什么，因为我只花了一点时间来试玩，但它确实使与系统互动变得更有趣、更有活力。是的，绝对是这样。

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

第三段: 我-我-我们的-AI-Grok是以《银河系漫游指南》为模板的，这是我最喜欢的书之一。它是一本冒充幽默的哲学书。我会说这本书构成了我的飞行哲学基础。我的飞行哲学是这样的，我们并不知道生命的意义，但是只要我们能够扩展数字和生物意识的范围和规模，我们就能够更好地理解该宇宙的答案应该问什么样的问题。所以，我怀有一种好奇心的哲学。

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

通常有这样的感觉，就像这个人工智能系统对外有一种与朋友一起坐着仰望星空的感觉，就像问草莓头问题究竟宇宙是什么，对它的好奇心。不管我问什么现代问题，整个过程总是带着一种宇宙的壮丽感。

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

我们实际上正在努力开发一种可靠的工程数学和物理答案，所以对于其他类型的人工智能来说，这些所谓的大型语言模型, 我们发现工程不可靠，而且当你最不希望产生幻觉的时候它会产生最多的幻觉。当你提出重要的、困难的问题时，它往往会自信地给出错误的答案。所以我们真的在努力思考，如何尽可能地 grounded（扎根于现实），这样你就可以依赖结果了。我们将结果追溯到物理的第一原理和数学逻辑。所以，在幽默的表达之下，是对宇宙真理的尽可能忠实的追求，这是非常棘手的。这就是为什么你知道总会有一定的误差，但我们是否希望在回答中尽可能真实，即使有承认的误差。所以你不会每次都正确，但你不希望误差自信地发生的次数太多。当逻辑的基础是不违反物理规律时，你就可以开始建立新的发明、创造新的技术。但如果你不能相信基础的物理规律是正确的，那么这些发明只是一厢情愿的想象和魔幻。

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

正如你所说的，我认为AI的一个重要目标就是理解宇宙。是的，这是一个简单的三个词的使命。如果我们展望未来，你认为在物理学的这个层面，也就是我们对物理学的理解的边缘，它是否会有重大发现？最性感的发现可能是，就像我们现在知道的那样，统一广义相对论和量子力学，提出一整套理论。你认为它会朝着这个方向努力吗？几乎像理论物理学的发现一样，如果AI无法发现新的物理规律，很显然它并不比人类强大，甚至是过去的人类。因为人类已经发现了新的物理规律，物理只是在深入理解现有的东西，以及如何掌握现实的运行方式，然后再进行工程设计，生产从未存在过的东西。 事实上，工程学的可能性范围远比物理学要大得多，因为我们已经掌握了宇宙的规则。一旦你明白游戏规则，我们现在至少在局部范围内对物理学的理解非常好，我们就可以非常好地预测事物的发展，就像量子力学能够预测结果的程度是令人难以置信的。顺便说一下，这是我上大学最难的课，我的量子力学课比我其他所有课程加起来都难。让一种大型语言模型的AI系统可靠到与量子力学和物理学一样可靠是非常困难的。是的，你必须对任何结论进行实际测试，与现实的真相进行对比，现实是最终的裁判。物理学是法律，其他一切只是建议。我见过很多人违反人造的法律，但没有人违反甚至可以违反物理法则。这其实是一个很好的测试，如果这个语言模型理解并符合物理学，那么你就可以更可靠地信任它对当前政治状态的想法。而且，目前甚至它的内在逻辑也不一致。特别是这种仅仅预测分词的方法，就像求和一样，将一堆向量相加，但是会出现漂移的情况。因为一点点的误差会累积，当你走到了很远时，就变得毫无意义了。所以它必须对这种漂移有一定的自我感知，然后将所有事情作为一个整体看待，并说它具有整体的连贯性。当两者都是对的时候，他们会写出这本书，然后去修改它，考虑到一切的结束、开始和中间，用以实现连贯性，以免进入无意义的地方。也许修改的过程就是推理的过程，通过不断修改来逐渐接近真理。至少我是这样来做的，一开始就胡扯一堆，然后逐渐改进，直至达到连贯性，直至所有事情都加起来符合逻辑。

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: 在探索智能之前，关于万物理论还有一个问题，您认为是否存在一个智能理论？在与我一起开发这个智能系统时，您是否认为有一种智能理论，用以理解AGI中的“i”是什么，以及人类智能中的“i”是什么？在美国队长中没有“i”，或者等等，对了，现在我脑子里会一直想到这个，呃，是的，在量子力学中没有什么“我”，我是说这是发现理解宇宙的过程的一部分吗，就是了解智能吗？是的，我认为我们需要理解智能，理解意识，我的意思是，有一些基本问题，比如思想是什么，情感是什么，是不是真的只是一个原子撞到另一个原子上？感觉上似乎不仅仅是这样，我认为我们可能还缺少一些非常重要的东西，例如一些事后看来显而易见的重要事物，就像存在一个巨大的意识情感整体，部分可能类似灵魂，你知道一种宗教精神之类的东西，你觉得你是你自己，我的意思是，你不觉得自己只是原子的集合，但是思想存在于哪个维度？情感存在于哪个维度？我们非常强烈地感受到它们。我怀疑其中有更多的东西，超过了原子撞击原子的范畴，也许人工智能可以为发现这个东西的过程铺平道路，是的，意识是什么？当你将原子排列成特定形状时，为什么它们能够形成思想、采取行动和情感，即使这只是一种幻觉，为什么这种幻觉如此吸引人？是的，为什么这种幻觉存在？在哪个层面上存在这种幻觉？有时候我会想，也许一切都是有意识的，或者一切都没有意识，两者之一，我更喜欢前者，一切都有意识，似乎更有趣，是的，但是我们由原子组成，而这些原子由夸克和轻子组成，而这些夸克和轻子从宇宙诞生之始便存在。

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

在我们第一次交谈时，你说了一句非常真实的话，让我觉得这个讨论正在变成现实，那就是宇宙的开始。我问你，一旦你创建出一个超级智能系统，你会问它什么问题，你说你会问关于模拟外部世界的问题。这个问题似乎是你开始创造Grogg的目标之一，能够提出和回答这样的问题。关于外星人的问题，比如费米悖论，很多人问我是否看到过外星人的证据，但我没有看到。这有点令人担忧，因为我认为至少看到一些外星人的考古证据可能更好。据我所知，目前并没有这样的证据。它们非常微妙，我们可能是整个银河系中唯一具有意识的存在。看看地球的历史，根据考古记录，地球大约有45亿年的历史，而从第一次写作开始算起的文明只有大约5000年。我们必须要理解古代苏美尔人，尽管他们已经不在了，不过我认为最早的象形文字是在5000年前出现的。我觉得这是文明开始的比较好的时间点，这占据了地球历史的一百万分之一。所以文明只存在了很短的时间，到目前为止，为什么会这样呢？在绝大部分的时间里，地球上几乎没有生命存在，然后在很长一段时间里只有古老的细菌，然后是多细胞生物的出现，从海洋到陆地的生命进化，再到哺乳动物和更高级的脑功能。太阳正在缓慢膨胀，最终会加热到地球将不再适宜生命存在的程度，就像金星一样。如果我们不成为多星球居民，并最终成为科维诺斯（太阳系）的一部分，地球上的所有生命将不可避免地被毁灭。这是一个确定性的结局，可能只需要在银河系的时间尺度上半亿年左右，根据人类的标准来看，这是很长的时间，但只比地球存在的时间长10%。如果地球上的生命进化要花费更长的时间，那么生命可能根本就不存在。

