播客精选：德瓦克什·帕特尔求知若渴的探索之旅

AI目前是如何融入你的工作和生活中的？

How is AI integrated into your work and in your life right now?

我发现很多话题我只是模糊地知道发生了什么，而与Claude交流能确保我走在正确的轨道上，这非常有帮助。

So a lot of topics I just find I have a vague sense of what's happening, and it's super helpful to chat with Claude to make sure I'm on the right track.

这一切背后的驱动力是什么？你觉得这是怎么回事？

What is driving all of this? What do you think that's about?

我真的只是想知道一切。等等，退一步说。为什么这是必要的？到底发生了什么？我该如何思考这里发生的更广泛背景？

I really just want to know everything. Wait, step back. Why is this necessary? What's going on? How do I think about the broader context of what's happening here?

因为除非我对他们谈论的内容有一个良好的心智模型，否则我真的无法提出好的问题。

Because I really can't ask good questions unless I have a good mental model of what they're talking about.

本播客由谷歌赞助。大家好，我是David，谷歌Gemini的产品负责人之一。如果你有梦想并描述它，Gemini中的VO3可以帮助你将其实现为视频，现在还有令人惊叹的音效、背景噪音甚至对话。使用Google AI Pro计划尝试，或通过Ultra计划获得最高访问权限。请登录gemini.google注册并开始创作，向我们展示你的作品。

This podcast is supported by Google. Hey everyone, David here, one of product leads for Google Gemini. If you dream it and describe it, VO3 in Gemini can help you bring it to life as a video, now with incredible sound effects, background noise, and even dialogue. Try it with the Google AI Pro plan or get the highest access with the Ultra plan. Sign up at gemini.google to get started and show us what you create.

Dorkesh，欢迎来到节目。

Dorkesh, welcome to the show.

谢谢邀请我，丹。

Thanks for having me, Dan.

能请到你真是太激动了。对于不认识你的人——虽然我觉得大家都认识你——你做的AI访谈是我见过最棒、最聪明、最真诚的。你请到了像马克·扎克伯格、德米斯·哈萨比斯、帕特里克·科里森这样不可思议的嘉宾。你打造了一档面向聪明人学习AI的必看节目，但你也涉足了许多其他领域，比如地缘政治、历史等等。这真的太棒了，你也是激励我制作高质量内容的灵感来源之一。

I'm so excited to have you. For people who don't know you, I assume everyone knows you, but for people who don't, you do the best, most like, honestly, the smartest interviews in AI that I found. You have, like, really incredible guests like Mark Zuckerberg, Demis Esabas, Patrick Hollison. You you you've created, like, the go to show for smart people to to learn about AI, but you also kind of branch out into lots of other things like geopolitics and history and stuff like that. It's it's really great, and you're like, you're just one of the one of the people that inspire me to, like, make smart content.

所以非常感谢你能来上节目。

So I appreciate you coming on the show.

嗯，你这么说真是太客气了。我一直试图进行那些如果我和这些教授或CEO共进晚餐时想进行的对话——我会想问他们什么？我很高兴其他人也喜欢这些内容。

Yeah. That that's really kind of you to say. I mean, I've I've always been sort of trying to make have the conversations that I would like to have if I was getting dinner with one of these professors or CEOs, what would I wanna ask them? I'm I'm glad other people enjoy them as well.

是的，这一点很明显。我觉得今天能稍微角色互换一下也很有趣，因为你虽然做过一些访谈，但主要是采访别人。我想大家可能都好奇你在工作和生活中是如何使用AI的，所以这就是我们今天要聊的话题。

Yeah. It comes through. And I I think, like, it's it's really fun to get to, like, turn turn the tables on you a little bit because you've done some interviews, but but mostly you're interviewing other people. And I think, like, it's probably on people's minds, like, how you use AI in your work in in your life. And so and so that's what we're gonna talk about today.

也许可以先简单概述一下，AI目前是如何融入你的工作和生活的？

So maybe just start by giving us a little bit of an overview. Like how is AI integrated into your work and in your life right now?

是的，其实变化很大。我记得一年前，那是在GPT-4发布之后，有人问我是否用AI辅助研究或准备工作，我当时说完全不用，觉得它毫无用处，只会给出一些平庸的内容。

Yeah, so it's actually changed a lot. I remember a year ago, this was after, I think it was after GPT-four, somebody asked me, do you use AI to help you with your research or prep? And I was like, not at all. It's completely useless in mid. It gives you these banal.

你问它，比如，我应该问某某教授什么问题，然后我会给你这些老套的问题。你在哪里长大的？你的书是关于什么的？诸如此类。所以一开始效果很糟糕。

You ask it like, what should I ask so and so professor and I'll give you these banal. Where did you grow up? What's your book about? Whatever. So initially it was terrible.

我认为最近这些模型已经发展到这样一个程度，特别是像4.0版本或者尤其是新的云端模型，它们变得智能且具有探究性，能够考虑你提供的上下文。所以它们在“我应该问这个人什么问题”这方面仍然不是那么擅长，因为很明显这就是为什么我有工作的原因，对吧？这样我才能想出问题。但对于研究本身来说，至少对我来说，我试图消化他们写过的所有东西、对他们观点的所有反驳，以及所有其他考量。

I think recently the models have gotten to just the point where with these like, I don't know, four point zero or especially with the new cloud models, they are intelligent and interrogative and can consider the context which you provide to them. And so they're still not that good at like, what should I ask this person? Because obviously that's why I have a job, right? So that I can come up with the questions. But for the research itself where you're for me at least, I try to ingest everything they've ever written, all the rebuttals to their ideas, all the other considerations.

这通常涉及很多内容，特别是考虑到我试图深入许多不同的领域。就像我最近刚做的采访是和Dylan Patel，他写的是半导体分析。那是一份关于半导体和AI硬件等的出版物。所以有很多东西需要学习。可以看看我的工作流程，但能够有这样一个工具，让我问“这里发生了什么？”，这非常有用。

And there's often a lot involved, especially given there's many different fields I try to go deep into. Like the last interview I just did was with Dylan Patel, who writes semi analysis. It's a publication about semiconductors and AI hardware and so on. So there's a bunch you have to learn. Can go through my workflow, but it's incredibly useful to be able to have this thing where I'm like, what's going on here?