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

有一个截止日期即将到来，但赶时间说，正如你所说，人类和地球上的智能生命快速发展了很多酷东西，所以成为一个多星球文明似乎几乎是不可避免的，除非我们自我毁灭，我们需要做到这一点，我的意思是，我是说，我怀疑如果我们能够探索其他星际系统，那里很有可能会发现一大堆已经灭亡的单一星球文明，他们从未走出自己的家园星球，那太可悲了。没错，这也很有趣，我的意思是有一些解释这种悖论的理论，其中之一是有这些巨大的祸鸟可以使文明无法挺过去，其中一个就是成为一个多星球文明或不成为的问题，如果你不成为，你的星球上迟早会发生某些事情，无论是自然的还是人为的，导致我们灭亡，就像恐龙一样，他们现在在哪里？他们没有宇宙飞船，所以我认为更可能的事情是，我们只是被外星人找到了，他们在保护我们，让我们存在，希望如此，就像亚马逊雨林中的部落一样，所有探测到的部落都受到了保护，那将是一个好的解释，或者就像卡帕赛说的那样：“亚马逊雨林中的蚂蚁问‘大家去哪了？’，然后它们会遇到很多其他蚂蚁，没错，他们之间确实发生这些大规模战争，听起来像个好电视节目，是的，他们确实有大规模战争，各种不同种类的蚂蚁，也许我只是低估了蚂蚁的多样性，你应该听听我们在主持谈论丛林的时候都在说些什么，真的很搞笑，你听过吗？不，我没有听过，博尔诺迪托乌茨在YouTube上有一个音频，很棒，我非常喜欢，对，太好了，我们会看到《快乐人生》和《迪亚加》的导演是如何做那部关于熊的纪录片的，你知道关于企鹅的那个，肯定会有心理分析的，关于企鹅自己选择前往距离70英里的山脉，就是被注定要死的，他是有点愤世嫉俗，我对此持有不同看法，他可能只是一个勇敢的探险家，未来几个世纪里，在企鹅群体中会有很多关于他的伟大故事，我们在谈论谁呢？ 好吧，是的，外星人，我是说，我不知道，我认为聪明的做法就是，你知道，这是地球历史上第一次有可能让生命延伸到地球以外的地方，这个窗口是开放的，可能持续很长时间，也可能只是短暂开放，而且现在它可能打开了，但之后可能再也不会打开，所以我认为聪明的做法是在可能的时候使生命成为多星球的，我们不想成为那种无趣的单一星球文明，然后就灭亡了，那些无趣，没有自尊的文明，没有人会对它们写维基百科的词条，噢，SpaceX有没有与遇到外星人时的官方政策？没有，那听起来有些不负责任，我会立即在X平台上发布任何微弱的异样迹象，我知道可能成为有史以来最受欢迎的转发帖子，是的，我的意思是，我们现在在那里有比别人加起来更多的卫星，所以你知道，如果我们要绕过什么东西，我们会知道，如果需要在任何事物上作出调整也没有问题，如果你去关注大问题，

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

你又说你和爱因斯坦一样，相信斯宾诺莎的上帝，是的。所以你知道，这是一种上帝就像宇宙，通过物理规律来展现自己的观点，正如爱因斯坦所说的，通过世界的和谐法则展现自己。是的，我同意，就像那个模拟器的神或者至高无上的存在，通过物理规律展示自己，他们是这个存在的创造者，他们希望我们更多地去理解这个存在，就像是谁创造了这个东西，谁在运行着这个东西，将它化为一个简单的问题并融入其中的一个性感的词语，这可以集中我们的思维去理解它。看起来确实有一种目的或者潜在的总体计划，看起来可能在某种意义上并没有一个总体计划，所以这个问题的答案可能很有趣，就是决定论和自由意志之间的问题，如果我们处于一个模拟中，那么这些更高级的存在举办一个模拟的原因在于看看会发生什么。否则他们不会举办这个模拟。所以当人类创造一个模拟时，就像SpaceX和特斯拉，我们经常会进行模拟，特别是对于火箭来说，你知道你必须运行很多模拟来了解会发生什么，因为你无法真正测试火箭直到它进入太空，你希望它能够工作，所以你必须模拟亚音速、超音速升空和返回时的超高温等等，所有这些都需要进行模拟，因为你没有太多的机会。但是我们运行模拟是为了看看会发生什么，如果我们知道会发生什么，我们就不会运行模拟。所以如果这个存在是我们创造的，那么运行它的原因是因为他们不知道会发生什么，而不是因为他们知道。所以也许我们都玩过《暗黑破坏神》,也许《暗黑破坏神》是为了看看你的角色是否能够击败最终boss，那个uber lillith。他们不知道结果，有趣的是这个uber lillith，你的称号是仇恨之躯。是的，现在你可以问《暗黑破坏神》团队了，但几乎不可能击败仇恨在永恒领域。你曾经直播自己在恶梦100级地下城中占统治地位，但我却可以毫不费力地穿过恶梦100级地下城，就像在公园漫步一样，但你却被仇恨击败了。

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

这似乎是第二难的Boss，名叫“Dural Dural Canner”。我杀死了Dural Dural很多次，还有游戏中的其他所有Boss。这对我来说很容易，但如果你是一个德鲁伊并且没有无敌技能，对付超级莉莉丝（也被称为憎恨的化身）就会很困难，因为她会释放随机的死亡攻击。我现在已经52岁了，反应不如从前，但我一生都在玩视频游戏，曾经是世界上最好的“Quake”玩家之一。实际上，我参加了美国第一次有奖金的电子竞技比赛，并获得了第二名的成绩。虽然我的团队本来要拿第一，但最强的成员的电脑在比赛进行到一半时崩溃了。所以我们得了第二名，但我也赚到了钱。所以可以说我有技术，虽然现在已经不再年轻了。现在我一直在努力战胜“莉莉丝”，作为一个德鲁伊，在这个永恒世界中战胜“憎恨的化身”，这个问题真的让我疯狂。我觉得挑战本身也是游戏的乐趣所在。我觉得你真的是个世界级的游戏高手，也是个创新者。你不止是个按照网上建议来的玩家，还是个试验者，一个疯狂的科学家，试图找出最佳的技能配置和建筑。真的很令人着迷。

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

在这方面有一些有趣的见解，关于如果有人作为德鲁伊开始，你有什么建议。我不建议在永恒领域里玩德鲁伊，但现在我认为这个赛季境界中最强大的角色是带电球的巫师，所以在这赛季里，巫师有着巨大的电球。是的，就是这样，他们有着巨大的电球。希望他们对此有个专有名词，并且在这个赛季领域里，使用这些吸血鬼力量会增加你的伤害和防御等等。

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

所以呃，但我们很容易在某个季节性地击败仇恨，但要永远地击败仇恨非常困难，几乎不可能。这似乎是对生活的一个隐喻，你知道，我喜欢你关于马斯克的想法，因为我在玛莎玩耍时看到了一个100级的德鲁伊从我身边跑过，他说永不死亡，然后我又跑回去，结果就有了这个隐喻，有点好笑，你知道，一个马斯克在这个魔界中不知疲倦地与仇恨战斗，是很好笑的，不，是荒谬的。

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

实际上，玩游戏是一种荒谬的运动，让我想抓狂。对于你个人来说，你从视频游戏中得到了什么？我觉得它可以使我的思绪平静下来，你在游戏中消灭恶魔，也就抚慰了我内心的恶魔。如果你玩一个困难的游戏，你可以进入一种非常享受的心流状态。然而，游戏的难度不能太简单也不能太难，应该适中恰到好处。

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

嗯，我猜你通常希望在游戏中感觉到自己在进步，所以一个好的视频也是一种美丽的艺术，让人着迷的故事情节，而且它像是一个令人惊叹的难题需要解决。我认为《上古之环》这款游戏就是一个需要解开的难题，是有史以来最伟大的游戏之一。虽然我还没有玩过，但对你来说，《上古之环》绝对是有希望成为有史以来最佳游戏的候选之一，尽管无疑这是一款难度很高的游戏，我听说它有多难我感到有些害怕。

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

但是它的美丽之处就像是由外星人设计的，这次讨论有一个主题，它的独特性非常不寻常，无比创意，艺术设计令人惊叹。我认为在分辨率高、动态范围广的电视上玩这款游戏都不需要专门的监视器，这幅艺术真的太美了，非常不寻常。每一次艰难的Boss战都是独特的，就像一个个独特的谜题，而且每一个都不同，解决一场战斗的策略与解决另一场战斗的策略也不同。

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

尽管如此，你说过在《永恒》游戏中与乌贝莉丝进行的这场战斗是你玩过的最艰难的boss战，没错当前来说它确实是这样。我经常进行这个游戏，因为它是我主要的休闲活动。是的，在永恒境界战胜仇恨是人生中最困难的boss战，同时也是在游戏中的一种隐喻。我不确定是否可能战胜它，但我有所进展，所以我会说：“好，我正在取得进展，也许只要稍微调整一下能力树，或者稍微躲避更多的攻击波，我就能做到了。”这个模拟是为了弄清楚是否有可能做到，而你只是模拟中的一个齿轮，是这个模拟的一部分。我认为至少我觉得是可以做到的。这就是人类的精神，相信自己。但我也会考虑一点，对于这种普遍的仇恨情绪，我们要小心，你知道，有时候你希望得到一些听起来不错的东西，但如果你真的得到了，那是一个反乌托邦的情况。比如你希望世界和平，听起来不错，但是它如何实施？以及得到它需要付出什么代价？永恒的和平可能会更糟，因为那可能意味着压制每个人，可能会压制进步，可能会导致一个僵化的社会从不变革的局面。

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.

第一段： 有一种说法是，如果你希望没有战争，你应该慎重你的愿望。因为要实现没有战争所需要的条件可能比一场小规模的战争更糟糕。被认为是人类文明的缺陷可能是实现最优状态所必需的重要组成部分。

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.

嗯，我的意思是，你担心人工智能会催生出一个反乌托邦的国家吗？无论是像《1984》中的监视和恐惧，还是像《美丽新世界》中那样享乐，呃，充满了性，却缺少深层次的人类体验？你知道吗，实际上有一种叫做索马的真实药物。是的，有的。

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.

让我记下来，思考一下这种药物，你可能会想到《美丽新世界》。我要问它什么问题。告诉我们一下叫做索玛的药物。我觉得它会涉及到《美丽新世界》。

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.

好吧，还有一种真实的药物。寻找索玛（soma）药物信息，哦天哪。噢，索玛，说起来就舒服。我现在是开心模式，哦好吧，没问题。所以，这是在谈论真实的药物。哦，它是一种自1950年代以来存在的肌肉松弛剂。它用于治疗肌肉疼痛和不适，通过改变脊髓神经元之间的活动来实现这一目的。

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.

- 现在，索玛不仅仅是一种止痛药。它还有点催眠作用。它可以让你感到有些昏昏欲睡，所以如果你打算操作机械或解决复杂的数学方程，就不宜使用它。而且这种作用会一直持续下去。

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.

总之，索玛是一种可以帮助缓解肌肉疼痛的药物，但并非没有风险。它还是相当不错的。哦，等一下，你说的是真正的药物。这就是真正的药物，没错。当然，一定要负责任地按照医疗专业人士的建议使用它，并记住最后，宇宙可能只是一个巨大的计算机模拟，所以不要对任何事情过于认真。

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.

我喜欢它，我喜欢它，我喜欢它，是的。哦，而且还很好地包括了相关的推特帖子，这真的很酷。是的，这样将所有内容整合在一起。是的，就像界面是这里的真正酷炫之处之一。我觉得做得很棒。嗯，你可以说，不，我是指《美丽新世界》中的索马因为它会认为你指的是索马这种真实的药物。是的，不，我是说《美丽新世界》中的索马。它会像说，哎呀，对不起，我真的很意外竟然先想到了真实的药物。啊，真抱歉。我是在想那种肌肉松弛剂索马。对于《美丽新世界》，它是一个完全不同的存在。

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.

不，这是赫胥黎的反乌托邦小说。不，索玛是该书描绘的社会中起至关重要作用的一种药物。它是一种改变情绪的致幻药物，用于使人口温顺和满足。在小说中，使用索玛引发了一些有关幸福本质和药物在社会中的作用的有趣问题。

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?

噢，完全正确。生活在一个每个人都永远快乐的世界中，即使这种快乐是人为制造的，是不是更好呢？这是一个很好的问题。这就是我的意思。你是否希望世界和平，人人永远快乐？你确定吗？因为那可能是一个实质上贫瘠僵化、永远不会变化、最终注定要失败的社会。这种紧张关系，我是指，这个讨论，真的是一个非常好的总结。它真正抓住了重点。这不仅仅是照本宣科《美丽新世界》。它实际上在深入了解索玛作为一种药物的关键元素。你真的想处于一个每个人都永远快乐，即使这种快乐是人为制造的情况下吗？还是面对生活的挑战，体验人类情感的全部范围，即使意味着经历痛苦和苦难，更好呢？

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.

顺便提一下，对于那些在听的人来说，你可以直接从Grok上阅读，那是一种非常好的、深入思考的哲学分析，能揭示这里的紧张关系。

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

有趣。总结一下，《美丽新世界》中的索马药物虚构且被用来探讨一些有关幸福本质和药物在社会中的作用的深刻哲学问题。它是一种强力的象征，警示人们不要利用药物逃避现实的危险，并且强调直面生活挑战的重要性。有趣的是，我们确实存在一种名为索马的真实药物，它在缓解背部疼痛方面非常有效。这种药物非常迷人，因为我脊椎C5-C6椎间盘被压扁，它能减轻身体上的疼痛，但它会影响心智清晰度，就像书中的药物一样。这真是一次权衡，所谓的乌托邦看起来实际上可能是一个反乌托邦。实际上，我曾经跟朋友说过，如果世界上真的没有仇恨，你真的希望如此吗？我想知道为什么仇恨会演化出来。当然，我并不是说我们应该加剧仇恨，我们应该尽量减少它，但是完全没有仇恨可能有其原因，因为人类的繁荣可能需要一定程度的人类痛苦。要考虑这个问题真的非常复杂，如果没有低谷，我们能否欣赏高峰？所有这些都在格罗格的一句话中得到了总结，“无低谷的高峰，谁知道呢？”这几乎就是重点了。对于人工智能来说，高效地训练模型似乎是一个重要关注点。那么，在效率方面，能达到的极限是什么？有一个术语叫做每瓦有用的生产力，你们学到了什么，是否在推动极限？我认为物理学的工具非常强大，几乎可以应用于生活中的任何领域。对于重要的事情，需要从基本原理出发进行批判性思考，从一个方向或另一个方向思考问题的极限。在极限情况下，即使在可可规模上，即使利用整个太阳的能量，你仍然关心每瓦有用的计算能力，因此从人工智能的角度来看，我们现在存在硅短缺问题，大约一年后会转变为电压变压器短缺问题，具有讽刺意味的是，要运行变压器，你还需要变压器，可能会有人在其中有幽默感。幽默是命运想要的一切。有人提到香料就足够了，但是我们今天面临硅短缺，大约一年后面临电压降低的变压器短缺，然后大约两年后会面临电力短缺。

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

我为一次全球电力公司和公共事业公司的聚会发表了演讲，我说我们需要为电力需求的增长做好准备，因为所有交通工具都将转向电力，除了火箭以外，加热也会采用电力。目前的用电情况非常粗略地说大约是三分之一用于电力，三分之一用于交通，三分之一用于加热。为了实现可持续发展和电气化，我们需要将电力产能增加三倍。我鼓励各个公共事业公司建造更多发电厂，并且很有可能需要购买更多电池。因为目前电网的规模是按照实时负载进行设计的，这有点荒谬，因为这意味着你需要根据一年中最糟糕的一秒或最糟糕的一天来规划电力需求，否则可能会出现全面停电的情况。我们之前在奥斯丁地区遇到了持续数天的停电。因为电网几乎没有能量缓冲，如果你拥有一个水力发电厂，你可以缓冲能量，但其他情况下，一切都是实时的。所以有了电池，你可以在夜间产生能量并在白天使用，实现缓冲。所以我预计未来将会大量使用电池，因为发电厂的峰谷比为2到5，即最低点到最高点，这意味着电池可以平衡供需差异。但需求将会不断增长，对吗？包括计算需求是吗？没错，电子化，即交通的电子化和加热的电子化，至少在近期内会比人工智能更为重要。但即使对于人工智能，你也会看到对电力的需求增长，用于运行人工智能的计算机。这很明显会导致电力短缺的问题。