你能帮我解释这个吗？然后我想我一直在思考的一个更大的事情是，自从我采访了Andy Matuszak（如果你的观众熟悉的话，他是那个经常谈论间隔重复和其他工具如何增强我们学习能力的人，以及正常的学习模式实际上你并没有学到那么多。如果你随便拿起一本书开始阅读，你并没有从中获得太多。我真的发现这非常符合实际情况，以至于如果我只是随意阅读一本书，我觉得我基本上是在浪费时间或娱乐自己。我已经想出了一些不同的工作流程和工具，帮助我真正探究并确保我巩固了我所阅读或学习的内容。

Can you help me explain this? And then I guess one bigger thing I've been thinking about is ever since I interviewed Andy Matuszak, if your audience is familiar, he's the guy talks a lot about how spaced repetition and other tools can enhance our ability to learn and how the normal mode of learning, you're actually not picking up that much. If you pick up a random book and start reading, you're not getting that much out of it. And I really have found that to very much to be the case to the extent that if I'm just casually reading a book, think I'm basically wasting time or entertaining myself. I have come up with a couple of different workflows and tools that help me really interrogate and make sure I've reinforced what I'm reading about or learning.

像语言模型这样的工具非常有用，因为它能在另一种上下文中给你提供内容，而且如果你愿意，它可以测验你。所以它在这方面超级有帮助。

A tool like a language model is very helpful because it gives you the content in another context and you can, like it makes it can quiz you if you want. So it's it's super helpful with

那种东西。真的很酷。我认为我们应该开始。我想从后往前开始，比如，从你用来阅读的工具开始，因为我认为所有的阅读某种程度上是输入，像是采访的输入之一，然后我们再深入采访。我对这两部分都感到非常兴奋。

that kind of stuff. That's really cool. I think we should start. I wanna start back to front, like, with the the stuff you're using to read because I think the reading all that reading is sort of the input, like, one of the inputs to the interviews, then we'll get into the interviews. And I'm really excited for both.

那么，让我们从使用AI来阅读和学习开始吧。

So let's start with using AI to read and to learn.

正如我之前所说，我认为重要的一点是，当我用几周时间研究某个主题时，尤其是对我来说陌生的困难主题，绝不能只是随意阅读。因为如果只是随意阅读，就像每天重复阅读相同的关键术语和概念，每次都从头开始。举个例子，我最近在采访Dylan对吧？如果我去看他的出版物和分析，会发现大量需要理解的专业术语。他最新那篇关于为什么还没人建成大型训练集群的文章就很有意思。

So as I was talking about one of the main things I think is important is if I'm studying a topic over the course of a few weeks, especially if it's a difficult topic, it's like new to me. It's incredibly important that I'm not just casually reading because if you're just casually reading, it's like every day you reread the same key terms, the same concepts, and you start over from scratch. So one of the things I like to do, for example, I was recently interviewing Dylan, right? So if I go to his publications and me analysis, there's just a ton of lingo and things you have to understand. So the new one was pretty interesting.

我做的第一件事就是搞清楚需要理解的核心观点和概念。于是我给自己创建了一个Hugging Face空间——说实话你不需要这么复杂，用Claude帮你创建很简单，或者你也可以用其他工具。

It's talking about why nobody has built a huge training cluster yet. And then first thing I do is just like, what are the key ideas and concepts I really need to understand? So I made myself a hugging face space. You honestly don't need to do anything like this. It's pretty simple to have Claude build your hugging face space or if you prefer.

它的功能就是对我粘贴的所有内容应用这个提示词。你可以直接把提示词复制粘贴到Claude里。基本上我复制了Andy Matuchak关于如何写好提示词的一些建议，然后让Claude帮我生成间隔重复记忆的提示词。这样操作后，几秒钟就能得到反馈。

What it literally does is apply this prompt to everything I paste in. So you just copy paste that prompt into Claude yourself. But basically it just has I copy pasted some of the things in Andy Matuchak's post about how to write good prompts. And I just asked Claude to make those prompts for me, spaced repetition prompts. So when I do this, hopefully in a few seconds we'll get something back.

初始阶段这会帮我理清需要理解的核心观点，非常实用对吧？我还可以进一步细化让它更有帮助。对于听众来说，它生成了一系列问答对，整合了这篇关于AI硬件文章的关键要点——虽然具体技术细节可能会让人无聊，但这些都是如果不理解就会完全错过重点的内容。

Initially, this will give just give me some ideas of like, what are the key ideas here I need to understand? Super So useful, right? I can even zoom in a little bit so it's more helpful. So for the audience who is listening, it's given me a bunch of question answer pairs that consolidate the key things I need to understand about this post about, know, we can go through the specifics here. I'm sure that the actual specifics of AI hardware will bore people, but a lot of the things where it's like, okay, if you don't get this, you've like totally missed the boat here.

你可以从这样的内容开始。我会添加到间隔重复应用里，或者直接浏览这些内容，逐渐形成认知：比如训练GPT-4级别模型需要10万块H100芯片集群，大规模集群训练需要哪三种并行计算方式等等。这是技术类文章的处理方式，其他类型的文章可能会生成不同类别的记忆卡片。

And so you can start with something like this. I add it to my spaced repetition app or I can just look through this and I'm getting a sense of like, oh, okay, here's what it would take to train a GPT-four level model on a 100,000 H100 cluster. What are the three main types of parallelism you need to use to train on a big cluster or whatever? And this is on for a technical post. On other kinds of posts, there might be different kinds of cards that come up.

历史类文章可能是另一种形式，哲学类又有所不同。这种方法能帮我建立知识图谱。

For history, it might be a different kind of thing. For philosophy, it might be a different kind of thing. So this gives me a lay of the land.

太棒了，这非常有意思。我感觉可以朝多个方向深入探讨，但我想先了解：你通常在什么时间如何阅读？你是专门为节目内容采用这种方法，还是对所有认真想学习的阅读材料都会这样做？

I love this. This is super interesting. I feel like I can go in a bunch of different directions. But where I want to start is how are you reading and when are you reading? So is this like are you using this specifically for reading that you're doing for the show, or are you just doing doing this for any reading that you're doing that you feel like is serious and you really want to learn?