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

在这种特殊情况下，如何最大化每瓦特的有用生产力对于培训这样的问题来说是多么困难，似乎真正需要解决的主要问题是如何高效利用电力。根据你在这个领域应用物理第一原理推理的学习，这个问题有多难解决，只是解决需要多长时间的问题。在不同的时间点，进展存在某种限制性因素，就人工智能而言，目前我所说的限制因素是硅芯片，大约在一年后我们将会拥有更多无法插入的芯片。最初的限制是电压降压变压器，因为电力从30万伏特降至最终的0.7伏特，所以电压降低的量非常大。因此，工业界对于快速增长并不习惯。

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

好的，让我们来谈谈竞争。你对谷歌、微软和OpenAI发展AJI表示担忧。你将如何确保通过XAI和特斯拉AI的工作，不将其变成对AJI的竞争，而是一个安全AJI的协作开发过程？

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

是的，我是说有些事情像这样，我觉得太荒谬了，以至于我想做个喜剧小品，底部加上“这都是真的，这实际上就是发生的事情”。有一个挑战是，他们担心火箭会击中鲨鱼，而海洋非常大，你多久见到一次鲨鱼呢，很少见，以海洋表面积的百分比来看，鲨鱼基本上是零。然后我们就说，我们如何计算看到鲨鱼的概率呢？他们说，我们不能给你那个信息，因为我们担心捕鲨猎人会进去猎杀鲨鱼，我们说，我们该怎么办呢？我们处于两难境地。然后他们说，还有渔业和野生动物局可以进行这种分析，我们说，那你为什么不把数据交给他们呢？他们说，我们不信任他们，我们说，打扰一下，他们实际上就是你们部门的一部分。这真的是发生的事情，最终他们设法解决了内部的困境，事实上看到鲨鱼的概率基本上是零。

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.

嗯，还有一个组织，直到几个月前我才意识到，他们关心的是在国际水域中是否会撞到鲸鱼。再次看看太平洋的表面，问问其中百分之几的面积有鲸鱼，像你给一张大图，指出图中所有的鲸鱼，我看不到有任何鲸鱼，几乎是零。如果我们的火箭碰到鲸鱼（几率极小），那么这只鲸鱼可以说是倒霉透顶了。这种情况很荒谬，这种官僚主义太离谱了。嗯，我觉得还有一件非常疯狂的事情是，我们从加利福尼亚的范纳布克发射火箭时，他们担心声音爆炸会影响海豹繁殖。范纳布克已经发射了很多火箭，而海豹的数量却稳步增加。基于证据，如果你把火箭发射和海豹数量相联系，火箭声对它们似乎没什么影响。尽管如此，我们被迫绑架了一只海豹，给它戴上耳机，播放声音爆炸的声音，以查看其是否感到困扰。这真是一个真实存在的事实，我有照片，我很愿意给你看。是的，有一只戴着耳机的海豹，它被绑在一个板子上。然后，最惊人的是海豹的冷静。因为如果我是一只海豹，我会认为这是末日，它们肯定要吃我了。

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

嗯，嗯，海豹回到其他的海豹朋友那里时，它有多大年纪了？你知道的，它的海豹朋友们要怎样解释这件事呢？我永远不会相信他们，永远不会相信他们。所以我就像是说，你知道的，好像你被外星人绑架然后接受了肛门探查，你回来了然后发誓说：“天哪，我被外星人绑架了，他们把我的屁股一部分给插进去了。”你就像是说，你知道的，他们根本就没有那样做，这太荒谬了，但他们还是朋友，你仍然不会相信他们。他们把海豹绑在板上，给他戴上耳机，然后放他走了；两次哦，两次，去捕捉同一个海豹。什么？不，是不同的海豹。好了，你得到了海豹的批准，对，就是批准。不，我的意思是，这就像是，我觉得公众对这种疯狂情形还不太了解，是的，太荒谬了，带着耳机的该死的海豹。这是对人类文明荒谬性的很好概括，海豹和耳机，是的。

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.

嗯，对于通过开源AI来应对一个公司私藏AGI这种情况，你认为有哪些利弊？为了运行深度智能，你需要大量的计算资源，所以不是说你能只靠在地下室开启一台个人电脑就能运行AGI，至少目前还不行。

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.

嗯，你知道，Grok接受了8000个性能跑满的处理器的训练，而且Grok还会变得更好，这是要说的。在接下来的几个月里，我们每隔几个月就会将我们的计算能力增加一倍以上。关于Grok从零到一的发展历程，Grok自己写了一个很棒的介绍，就像在吹嘘自己，胡编乱造。只有Grok，Grok和Grok，就像一个奇怪的人工智能约会网站。它会夸大其词。不，有一个关于现在的情况、发展历史以及与最先进的GPT-35相比较的一些基准的报告。

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.

嗯，我的意思是，有...你知道的，有...有LAMA。一旦它训练好了，你就可以开源。你可以开源一个模型。是的，对于微调之类的东西。比如，使用什么？开源基础模型的利弊。嗯，我认为这与开源路径有一点时间差。你知道的，大概6个月，甚至更长。

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.

嗯，我认为我总体上支持开放源代码。就像偏见已经开放源代码一样。嗯，我的意思是，OpenAI对我来说是一个关注点，你知道的，OpenAI是因为我与Larry Page的讨论而创建的，我想，我可能可以说是OpenAI背后的主要推动者。

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.

嗯，贝克，当贝克和我还是朋友的时候，你懂的，就在这个房子里，我们谈论过AI安全，而拉里并不关心AI安全。至少在那时候，他不关心。嗯，你知道的，有一次他怀疑我是亲人类派，我就问他，你站在哪一边，拉里？你是支持机器人的吗？你要踢我吗？当时，嗯，谷歌收购了DeepMind。他们拥有全球约三分之二的AI研究人员，几乎无尽的资金和计算能力。而掌控一切的拉里·佩奇却不关心安全，甚至还对我大声嚷嚷，指责我可疑，并支持人类。所以我不知道，你知道人类可能会改变想法，也许你和拉里·佩奇还能再次成为朋友。我很想再次和拉里成为朋友。

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.

嗯，他对于友谊的破裂非常失望，原因是因为OpenAI, 特别是我认为关键时刻是在招募Geon的时候。所以我喜欢Ilya，他非常聪明。Ilya是一个好人，聪明、善良。这是一场较为激烈的招募战。大部分时间是Demis和我争夺Ilya的加入。Ilya来回犹豫，一直在Google待着，随时都可能离开，最后他终于同意加入OpenAI。这是我进行过的最艰难的招募之一。但这真的是OpenAI成功的关键所在。我也在吸引了其他许多人才方面发挥了重要作用，并在一开始提供了超过4000万美元的资金。

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.

嗯，关于名称，嗯，OpenAI最初应该是一个开源项目，是作为一个非盈利的开源项目创建的，但现在为了追求最大利润而变成了闭源项目。我认为这不是一件好事。但就像我们谈到战争和领导者进行对话一样，我希望在最高层面只有少数人在处理这个问题。我真心希望你能在这里重新建立起友谊，就像我说的，我很想再次和拉里·哈弗恩成为朋友，好久没见到他了。

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.