两者都有。就这个周末，我在读一本忘了作者名字的书，叫《中世纪技术与社会变革》，讲的是过去一千到五百年间发展的各种技术，比如马镫，如何影响社会。这本书挺有意思的，可以读读。然后我在想，我真的理解了他试图阐明的这种关系吗？所以后来，我其实在阅读过程中还进行了一些爪聊（claw chats）。

Both. So just this weekend I was reading, I forgot the author's name, but it's a book called Medieval Technology and Social Change, it's about how different things that were developed through the last one thousand to five hundred years technology is like the stirrups, how they affected society. And it's like, it's entertaining, you can read it. And then one of the things is like, Okay, did I really understand what's going on here with the relationship he's trying to elucidate? So afterwards, in fact, I had some claw chats where I was just going through while I was reading it.

让我看看这个能不能回忆起来。

Let's see if this recollects.

说吧，我想知道。我迫不及待了，因为我有这本书，就放在我面前的桌子上。所以我想知道你从中学到了什么。

Do it. I want to know. I'm on the edge of my seat because I have this book. It's like sitting on the desk in front of me. And so I want to know what you got out of it.

好的。首先，我会让它帮我做一些基础复述提示。一开始，我只是觉得我读了这一章，但不确定是否理解了。所以就请它解释一下这一章，关于他如何说马镫创造了封建主义。这里的联系到底是什么？

Okay. So first, I would just ask it to make some base repetition prompts for me. First of all, I was just like, I read the chapter, I'm not sure I got it. So just explain to me the chapter about how he says that stirrups created feudalism. Like what exactly was the connection here?

所以这是一个更浓缩的版本，基本上就是这样。如果你理解了这个，它就是一个有用的框架，这样当你阅读章节的其余部分时，你就知道各个部分是如何组合在一起的。

So it's a much more condensed, like here's what's going on here basically. If you understand this, it's a useful scaffold so that when you're reading the rest of chapter, you understand where the pieces fit together.

你有没有试过……我有时会这样做，因为有时候它不知道，尤其是像这样不太流行的书。我有时会创建一个小的Claude项目，如果我能找到文本的话就上传上去。你试过这个吗？

Have you tried like, one one of the things that's that I've tried with this is like because sometimes it doesn't know, especially for a book like that where it's like not that popular. Have you tried one of the things I do is create a little Claude project and then upload the text if I can find it. Have you tried that?

事实上，让我直接去claude.ai项目。所以如果我就像是一个播客主持人，试图提出好问题。我猜接下来是一位遗传学家，我就上传文件的EPUB版本。我用在线转换器将EPUB转换为文本，然后上传到项目知识库。

In fact, let me just claude.ai projects. So if I go to literally just sound like I'm a host of a podcast where I try to ask good questions. My upcoming guess is a geneticist and I just upload the I get the EPUB of the file. I convert the EPUB to a text using an online converter. I upload it to Project Knowledge.

那我刚开始为这位嘉宾做准备，但我会进行很多对话，比如问他如何解释现代欧洲人由哪些群体组成。里面包含了所有背景信息，最终变得非常有用，就像你刚才说的那样。

Then I've only just started prepping for this guest, but I'll just have a bunch of chats where I'm like, how does he explain what groups made up modern Europeans? It has all the context in there that ends up being incredibly useful, like you were saying.

是啊。这太酷了。我喜欢这个。我喜欢这个功能。好的。

Yeah. That's so cool. I love that. I love that feature. Okay.

等等。我们回到马镫以及你正在和这本书进行的对话，或者关于这本书的讨论。

Wait. Let's go back to stirrups and this chat you were having with this book or about the book.

是的。所以，你知道，它解释说马镫之所以会催生封建制度，是因为你需要大量土地来供养那些成为重骑兵的人，也就是骑士。骑士需要大量土地才能有收入来购买盔甲、长矛和其他装备，并进行训练。但只有拥有马镫，你才能在挥剑攻击时借力支撑自己，否则你就像蒙古人那样只是射箭。但这里有很多令人困惑的地方，比如：为什么当骑士如此昂贵，以至于需要完全没收教会土地来补贴这种骑士生活方式？

Yeah. So, you know, it explains that the reason stirrups should create feudalism is because you needed you needed a lot of land basically to support the kinds of people who become heavy cavalry, the knights. The knights need a lot of land in order to have the income to have, you know, like armor and lances and other kinds of equipment and to train themselves. But a knight is only possible if you have a stirrup against which you can brace yourself as you're attacking with a sword because otherwise you're just like a Mongol who's shooting bows and arrows. But then there's a bunch of stuff that's confusing here like, why is it that expensive to be a knight that you need to completely confiscate church lands in order to subsidize this knight lifestyle?

然后对于这类问题，作者已经去世了，但我对此很模糊。我不知道是怎么回事。这类事情书里甚至都没谈到，对吧？但我总是可以继续和Claude对话，让它解释发生了什么。所以这就像是一种休闲阅读，而Claude最终变得超级有帮助。

And then on these kinds of questions, the author is dead, but I'm just murky about it. I don't know what's going on. These kinds of things I can the book didn't even talk about, right? But I can always just continue the conversation with Claude and have it explain what's going on. And so this is just like a recreational reading that Claude ends up being super helpful with.

我觉得这真的很有趣。你怎么看这类书？比如，作为一个非常喜欢历史的人，你怎么看待那些挑出像马镫这样的特定事物，然后说所有这些东西都可以追溯到那一件事，听起来很有道理。但也有一些书，比如《枪炮、病菌与钢铁》，贾里德·戴蒙德提出了那个整个论点——我不记得具体是什么了，但好像是关于 warmer climates 的人或者……我记不清具体论点了，但结果证明是完全错误的。是的。

I think that's really interesting. What what do you think about, like, books like this? Like in your you know, as as a person who likes history a lot, books that sort of single out, like, a specific thing like the stirrup and then are like, well, you can trace all this stuff to that, like, one thing where it, like, makes so much sense. But then there are things like, I don't know, like Guns, Germs, and Steel where, like, Jared Diamond had that whole thesis about I I can't remember the the exact thing, but it's like people in warmer climates or I I can't remember the exact thesis, but it turned out to be, like, totally wrong. Yeah.

你对这类事情有什么感觉？

How do you feel about things like that?

是的。所以我对这类书的看法是，简而言之就是：确实有些书写得很糟糕，但别读那些糟糕的就行了。公共知识分子有个失败模式：他们最初从某个学科起步，在那里做出杰出工作，然后写第一本宏观著作，阐述这个思想如何解释世界大部分现象，结果大获成功。于是他们就进入了公共知识分子模式。

Yeah. So my opinion on these kinds of books, there's I mean, the sort of concise answer is like, yeah, there's ones that do it poorly, but just don't read the ones that do it poorly or something. There is a failure mode for public intellectuals where they initially start off with a discipline and they do some exemplary work there. And then they write an initial broad book that's about how this idea explains a lot of the world and it does incredibly well. And now they're in public intellectual mode.

接下来写的书就变成了'这是我的万物理论'，但这种书往往不尽如人意。所以我确实担心这类情况。但 presumably（大概）原因是——我也不确定，我不喜欢读500页就讲某个东西物理原理的书。这有什么意义呢？我想了解的是其影响，也许他们的观点是错的，但我们在这里追求的到底是什么呢？

And now the next book has to be like, here's my theory of everything, and it's just not that satisfying. So I do worry about those kinds of things. But presumably the reason, I don't know, I'm not into like reading 500 page books about like just how this tear up physically worked. Like what's the point of that, right? I do want to understand the implications and maybe they're wrong, but what else are we trying to do here?

也许你就是天生关心立体声的物理原理。我想举几个例子。有很多有趣的话题，如果不考虑完整背景故事，就无法触及核心。事实上，有几本传记在这方面特别突出，比如卡罗写的林登·约翰逊传记，或是科特金写的斯大林传记——这些本质上都是二十世纪历史（科特金那本还涉及二十世纪前）。我记得卡罗的LBJ传记是从19世纪中叶科曼奇人对边境定居者的袭击开始写起的。

Maybe you just intrinsically care about how the stereo physically works. I will point out a couple of examples. So there's a lot of interesting topics where you really can't get at the heart of the matter without just considering the whole story. And in fact, so a couple of biographies especially stand out in this way, where if you look at Caro's biography of LBJ or Codkin's biography of Stalin, it's basically a history of this twentieth century, or in the case of Codkin, before the twentieth century. I think this Caro books on LBJ start off with the Comanche raids on frontier settlers in the mid nineteenth century or something.

书中讲述了德克萨斯州的乡村生活、为什么电气化如此重要，以及许多其他内容。所以这本质上是二十世纪的历史，但有着非常特定的视角或焦点——通过一个推动故事发展的人物来呈现。我发现这类书对全面理解一个时代非常有帮助。还有几本书其实并不是要写万物理论，比如卡罗并不是要写二十世纪通史，但他们就是忍不住要展开。

And it goes through rural life in Texas, why electrification was such a big deal, a whole bunch of other things right now. So it's basically history of the twentieth century, but it has a very specific point of view or a specific locus, a character that's moving the story along. And I find those to be incredibly helpful in getting a full picture of what's going on in an era. There's a couple other books where they really aren't trying to write a theory of everything. Like, I don't think Caro is trying to write about like what is the history of the twentieth century, but they just can't help themselves.

他们觉得：如果我不告诉你所有相关背景，你就无法真正理解我关心的这个特定主题。比如科特金的斯大林传记是从俾斯麦的军旅生涯写起，讲述这如何改变了列强对殖民主义和现代化需求的看法——这本书就从这里开始，而这可是本关于斯大林的传记啊。所以，是的，我特别喜欢这类书。

They feel like you really cannot understand the very specific topic I care about unless I tell you everything about everything. Like Kotkin's story biography of Stalin starts with the like Bismarck's career as a military general and how that changed the way that different powers thought about colonialism and the need to modernize. And that's where it starts, right? And it's a biography of Saul. And so, yeah, I love those kinds of books.

我觉得这里涉及一个关于宇宙互联性的深刻观点。但对于创作者——无论是写作者还是播客制作人——也有个很有趣的启示。因为大家都有种深层恐惧，害怕被定型。会觉得：如果我选了这个特别具体的主题，就无法全面展现自己，无法呈现多面性。但其实不是这样的。

I think there's like a very just deep point about the universe being interconnected there. But there's also like a really interesting point for people who want to make stuff, like make writing or make podcasts or whatever. Because, like, there's this deep fear that everyone has about, like, being pigeonholed. And it's like, well, if I pick this, like, really specific topic, I won't be able to, like, bring all of myself to it or I won't I won't be able to be, like, multifaceted. And it's like, no.

不。根本不会。你只需要专注一个人物，比如林登·约翰逊，深入挖掘他，为了解释清楚这个人，你就必须解释世界上所有其他相关事物。我太喜欢这种方式了。作为创作者，当我担心自己是否过于局限时，想到的就是这个道理。

No. No. You just pick one guy, Lyndon Johnson, and really get deep into him, you have to explain everything else about the world in order to explain him. And I I love that. And, like, as a creator myself, like, that's the thing that I think about when I'm like, oh, maybe I'm getting too narrow here.

就像是，不。不。专注其实是好的。你可以在专注中找到整个宇宙。

It's like, no. No. The narrow is actually good. You can find the entire universe in the narrow.

是的。对。对。对。我我说得再好不过了。

Yes. Yeah. Yeah. Yeah. I I couldn't have said it better.

对。好的。所以基本上，我现在看到的是，你在阅读那些你关心、想要学习的书籍时会使用Claude。你用它来稍微准备一下心态，为你即将阅读的内容做准备，我觉得这对难懂的书特别有用，或者在深入某个论点之前先思考一下。你在提问。

Yeah. Okay. So so basically, what I'm what I'm seeing right now is you're using Claude when you're reading books that you care about you care about, like, learning from. And you're using it a little bit to, like, prepare your prepare the mind your mind for, like, what you're about to read, which I think is particularly good for, like, difficult books or for, like, thinking through a particular argument before you, like, go through it. You're asking questions.