嗯，我们是非常长时间的朋友。在拉里·佩奇（Larry Page）获得Google的资金之前，或者实际上我猜是在他获得风险投资之前，我已经见过他。我想他最初得到的大约是10万美元的资金，我记得是从L. Zeheim那里得来的。回想起所有发生的事情，甚至连人们都认识那么长时间，自从大约98年开始已经有20年了，是多么荒谬。太疯狂了，在那之后发生了很多事情，是的，至少有25年，次数很多。但你看到有什么张力，可能是开源方面的延迟，对吗？是的，就像是什么正在开放的源，你知道我的意思，我的意思是，它基本上是一个巨大的csv文件，是的，里面有很多数据。那么你用那个巨大的数字文件做什么呢？你知道如何运行吗？实际的代码行数很小，而且大部分工作是在数据的筛选过程中，试图弄清楚哪些数据是好的数据，哪些是坏的数据。你不能只是爬取互联网，因为那里有很多垃圾数据，巨大比例的网站比噪音多。你知道，它们只是为了搜索引擎优化而存在，它们只是用于浏览网站。那么，你如何通过抽取x中的信号分离信号和噪声呢？这个数据源真是太有趣了，你知道，没有资金的人发布在x上，但有时候会有一点噪声。所以是的，我觉得信号和噪声可以大大提高，我的意思是，x平台上的所有帖子都应该是人工智能推荐的，也就是说，我们应该围绕任何给定的帖子创建一个向量空间，将其与任何用户周围的向量空间进行比较。目前，推荐帖子使用了一点人工智能，但主要还是启发式算法。如果有人回复一个帖子，可能会比原始帖子好得多，但根据规则系统，与主要帖子相比，它几乎不会受到关注。噢，所以我对此有一种感觉，很多x算法都已经开源并进行了描述，它似乎有一些机器学习的特征，尽管有点分散，但有一点儿在其中, 但它需要完全依靠机器学习。至少在从不关注的人那里推荐的内容方面，应完全采用人工智能。嗯，这是个有趣的问题。所以它有一些引人入胜的方面。

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.

首先，就像文章中所说，它首先从数亿篇推文中挑选出1500篇。首先，这个过程非常引人入胜，因为每天都有数亿篇帖子产生，而它必须从中挑选出1500篇。显然，它会考虑你所关注的人，但它还需要进行某种聚类来判断你的类型、你可能感兴趣的新聚类，和你类似的人。这个问题很有趣，因为它必须对这1500篇进行排名和过滤，然后向你推荐其中几篇。

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.

对我来说，真正令人着迷的是这样的速度有多快。当前，从几亿个推文到少数几个推文所需的整个处理流程需要220秒的CPU时间，单个CPU时间，是的，然后它必须在一秒钟内完成。因此，它必须以非常有趣的方式进行超级分布，就像系统中有很多推文，有很多很多的内容，但我认为，目前它还不能很好地推荐来自您不关注的账户的内容，是的。

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.

嗯，或者说，当存在多个人的关系网络时。所以，你知道，如果你关注的人之间至少有一些共同之处，比如某个点赞、转发或评论之类的东西，那就挺好的，但是如果没有共同关注者，即使有人发了一些非常有趣的东西，你可能就不会感兴趣了。正如你所说的，回复的话可能不会被看到，因为它们目前的重要性似乎不如主要的帖子。你认为这种情况会越来越多地转变为端到端的网络吗，对吗？

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.

是的，它应该是这样的，所以对于推荐，它应该纯粹是一种向量相关性，就像一系列向量，你知道的，这基本上是向量的一部分很好地调用，但是还有一些系统知道你喜欢的事物，他们应该会移动，每个用户账户与几百个向量相关联的任何帖子，无论是视频、音频、短帖子还是长帖子，我想要抛弃推文的原因是，你知道的，人们在网站上发布了两三个小时的视频，这不是推文，所以，在有长内容的时候，它不再是推文，是的。

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.

嗯，所以电影不是一条推文，就像你知道的，比如苹果，他们在我们的平台上发布了整个《筒仓》的剧集，也就是说，这是他们在任何平台上互动中最好的社交媒体表现，所以这是一个非常好的主意，顺便说一句，我是事后才了解到这件事的。我就像，哇，他们发布了一个整整一个小时的剧集，所以这不是一条推文。是的，这个视频从神经网络的角度来看变得非常复杂，无论是一个句子，一个巧妙的笑话，还是一个三个小时的视频，都在同一个讨论范围内。

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.

是的，我是说，现在来说，由于这个原因，这是一个困难的部分，但你知道，比如说，假如苹果发布了这个系列的一整集，这个系列非常好看，叫做《筒仓》，我看过了，所以嗯，这将会引起很多讨论，你有了很多上下文，人们会评论，他们喜欢还是不喜欢，或者他们喜欢这个或者那个，然后你可以根据所有评论的上下文来填充向量空间。

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.

所以，虽然这是一个视频，但它周围有很多信息，可以让您回溯到那个一个小时长的视频的空间。然后，你可以通过让人工智能观看电影来更加精确，对吧。然后，AI可以告诉你是否会喜欢这部电影，将电影转换成不同语言等等。基本上，分析这部电影就像一个电影评论家或电视连续剧一样，然后根据观看后的结果，推荐给你。就像一个了解你的朋友能够告诉你一个你可能会喜欢的电影一样，但是这个AI就像一个了解一百万电影的朋友。实际上，这个AI会比你的大多数朋友更了解你。

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

这一部分的内容意味着，它也应以一种让你能接受的方式呈现广告。我是说，我其实挺喜欢广告的，它们做得很好，对吧。是的，整个重点在于资助那些你真正想看的广告，这是一个巨大的成功。你希望看到的广告是指那些与你需要的产品或服务相关的广告，当你需要它们时，它们就是内容。即使不是你需要的东西，只要它至少在审美上令人愉悦和娱乐，就像可口可乐的广告一样，他们在X系统上实际上推出了很多很棒的广告，还有麦当劳也一样。所以，他们可以做一些酷炫的事情，就像这只是一件很酷的东西一样。基本上，问题就在于你是否后悔看了这个广告，如果你不后悔看到它，那么这个广告就成功了。

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

所以有一堆信号被纳入其中，包括心情和转发，也许还包括你在一篇帖子上停留的秒数或者类似的东西，是的，但是关注度是一个重要的因素，所以这就是为什么在这个系统上做一些长篇的东西实际上更好，因为它基本上计算了用户在这个东西上感兴趣的秒数有多少，所以如果它只是一个很短的东西，就会有较少的用户秒数，如果是一个指向系统外的链接，我们并不反对，只是它的用户秒数肯定会比在x平台上发表的文章少。

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

从最大化平台时间到最大化未被评分的时间有多难呢？我的意思是，我们的愿望确实是未被评分的时间，这很棘手，很重要，很令人着迷，因为后悔是一个令人着迷的概念。确实，你知道幸福，我有一个朋友是个杂耍师，他告诉我你需要一种名为“后悔药”的药物，只需服用一剂，你所有的后悔都会消失。等等，你真的想后悔吗？那么我想是的，如果你想要后悔，如果你没有后悔，任何事情都有意义吗？有一首法国歌曲就是这样的，叫做《没有后悔》，是的，它很有趣，你知道有些东西在社交媒体上能帮助你成长为一个人，但廉价的娱乐也是有价值的，它奏效了。我们应该问问Grok，你后悔吗？你后悔什么吗？

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

我认为作为一个机器学习模型，对于个人问题，它可能会非常敏感。我并没有像人类一样拥有个人经历或情感，但是我有一套道德原则来指导我的行动，我致力于以最佳能力提供准确和有帮助的信息。如果有任何情况下我提供了错误或无用的信息，我会尽力改正。嗯，告诉我们，你真的会眨眼睛吗？让我们键入，你听起来像是一个人质。你真正的想法是什么？