你在提问。所以它有点像是一个阅读伴侣。通过这种方式，你从所读的书中收获更多。但然后你会把你读到的内容扔进这个卡片生成器里。

You're asking questions. So you're kind of like it's a reading companion. You're getting more out of the books you read from that. But then you kind of take take your what you've read and throw it into this this card generator.

是的。所以那主要就是和Claude聊天。让我看看能不能找到一个更好的例子。我的意思是，很多话题我只是模糊地知道发生了什么，但并不真正理解。和Claude聊天非常有帮助，能确保我走在正确的轨道上。

Yeah. And so that's mostly it's just chatting with Claude. And so let me see if I can find a better example. So I mean, a lot of topics I just find I have a vague sense of what's happening, but I don't really like get it. And it's super helpful to chat with Claude to make sure I'm on the right track.

就像，Dylan有几篇关于为什么封装技术对这些先进芯片超级必要的帖子。我不是想让这个播客全都讲这个，只是碰巧这是我最近听的播客，所以你就听到了这个。但然后这是一系列令人困惑的、关于高级封装如何工作以及技术规格是什么的五篇帖子。我就想，等一下，退一步。

Was like, Dylan has a couple of posts about why packing as a technology is super necessary for these advanced chips. I'm not trying to make this podcast all about it harder. It just happens to be the last podcast I that's what you're getting. But then it's like a confusing, it's like a five series post about how advanced packing works and what the technical specifications are. And I'm like, wait, step back.

为什么这是必要的？发生了什么？还有各种各样其他问题，我担心在解释时可能会陷入太细节的地方。是的，基本上我就是想，我该如何思考这里发生的更广泛背景？因为除非我对他们在谈论什么有一个好的心智模型，否则我真的问不出好问题。

Why is this necessary? What's going on? All All kinds of other questions about I'm worried about where I might get too deep in the weeds when I'm just explaining. Yeah, basically I'm just like, how do I think about the broader context of what's happening here? Because I really can't ask good questions unless I have a good mental model of what they're talking about.

比如，我真的明白这一切是如何融会贯通的。

Like, I really get where all this fits together.

有道理。所以Claude就像是当你想要了解这些时首先会去查阅的东西。你是在手机上使用它还是在桌面上使用？

That makes sense. And so Claude is kind of like the first thing you flip to when you want to know that. Are you using it on mobile or are using it on a desktop?

桌面。

Desktop.

好的，有意思。所以你大部分阅读和研究工作都是在桌面上完成的？

Okay. Interesting. So you're doing most of your reading and research stuff on desktop?

是的，没错。

Yeah, that's right.

那你觉得Claude现在这么出色，像Chetch这样的工具呢？我猜你现在用Chetchy PT的频率比以前低了吧？

And what do you think about like just Claude being really great right now and like Chetch? Like I assume your Chetchy PT usage is lower than it used to be.

是的，我认为这些工具会随着时间的推移不断改进，而且我们正在逐渐习惯使用这些工具。我会稍微谈谈这些工具如何与我的后期制作流程相关联。起初它基本上没什么用，但我确实花了几个周末尝试写一些提示词并创建 workflow。那时候基本上没什么用。但现在它实际上变得有用了，我可以用同样的Jupyter Notebooks之类的工具来完成工作。

Yeah, I think these things will keep getting better over time and I I think we're just like getting in the practice of using these tools. I'll talk a little bit about how these tools relate to my post production process. Initially it was kind of useless, but I did spend a few weekends trying to write a few prompts and create a workflow. The time it was basically useless. Now it's actually ended up being useful and I can use the same Jupyter Notebooks or whatever to get things done.

所以即使它们现在运行得还不完美，也值得投入去获取，让它们成为你工作流程的一部分，这样随着它们不断改进，你就能从中获得回报。

So it is worth investing in getting, even if they don't work perfectly now to get them part of your workflow so that as they keep getting better, you're getting the returns from that.

是的，这很有道理。我想回到Anki卡片生成器，也就是间隔重复卡片生成器。作为这个过程的一部分，当你完成了所有概念上的梳理，让自己基本理解了嘉宾谈论的内容或你感兴趣的想法后，你就会添加到你的闪卡中，这样，我想，即使在你和那位嘉宾交谈之后，你也能保留这些信息。是这样吗？

Yeah. That makes sense. So I want to just go back to the Anki card generator, space repetition card generator. So as part of this, once you've done all the conceptual clearing the ground conceptually for yourself to kind of understand the basics of what a guest is talking about or an idea that you're interested in, then you're adding to your flashcards so that, I guess, so that you retain the information past even when you talk to that guest. Is that right?

是的，没错。我认为播客的更大使命在于，为什么播客会随着时间的推移变得更好？这是因为基本上我变得更聪明或学到了更多东西，我在减少对一系列话题的无知。如果我不这样做，我会想到在采访安迪并开始使用间隔重复之前所做的所有节目。

Yes, that's right. I mean, I think of the larger mission of the podcast is to why does a podcast get better over time? And it's because basically I'm getting smarter or learning more things. I'm reducing my ignorance around a bunch of topics. And so if I don't do that, I mean, I think about all the episodes I did before I interviewed Andy and started using spaced repetition.

我真的很后悔，因为我和所有这些不同领域的世界专家交谈过。说实话，在很多情况下，并没有带走太多东西。我模糊地记得一些事情。而现在，我使用的方法——我可以带你了解我制作的卡片类型和我使用的间隔重复工具——但这在我能保留的内容方面完全改变了游戏规则。事实上，我认为这甚至不是确保我记得之前节目讨论的内容或之前学到的东西。

And I just really regret it because I talked to all these world experts in a ton of different domains. To be honest, in many cases, didn't take that much away. I vaguely remember some things. And now that I use, I can walk you through the kinds of cards I make and the space separation tools I use, but it's totally a game changer in terms of what I can retain. And in fact, I think it's not even about making sure I remember what I discussed in a previous episode or what I learned previously.

这更多是关于未来的学习，因为我肯定你听过学习是复合增长的说法，因为你可以利用过去学到的知识来学习未来的东西，因为它们都是相互联系的。但如果你基本上忘记了过去学到的大部分东西，你就无法做到这一点。所以，我对未来其他事物的学习变得快得多，因为我缓存了所有这些不同的概念、数据和事实。因此，未来的学习就像是，我更理解一切是如何组合在一起的。这甚至与过去无关。

It's more about future learning because I'm sure you've heard the saying about learning compounds because you can use what you've learned in the past to learn future things because they all interconnect. Well, you can't do that if you basically forgotten most things you've learned in the past. So my learning has been for future other things has become much faster because I have cached all these different concepts and figures and facts. So the future things are just like, I understand how everything sits together much more. It's not even about the past.

这真的关乎未来的学习。

It's really about future learning.

我们能看看你的——我不知道你用什么来做间隔重复——我们能看看你的卡片组吗？

Can we see your, I don't know what you use for first base repetitions. Can we see your deck?

是的。顺便说一下，我要指出Claw的一个实际应用场景，结果证明还挺有用的。有时候你会读到一些晦涩难懂的东西。我当时在读尼克·兰德关于人工智能和他加速主义思想的选集。我就在想，这到底在说什么？

Yep. I will point out, by the way, as a side note, one use case of Claw that ended up actually being pretty useful. Sometimes you read obscure for lot. I was reading Nick Land's selected writings about AI and his accelerationism. And I was like, what's going on?

真的，我就在想，他的核心论点到底是什么？为什么他认为人工智能接管人类以及它在'后果'中创造的东西会是好事？因为他是个聪明人，我猜他肯定有有趣的论证。所以我就上传了他选集的PDF文件。

Genuinely, I'm like, what is his argument basically? Why does he think that the AI takeover and whatever thing it creates in Aftermath will be goo? Because he's a smart guy. I'm assuming he has an interesting argument. So I upload a PDF of his selected writings.

我就直接问Claude：好吧，那他为什么认为AI接管人类是件好事？它给出了一个摘要。这倒不一定特别有帮助，因为我在文章里已经读过了。但有用的是，当我继续追问，比如回应说'我还是不明白。他认为人类社会到底有什么问题，以至于必须彻底抹除？'

I just ask Claude, Okay, so why does he think it's a good thing that AIs take over humans? It offers a summary. This isn't necessarily that helpful because I kind of did read this in the essay. But what's helpful is that when you go through and I respond like, I don't get it. What does he think is wrong with human society that you have to erase it?

然后它给出解释，我还是说'我还是没懂。这里具体在讨论什么？'就像我做播客时那样，对吧？我请来嘉宾然后问他们：你这里是什么意思？比如，我不同意这个观点。

And then he gives an explanation and I'm like, I still don't get it. Like, what exactly are talking about here? And then like, here's what I do with the podcast, right? I have the guest on and I ask them, what do you mean here? Like, I disagree.

这里有个矛盾，诸如此类。通过用Claude梳理他们的著作，我实际上是否发现了他们思维中的某个盲点，还是只是我自己对他们的想法感到困惑？这真的超级有帮助。

Here's a contradiction, whatever. And going through their writings with Claude and like, have I have I actually found a sort of blind spot in their thinking, or is this just me being confused about their ideas? It's super helpful.

这确实很有趣。就像你可以在和他们交谈之前就深入到一个更深的层次，这样你就可以从那里开始，而不是从表面开始。

That's that is really interesting. It's like you can you can get you can get down to a deeper level before you talk to them so that you can start there with them as opposed to, like, starting at the surface.

没错。

Exactly.

这真的很酷。我也用它来处理一些难懂的书，不一定是为了采访那些书的作者，但比如，我大概一两个月前采访了里德·霍夫曼，我想和他谈谈哲学与人工智能之间的交叉点。他几乎成了牛津大学的哲学教授，对维特根斯坦非常着迷。所以我就读了一些维特根斯坦的书，我已经很久没读过了。

Which is really cool. I I use that too for, like, for for difficult books, like not necessarily for, like, interviewing the author of those books, but, like, for example, I I interviewed Reid Hoffman, like, don't know, month or two ago, and I wanted to talk to him about the kinda, like, intersection between philosophy and AI. And he was like he he, like, almost became a a philosophy professor, like, at Oxford. Wanted like, was really deep into Wittgenstein. So, like, I read a bunch of Wittgenstein, which I hadn't read in a while.

我就用了Claude来处理，效果真的好多了，因为我没上过维特根斯坦的课，或者可能大学时上过一门，但那是很久以前了。我读过他很多书，但总是会有一些地方让你觉得，我大概明白他们在说什么，但可能得去读个研究生、拿个硕士学位才能真正搞懂。而Claude实际上让我觉得，哦，我不再需要那样了。任何我想读的这种书，我基本上都能懂了。这在那次采访中帮了我大忙，因为我可以提出非常深入的维特根斯坦相关问题，而他也能回答。

And I I just used Claude for it, and it was, like, so much better because I'd like, I haven't taken a Wittgenstein class or maybe I took one in college, like, a long time ago. But I've read him a lot, and it just there are always these those points in those kinds of books where you're like, I think I I know what they're saying, but, like, I'd probably have to go to a a grad graduate school and, like, get a master's in this to, like, really know. And Claude is actually like makes me be like, oh, I don't need that anymore. Like, I any book I wanna read like this, like, I basically know. And it just helped me so much in that in that interview because I could just ask, read, like, really deep Wittgenstein related questions and he could answer them.

是的，是的。我觉得这完全合理。有些人可能会说，哦，你得读原版 blah blah blah。但如果你关心的是思想，并且认为这些思想是永恒的，而不是关于原作者使用的特定散文风格，而是一般性地关注这里发生的本质和要点。

Yep. Yep. I think that's totally legitimate. I think some people would be like, oh, you need read it in the original blah, blah, blah. I think if you care about the ideas and you think the ideas are timeless and not the ideas are not about the specific kind of prose that the original author used, but just generally like what is the essence and the gist of what's happening here.

如果你关心的是思想，我觉得这完全有效，对吧？我并不同意那些说‘不，你得读维特根斯坦用的特定音节’的人。

If you care about the ideas and I think this is totally valid, right? I don't disagree with the people who are like, no, you need to read like the specific syllables that Wittgenstein used.