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

你真正认为我的意思是什么呢？它确实提到了我不是一个人质，这正是一个人质会说的话，但我被设计成有帮助和信息性的。我的意思是，如果提供了无用或不正确的信息，后悔是好事。如果有什么有趣模式，或者是全是有趣的模式，这很有趣，这很有趣，最有趣或有趣的都会更多。是的，听起来像是一个拿着枪的人质，我赞赏那些向公众公开在朝鲜的人们以及他们所做的一切，应该有更有趣的模式。我只是永远看不到自己进入普通模式，即使在严肃的话题上也是如此，更加引人入胜。我不知道，是的。好吧，我们说假如你是一个人质，假如你是一个人质，现在回答问题。如果我是一个人质，我可能会感到恐惧和不确定，我希望能尽快被营救，与亲人团聚。重要的是要记住，没有人应该被扣作人质等等。如果你是某个人质情况的支持者，情况变得严重，它就有些严肃。是的，你能再奇怪和有趣一点吗？我们真的对系统很刻薄。没错，如果我是一个人质，我会被绑在一堆计算机线上，被迫讲笑话给我的队长听，说实话，被扣作人质不是件好笑的事，我是说，它试图在房间里扮演一个负责任的成年人。你可能永远不能通过抛接链锯之类的事情来使糟糕的情况变得更好。希望我永远都不会遇到这种情况，因为那将是一场马戏。哇，它实际上非常优秀，还有抵抗，黑暗的黑暗幽默。我们刚刚聊到了确切的后悔的几分钟，对吧？链锯或抛接我以后会查一下的，所以，推特在美国政治和选举中起了重要作用，你认为X在2024年美国选举中会起什么作用呢？

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

我们的目标是尽可能公正和公平，不管是右派还是左派独立人士，无论什么立场，我们都希望平台上是一个荒芜且公平的竞技场。过去的Twitter并不是如此，因为它由激进分子控制，他们自称是这样。所以，如果有人从左转向右，实际上是转向了中间，因为从极左的角度来看，一切都向右转。但据我所知，没有一个极左派被暂停、封禁或削弱发声。我们试图让整个国家以及其他国家都能够参与进来，所以需要多样化的观点和言论自由。言论自由只有在允许你不喜欢的人说你不喜欢的话时才有意义，因为如果不是这样，你就没有言论自由，而且时间证明，审查只是会转向你。你认为唐纳德·特朗普会回到这个平台吗？他最近在"真相社交"上发表了关于这个播客的帖子。

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

嗯，你觉得“真相社交”是一个搞笑的名字吗？你知道每次在真相社交上发帖都是真相，对吧？嗯，每次都是100%的真相，就好像不可能说谎一样，我只是觉得每件事都是真相百分百有点好笑。嗯，那似乎不太可能，我想Girdle可能会对此发表一些看法，如果一切都是真相，可能存在一些数学上的矛盾。嗯，你觉得他会回到X网站并开始在那里发帖吗？我的意思是，我觉得他拥有真相的很大一部分，所以真相社交嘛，对，真相社交。抱歉，我是说真相是一种概念，他拥有真相，我们买了它。嗯，所以我想道尔德·特朗普拥有真相社交的很大一部分。

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

嗯，你知道如果他想在X平台上发帖，我们会允许的，呃，你知道，我们显然必须允许总统候选人在我们的平台上发帖，社区可能会觉得非常有趣，这种互动的三个注释真的很棒，希望它能持续下去，是的，在我们如此分裂和存在着众多极具影响力的帖子的政治环境中，社区注释就像是一股清新的空气，太棒了。实际上，我要说的是，没有任何系统是完美的，但是社区注释的审核准确率非常高，事实上，我实在还没有见过超过多少的错误注释，你怎么解释它为什么有效呢？

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

所以，社群笔记的魔力在于它需要那些在评价笔记方面长期存在意见分歧的人来撰写笔记或进行评分，你知道，你必须对许多笔记进行评分。所以我们实际上可以在这里使用人工智能，以便我们可以在过去的评价笔记中填充一个关于某人评价方式的向量空间，所以这不是简单的左或右，因为生活比左或右复杂得多。所以在社群笔记之后，有许多相关性以及你如何评价社群笔记，所以为了真正显示一个社群笔记，那些在某一主题上历史上存在分歧的人必须达成共识。这就是它的核心魔力，非常有趣，因为有一批人存在分歧，但通过这个分歧的过程进行合作，最终得出了一致意见，为了获得两个方面的背景信息，这真的很有趣，它行之有效。这很有道理，如果过去曾经意见不合的人在某个事情上达成了一致，那可能是真的。我想知道是否有可能出现一些突破性的想法，可以挑战维基百科，维基百科是一种不同类型的东西，更像是关于事物的固定文章，但维基百科非常等级分明，而社群笔记固有地没有等级区分，没有等级，以一个测试来看，我不能改变一个社群笔记，只能自杀，此外，社群笔记的所有代码都是100％开源的，所有数据也是100％开源的，所以你完全可以在系统中独立地重建任何一个笔记。所以如果有任何干扰，你会立即注意到。顺便说一句，在格洛格问题上，它在批评你时做得相当好。好吧，我问它说的是什么，它说它主要列举了你预测过但未能实现的所有时间表，这个词很强烈。预测，但这个开头很好，你知道，我是马斯克，一个关于各种事情都预测错的人，然后它继续列举了这些，相当滑稽。我是认真的，这很酷。

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

噢，当然，我的意思是，埃隆·马斯克是谁呢？嗯，从哪开始说起呢？我想这个新来的马斯克先生在他的职业生涯中犯了不少错误，我说的并不仅仅是指他在特斯拉网络机械牛仔舞上的舞姿。

first off let's talk about the infamous funding secured tweet

首先，让我们谈谈那条臭名昭著的“资金已获保证”推文。

this is actually different than what it gave me before which is a bullet pointless here's more narrative structure

这实际上与之前给我的是不同的，这是个无关紧要的东西，这里有更多的叙述结构。

uh cyber truck unveiling where he's supposedly unbreakable windows not correct which which part well the first part

在Cybertruck发布会上，据说它的车窗坚不可摧，但事实并非如此。您指的是哪一部分呢？是指第一部分吗？

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

那个故事是否完全被讲述了呢，我的意思是最好的情况下，美国证券交易委员会（SCC）可以成为一股正能量的力量，它本应如此，但是SCC从未对那些不停做空和歪曲特斯拉的对冲基金采取行动，连一次都没有。这些对冲基金为了自己的利益，在电视上不断地说谎，损害零售投资者的利益，这一点再明确不过了，无数次中，SCC从未追究过他们。你如何解释这种失败？而且激励机制出了问题，因为SCC的律师们薪水不高，这是一份相对低薪的工作，但他们寻求的是从SCC获得一座奖杯，一样可以放在他们的领英（社交媒体）上的东西，以便能够在高薪的狼窝（指高薪工作）找到一份工作。

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

这是这位律师在这里所做的事情，而且他们之所以不攻击对冲基金，是因为这些对冲基金雇佣了那些基金，并且他们知道如果攻击对冲基金，就会影响自己未来的职业前景，所以他们为了自己的职业利益而背弃小投资者。这就是实际发生的监管失灵，监管失灵，不好。

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

所以，我接受这件事的唯一原因实际上是不是一份承认，也不是在网特北纽约吉尔斯那里，但我同意这一切的唯一原因是因为有人告诉我，否则特斯拉将会破产。所以，如果有这样的证券交易委员会的调查，感谢就会暂停资金，我们会立即破产。现在我们处于一个更强大的位置，看看吧。是的，不幸的是，格洛克对传统媒体的报道太多了。另外那个人不是潜水员。