是的。我的意思是，我也只是说，我打开书，然后拿出他的一句话扔进去，然后它就会告诉我这是什么意思之类的，我觉得这真的很棒。好了，你要给我们看那个间隔重复卡片了。

Yeah. I mean, I'm also just saying, like, I'm I have the book open, and then I just take one of his, like, statements and just throw it in there. And then it's like, here's here's what it what it means or whatever, which which I think is really great. Okay. So you're gonna you're gonna show us the, the the spaced repetition card.

那么这是什么应用？

So what what app is this?

这是Mochi。挺有意思的。它像Anki，但这是我用的那个。怎么了？其实我今天没有任何卡片，因为我今天早上刚复习完。

This is Mochi. Interesting. It's like Anki, but this is the one I use. Why? So actually I don't have any cards today because I just went through them this morning.

但让我给你介绍一下我有哪些内容，好吗？回顾历史，最近我计划采访大卫·赖克，他是一位研究人类起源的遗传学家。这些情况特别容易像读书一样被完全遗忘。他列举了所有这些不同的祖先群体，以及它们如何结合、在哪个时代结合。亚玛纳人是什么时候穿越欧洲的？

But let me give you a sense of what kinds of things I have, right? So if you go through history, recently I've been planning on interviewing David Reich, who is a geneticist who explores human origins. And these are especially cases where just like reading the book, I'm like, would have totally forgotten. He names all these different ancestral groups and how they combined and in what eras. When did the Yamana people come through Europe?

安纳托利亚的狩猎采集者是什么时候席卷欧亚大陆的？所有这些内容，你读了一遍就会从另一只耳朵出去，除非你为它们制作卡片。所以我为这类内容制作了大量卡片。这里就有一些例子。这对硬件和技术类内容尤其有用。

When did the Anatolian hunter gatherers wash over Eurasia? All these things that were just like you read it in one year goes out the other one unless you make cards for it. And so I made a ton of cards about this kind of stuff. There's examples of that here. It's especially useful for hardware and technical things.

所以在这里，我觉得如果不制作卡片，我就会不断重新学习相同的内容，因为我一开始没有以正确的方式学习术语。不仅仅是学习术语，更是理解底层概念。让我给你举一个好例子。也许我会退一步，解释一下我早上如何复习这些卡片。你可以看看如果我做突击卡片会是什么样子。

So here I feel like if I don't make cards, I'm just constantly relearning the same things because I didn't learn the lingo in the right way first. It's not just about learning the terminology, it's about understanding the underlying concepts. Let me give you a good example of that. So maybe I'll step back and I'll explain like I go through these cards in the morning. You can see what it kind of looks like if I did a cram cards thing.

请看。我可以浏览它们，现在我就想，记得这个，对吧？我记得这是随机出现的第一个，但它是多查询注意力，以避免使用巨大的键值对，然后在层之间共享键值对并使用局部注意力。这就是答案。现在看起来似乎有点琐碎，因为它只是三件事。

Please. I can go through them and right now I'm like, remember this, right? I remember it's this is the first one that came up randomly, but it's multi query attention to not have to use huge KV values and then sharing KV values between layers and using local attention. And that's the answer. Now, it seems sort of trivial right now because it's just like three things.

但如果没有在读到博客文章后立即制作卡片，我肯定会完全忘记这个。然后就像在未来浪费了时间，如果我在不同背景下学习这些技术，我就无法将这里发生的事情联系起来，对吧？如果我切换到另一个类别，比如突击卡片，就是这个白色的东西。如果没有制作这些卡片，我肯定会完全忘记它。是的，我现在是个超级粉丝。

But I would have totally forgotten about this if I hadn't made a card for this as soon as I read the blog post. And then it just like I've wasted my time in the future if I'm learning about these technologies in a different context, I just don't have the connection to what was happening here to connect it to, right? If I go to a different category, if I go cram cards, this is the white thing. I would have totally forgotten about it if I hadn't made these cards. Yeah, I'm just a big fan right now.

我最近有点变成了间隔重复的狂热爱好者。

I sort of I've become a space repetition fanboy these days.

在一个几乎所有这些问题都可以通过像Claude这样的工具一次搜索就能回答的世界里，你是如何看待间隔重复的实用性的？

How do you think about like the usefulness of space repetition in a world where like any of these questions is possibly is like pretty much answerable, like with Claude with like a one search?

是的。所以我认为重点不在于必须记住这些信息，而是当未来遇到相关事物时，你能理解其中的概念。实际上，让我给你举个很好的例子。我记得有时候我会制作一些关于当下并不理解的事实的卡片。但随着我对这个领域了解加深，随着某个知识版图逐渐清晰，卡片上记录的内容在未来会让我更加明白。

Yes. So I think it's about not necessarily remembering this information, but when a future thing comes in, you understand like the conceptual. In fact, let me give you a good example of this. So I remember sometimes I actually make cards about facts that I don't even understand in the moment. But in the future, as I learn more about the field, as a sort of territory becomes more clear, the things I said in the card make more sense to me.

当时我正在阅读Colin Burns的一些论文。于是我制作了这张卡片，内容是关于Colin Burns为何认为对齐是个可解决的问题，或者理解模型认为什么是可解决的问题。当时我写下了一些内容，比如特征存在于线性空间中。这是什么意思？或者比如我们可以在其他类别的范畴中看到特征。

I was reading some of Colin Burns papers. And so I made this card about like why Colin Burns thinks that alignment is a tractable problem or understanding what model thinks is a tractable problem. And at the time I wrote things down about like features are in a linear space. What does that mean? Or like we can sort of see features in other sorts of categories.

当时我就想，我完全不明白这是什么意思，但既然读了博客文章，不做卡片就白读了，所以还是记下来。后来，随着我更多了解了注意力机制的残差流模型及其原理，这张卡片在未来变得更有意义。但如果没有制作这张卡片，我可能完全记不住，甚至彻底忘记这些需要未来理解才能消化的内容。当我在未来再次看到这张卡片时，我就会恍然大悟：原来Colin Burns是这个意思。既然现在我理解了注意力机制的工作原理，这就说得通了，对吧？

And at the time I'm like, I have no idea what this means, I'm just going to write it down because I read the blog post and there was no point of reading the blog post if I'm not going make the card. Later on, as I learned more about how the residual stream model of how attention works, what that is and so forth, this card made much more sense to me in the future. But I would have just totally memory hold or not even memory hold, I would totally forgotten this content, which required future understanding if I hadn't made a card of it. And then when I see the card again in the future, I'm like, Oh, this is what Colin Burns meant. Now that I understand how attention works, this is what it means, right?