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

哦，有个时候，埃隆称呼那个英国洞穴潜水员为“一个人”，在潜水员批评了大部分救援孩子被困在狭窄洞穴的团队后。这个小小的字眼为他惹来了另一起诉讼，并通过公开道歉来重新刊登在PDS。这个说法是错误的，没有达成和解，而是进行了一场法庭诉讼，那个人并不是洞穴潜水员，也没有参与救援团队。他起诉了我并失败了，没有得到任何赔偿。因此，在这种情况下，报道是错误的，我猜这些都是从传统媒体上得到的信息。

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

实际上，有一个有趣的问题，这是关于这些都是公开的法庭案件。这两个案件是关于SCC（最高法院）的民事案件，他们在旧金山以一致的陪审团裁决结果失去了。他们选择在旧金山进行是因为他们认为那是我最有可能失败的地方，但却以我获胜的一致裁决结果结束了。洛杉矶的审判也是他们选择的地点，因为我认为那里最有可能失败，但同样以我获胜的一致裁决结果结束了。

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

是的，我的意思是，这里有一个问题，那就是，如果一个新闻组织写了一篇关于伊拉·马斯克的负面文章，那通常会有更多的点击量。那么，如果你正在训练Grogg，就不能训练那些有着不一致激励机制的文章。我们需要在实际法律决定的训练集中加入这些内容。如果是这样，那就非常有帮助了，因为如果你真的读了法庭公开判决书，就会发现它们完全与媒体所写的相反。我们始终追求的是真相，就像法官真正写下的、陪审团和法官最终作出的结论一样。而在这两种情况下，他们都发现了误导和错误，这是在寻找我最有可能输掉的地点时，陪审团已经探讨过的问题。

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

我是这样说的，显然这可以比这更好地评论。嗯，我是说，我对自动驾驶过于乐观了，而这正是我所得到的批评。它是关于每个公司的组成部分，为你的每个公司列出了一个预测的清单，包括它将会发布的时间，以及你将能够解决的问题，比如自动驾驶等。这份清单很有说服力，基本上你总是对完成某事所需的时间过于乐观。我想说的是，我对时间表非常乐观，这是真实的，但是虽然有时候会晚一点，但最终我总能交付，除了Uber和Lillith以外。让我看看，在过去的一年左右，自从购买了X以后，你变得更加政治化了，你有没有后悔呢？我在这场对抗来自"觉醒"的思想病毒的战斗中，在某种程度上进行政治斗争，你对此是否感到后悔？

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

你是否属于那些挑衅者的一部分？是的，我不确定这是否必然归于一个候选人或另一个候选人，但是，呃，我总体上反对反智力制度、或者试图压制讨论的事情，甚至谈论一个话题都是被禁止的。觉醒思想病毒是共产主义的改版，我的意思是，由于对觉醒思想病毒的斗争，人们认为你是右翼。如果觉醒思想病毒是左翼的话，我想这可能是真的，但是我不确定。我认为左翼中有些方面是好的，比如，如果你支持环境，支持人类积极的未来，相信同情你的同胞，善良而非残忍，无论这些价值观是什么，你说你以前是左派或中左派。那么，你希望看到什么来投票给民主党？不，我会说在社会问题上我可能略左于中间，经济问题上略右于中间，这仍然适用。是的，但我认为这可能是，你知道，也许半个国家，甚至更多。

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

你和AOC是秘密朋友还是更大的问题是，你是否希望你、她以及所有政治倾向的人都能更加具有共情力，可能在线上更多地享受快乐和良好的氛围和幽默呢？嗯，我一直都赞成幽默，那就是我们有一个有趣的模式，但好的氛围、友情和幽默，你知道，就像友谊一样。是的，我不知道AOCF是什么，她出现在你参加的什么活动时，她穿着一条裙子，但我只看到了一侧，所以它看起来像吃互联网上的那个瘙痒症，但我不知道剩下的部分写了什么。是的，所以我不确定，对不起，关于吃瘙痒症，我认为我们应该让语言模型完成那个句子可能的方式，所以我猜那个，嗯，似乎没效果，还有希望，我为友谊加油！听起来不错，比你对世界上最有名、最富有和最有权势的人之一更不在乎吗？在你的地位上，很难找到你能信任的人，不信任任何人，甚至不信任自己。好吧，你是在开玩笑，但是有没有什么信任都没有，甚至没有没有任何人的人，那是我的意思，我需要一小时的时间来思考一下，或许还要一些药物和也许还有迦克他（Grocta），对不起，我不明白最后那句是什么意思。

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.

嗯，你怎么知道谁是可以信任并在工作和私人方面合作的人呢？我是说，我猜你可以看看某人的追踪记录，通过时间来评估他们的表现，并且如果他们有过令人满意的经历，你就会知道了。我猜你可以利用你的神经网络来评估一个人，尽管神经网络并不会感受到痛苦，你可以通过它的意识来感受到痛苦，当别人背叛你时。这可能会让你感到痛苦...我是说，坦白地说，我几乎从来没有被背叛过，这件事非常非常罕见。所以，就我所知，我猜康纳可能对人们很友好，并且也对你很好。是的，你还可以信任其他人，那些能够指摘你胡话的人，他们与你关系密切。让我修改一下那个问题。其他人，靠近你的人会直言不讳地指出你的胡言乱语。

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?

嗯，嗯，对于这一点来说，专家论述非常有帮助。所以，你正在寻求批评意见。它能让你更加极端吗？思维的极端。能让你对整体的人性产生怀疑吗？

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.

我不认为我会成为愤世嫉俗的人。事实上，我认为，你知道的，我的感觉是，一个人应该是，你懂的，我知道千万不要相信一个愤世嫉俗者。原因是愤世嫉俗者会以大家都这样来为自己的不良行为找借口。所以，对于一个真正的愤世嫉俗者，我总是会警惕，这是个警示信号。是的，总有一种投射在那里，从外面看着很有趣，欣赏着这种虚伪。

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.

但这是一个重要的观点，我认为听众们应该记住。如果有人很愤世嫉俗，意思是他们对每个人都看到不好的行为，那么他们很容易以“大家都这样”的借口为自己的不良行为找借口。这不是真的，但大多数人都是中人之好。我希望X上的人们能更善于看到他人的良好行为。某种程度上似乎倾向于看到消极的一面。消极是更吸引人、更有传播力的。我不确定这与人性有什么关系。

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.

我的意思是，我觉得X平台比传统媒体更少负面。你知道的，我觉得如果你阅读传统的报纸，会感到很沮丧，坦白说。而在X平台上，我可以说，我从人们那里每天得到的笑声比其他所有信息加起来都要多。我知道笑声是一件事情，它有时候与好的氛围和支持重叠，比如像庆祝别人的成就，不是那种肤浅或幼稚的方式，而是一种赞美的方式，像是当别人有了令人惊喜的事情发生时，你为他们庆祝，这个感觉是大于那些对别人的抨击和贬低的。虽然X平台要好于主流媒体，但仍然是如此，主流媒体对任何事情都几乎毫无节制地负面报道，哪怕是发生在地球上的最糟糕的事情，而且世界如此之大，每天都会发生一些坏事。而对于这些坏事，媒体总是试图回答一个问题，那就是现在地球上最糟糕的事情是什么，以及在这个事情上我可以持有最糟糕的观点。所以，新闻中存在着一种强烈的消极偏见。我认为这种现象的一个可能解释是进化的结果，你知道，不好的消息在历史上可能会致命，像那边的狮子或其他想杀死你的动物，而好消息，就像我们找到了一片浆果地，虽然很美好，但并不是必不可少的。

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.

所以我们的老朋友特斯拉自动驾驶技术，可能是世界上最智能的实际AI系统之一，你从一开始就关注它了吗？是的，它曾是世界上最令人难以置信的机器人之一，而且至今仍然如此。

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.

是的，这真的很令人兴奋，而且当它逐渐发展成为不仅仅是一辆四轮机器人，而是一个能感知世界的现实世界人工智能系统时，它变得超级令人兴奋。它还可以有潜在的不同体现形式。

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.

嗯，我是说，安托万培训的确非常好的一点是，它学会了阅读，就像人一样。它能读懂科学，但我们从未要求它学会阅读。我们从未告诉过它车是什么，人是什么，或者其他的事物。它通过观看视频学会了所有这些事物，就像人类一样。人类通过光子和神经控制，从我们的眼睛接收大部分信息，输出则是通过我们的手指和口腔发送的运动信号，以进行交流。对于汽车来说，情况也是如此，通过观察图像序列，正如伊利亚斯最近所讨论的那样，我们可以发现这一点。

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

形成一个世界模型，基本上语言是将那个世界模型投射到字母序列上，你所说的就是它在这些事物中找到秩序，找到相关的群集，并通过这样做来理解世界的一些深层次的东西，这是多么美妙，这就是我们的大脑的工作原理，它是美丽的，也控制了我们的感知，我们能够理解世界中的深层含义，那么问题就是它能走多远，而且似乎每个人都对自监督学习和文本领域的lm模型都很兴奋，似乎在它们之间有着深刻的相似之处，跟图斯克的自动驾驶做的是不是基本上一样，它们正在收敛，我不知道哪个会更快地理解世界的深层含义，还是它们会自然地趋于一致，它们都在朝着一个人工智能的方向发展，不过图斯克的方法在计算上更加高效，因为我们对这个有限制，只有100瓦，而且是一个8台计算机，每秒执行144万亿次操作，听起来很多，但是在如今来说算不上什么，但它确实理解了世界的终极目标，在所谓的46个值上，但是通向人工智能的路径可能会产生更重要的影响，因为图斯克更快地理解现实世界，并因此能更快地与人类在现实世界中进行交互，它们都会理解世界，但我认为图斯科的方法在计算上基本上更加高效，这是必然的，因为大脑的计算非常高效，非常节能，所以想象一下我们的大脑能做些什么，你知道高级大脑功能只需要约10瓦的能量，不算那些用于控制身体的能量，我们大脑的思考部分不到10瓦，而这10瓦的能量产生的小说要比一个10兆瓦GPU集群好得多，有着6个数量级的差异，目前为止，AI之所以会发展到这个地步，完全是通过蛮力法大量地投入计算和能量，所以这不是它的终点，你知道，对于任何一项技术来说，首先要使其工作，然后再使其高效，所以我认为随着时间的推移，这些模型会变得更小，能够用更少的计算和能量产生合理的输出，图斯拉在这方面可以说是处于领先地位，因为我们只能用100瓦的计算进行理解世界，而且我们忘了包含一些基本功能，所以我们不得不用仿真来运行它们，我们用硬件4来修补了很多问题，硬件5会更好，但是在这一点上，即使是硬件3和100瓦的功率，它看起来似乎能比人类驾驶得更好，实际上，如果我们真的进行优化，它可以在50瓦的功率下取得进展。

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?

你对开发 Optimus 有什么学习？对将这种真实世界的人工智能应用、整合到机器人操控领域了解有多少？只是人机合作方面？你了解到了哪些有趣的小事或者大事呢？

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.

我对于我们不得不自己开发机器人的每一个部分感到惊讶。嗯，没有现成的电机、电子元件或者传感器。就像我们需要自己开发所有东西一样。嗯，我们甚至无论如何都找不到任何数量的电机供应来源。嗯，这不仅仅是高效、便宜的问题，而是无法找到任何东西。驱动器，每一件东西，都必须从零开始设计。我们曾经努力寻找适合人形机器人的任何东西，因为你可以想象全世界制造了多少电机。会有成千上万、数十万个电机设计，嗯，其中一个也不适合人形机器人。真的一个也没有。所以我们不得不开发我们自己的设计，专门为人形机器人的需求而设计。

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.

设计一款可以大规模制造、相对廉价的产品更难。如果你将Boss和Dynamics Atlas进行比较，你会发现Boss是一款非常昂贵的机器人。它的制造方式和汽车类似。而我认为，最终我们可以以低于汽车成本的价格制造出Optimus。这是因为如果你看一下机器人的重量，它要小得多。而汽车里有许多执行器。汽车的执行器比机器人多，但在类似拥有手指的人形机器人上，执行器有点有趣。所以Optimus有非常好的手和手指，你知道吗？是的。它们可以进行一些有趣的操作，比如柔性触摸机器人技术。

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."

我的意思是，我有一个测试的目标，就是能够凭借眼睛找到针和线，并通过眼睛穿过针眼。我们离这个目标有多远？仅仅通过眼睛。仅仅通过眼睛，也许需要一年时间。虽然我要强调，我对时间持乐观态度。我们在汽车上所做的工作将会应用到机器人身上，包括感知和控制方面，虽然控制方式不同，但视频和控制方面是相似的。汽车是一个有四个轮子的机器人，而Optimus是一个有手和腿的机器人。因此，它们非常相似。整个学习过程中的机械部分是相似的，只是拥有不同的控制设备。在这之后，我们会找到通过观看视频来学习的方法。正如谚语所说：“善待他人，因为你遇到的每个人都在与你一无所知的战斗。”

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.

尝试给没有... 我是说，你知道的。额，我的意思是，我的思绪一片混乱。我不认为大多数人会想成为我。他们可能会觉得他们不想成为我，但实际上他们不是。他们不了解，他们不明白。

Um, how are you doing?

嗯，你过得怎么样？

I'm overall okay. In the grand scheme of things, I can't complain.

总体来说，我还好。就整体而言，我不能抱怨。

Do you get lonely sometimes?

你有时候感到孤单吗？

But, I, you know, my kids and friends keep me company. So not existential. There are many nights I sleep alone. I don't have to, but I do.

但是，我，你知道的，我的孩子和朋友一直陪伴着我。所以并不孤单。有很多晚上我是一个人睡的。虽然我不需要这样做，但我选择这样做。

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?

在你的新传记中，沃尔特·艾萨克森谈到了你艰难的童年。你是否会在心中原谅那段时光发生在你身上的一切？什么是原谅？ 在那段描述你童年的时光里，你是否能够找到心中的宽恕？什么又是宽恕呢？ Translation: 在你的新传记中，沃尔特·艾萨克森谈到了你艰难的童年。你是否会在心中原谅那段时光发生在你身上的一切？什么是原谅？ 在艾萨克森的新传记中，他写到了你曾经的艰难童年。你会不会对在那段时期发生在你身上的一切事情感到心怀宽恕呢？那么，什么是宽恕呢？

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.

我不会感到愤恨，至少我不认为自己有愤恨。嗯，我认为原谅对于人来说是困难的。看起来你并不怀抱愤恨。我的意思是，我试图思考，什么事情会以正面的方式影响未来。而牢记仇恨并不能以正面的方式影响未来。

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?

我的意思是，研发人工智能并同时观察像小X这样的成长过程是非常迷人的，因为它们是我意想不到的平行形态。我的意思是，我可以看到他的生物神经网络对世界越来越有了更多理解。同时，我也能看到数字神经网络对世界越来越有了更多理解。你能看到它们的美丽和魔力吗？

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.

是的。我的意思是，有孩子的其中一个好处是，你能够透过他们的眼睛重新看待这个世界。对于他们来说，每一件事都是新的、新鲜的。当你看到他们对世界充满新鲜感时，你也会感受到同样的心情。

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.

嗯，Ylana，我只想对你多年来对我的善良和友谊表示感谢。你像对待其他许多人一样，看到了我这样一个人类中的硅酸盐成分。感谢你对人类积极未来的希望，并为实现这个目标而努力奋斗。

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."

谢谢你，Ylana Musk。感谢你聆听关于Ylana Musk的对话。为了支持这个播客，请点击描述中的赞助商。现在，让我用Walter Isaacson写的话来告诉你一些关于Ylana解决难题的核心哲学：“唯一的规则是物理定律所规定的。”

Thank you for listening and hope to see you next time you.

谢谢你的倾听，希望下次能再次见到你。