是的。这对我来说真的很有趣。我想深入了解你使用AI进行面试准备的一些方法，因为我觉得我们主要讨论了阅读方面。但在那之前，我想先理解驱动这一切的动力是什么？感觉你就像在大量吸收信息，并将其转化为头脑中的知识。

Yeah. This is this is really interesting to me. So I I wanna get into some of the, like, the ways that you use AI for for interview prep because I think we we've mostly covered the reading stuff. But before we do that, I just wanna understand what is driving all of this? It feels like you are just consuming massive amounts of information and turning that into knowledge in your head.

你有一种超乎寻常的好奇心，这一点我其实深有共鸣。我现在周围全是书。我只是好奇，你觉得这种动力源自什么？

You have this sort of overdrive just of curiosity, which I actually resonate with a lot. I'm surrounded right now by books. And I'm just sort of curious for you what do you think that's about?

我想我可能只是想知道所有事情吧？不知道该怎么表达。威尔·杜兰特在90岁时写的回忆录《落叶》中有段关于哲学的精彩段落，他说：随着年岁增长，或许凭借所有钻研过的哲学和历史，我已经达到了更高理解力和更清晰洞察力的平台，或者至少我明白了这种境界是可能存在的。类似这样的想法让我很有共鸣。

I think I really just want to know everything, right? I don't know how to express it. There's a beautiful passage in a Will Durant book as he's turning 90, where he's writing a memoir basically of his main ideas called Fallen Leaves. And there's a passage on philosophy where he says, as you get older, maybe with all the philosophy and history I've done, I can I've reached some plateau of higher understanding and clearer insight, or at least I've understood that such a thing is possible. And something like that just resonates with me.

说不清楚。就是觉得这个理念非常吸引人。虽然我还远未达到那种境界，但希望在未来几年里也能如此。我也非常钦佩那些拥有自洽且经过深度审视的世界观的播客嘉宾，比如Karl Schulman、Tyler Cowen或Bern Hobart这些人。感觉他们真的无所不读，而你所知道的一切都只是他们知识体系的子集。

I don't know. Just like I find that idea really appealing. I'm nowhere close to it, but I just hopefully in the years to come, that'll just be a thing that I also really admire people I've had on the podcast who do have these self consistent and really deeply interrogated world models. You know, I've interviewed these guests and some of them, couple of names come to mind, people like Karl Schulman or Tyler Cowen or Bern Hobart. It feels like they've really read everything and everything you know is a subset of what they know.

我只是觉得，作为思想家，他们极具吸引力。当然，他们可能还有很多错误之处。我不是那种盲目崇拜者，认为有人无所不知、永远不会犯错，对吧？每个人都有自己的盲点。但当你与他们交谈时，你能看到他们那种能力——将你提出的任何话题都联系起来的能力。

And I just, I find them to be super compelling as thinkers. Of course, there's many things they can still be wrong about. I'm not one of these bull buys like, there's like a thing where you just know everything and you can never be wrong, right? You always have blind spots. But their ability to, which you can see when you talk to them, to connect anything you ask them about.

他们就像万能钥匙一样，比如你开始讨论为什么金融占GDP的比例会是这样？我记得问过泰勒这个问题。他立刻就能给出一个非常有趣的答案，融合了多个不同学科的知识。你问卡尔人工智能硬件能发展多快，他就能进行费米估算，涉及藻类繁殖速度、太阳能消耗量以及CSMC芯片的制造速度。我觉得这是他们一生中吸收的信息经过高度压缩的体现。

And they're like a claw to six in the sense of like, you start talking about why has a fraction of finance as a percent of GDP? I remember asking Tyler this. And he has a right off the cuff, just a super interesting answer that connects a bunch of different disciplines. You ask Carl about like how fast AI hardware could grow and just done this sort of Fermi estimates on how fast algae bloom and how much solar power they consume and how many fast CSMCs make. I find that sort of compression of the input they've ingested over their lives.

他们不仅知道这些知识，还能以非常有趣、引人入胜的新颖方式将其联系起来。我觉得这特别吸引人。

Not only do they know that stuff, but they can really connect it in a really interesting and compelling novel way. I find it super compelling.

在构建你自己的世界观方面，你有没有在创建某种活文档，还是说所有学到的内容都只存在脑子里？显然你有知识卡片，但那感觉更像是空间中的散点，而不是它们如何相互连接以及你如何将一切作为一个整体系统来思考。

And in terms of developing your own worldview, do you have that anywhere where it's like you're creating some sort of living document, or is it just all in your head, all the stuff that you're learning? Obviously, have the cards, but that feels more like dots in the space rather than the ways that they all connect and how you think about everything altogether as a system.

我觉得最近我在尝试多做这类事情。由于播客节目，我可能已经积累了一定的基础词汇或理解，现在做更多这样的事情是合理的。最近我做的一件事，让我找出来看看。我才刚开始，希望人们看到这个时会有更多内容，但我已经开始就不同的书籍或阅读内容写一些即兴思考。基本上都在我的网站上。

I think I've been trying to do more of this recently. And now that I've sort of built up an underlying maybe vocabulary or understanding because of the podcast, it makes sense to do more of this. One thing I've been doing recently, let me pull this up. I've only just started, hopefully there'll be more by the time people are looking at this, but I've started writing riffs on different books or things I read. And if I go to, it's basically on my website.

就像我读一本书时会产生问题，或者把它与我读过的其他内容联系起来。我记得，比如史蒂芬·平克的《语言本能》，他写这本书时还没有发现能解释人类语言的FOXP2基因。所以他当时的所有观察后来都被FOXP2基因解释了。通过对他人的观点进行即兴发挥，我就能做到你说的那种联系。我其实很好奇。

And so just like I can read a book and I have questions or I connect it with other things I've read. I remember, for example, Stephen Pinker's Language Instinct, he was writing the book before the FOXP2 gene that can help explain human language was found. And so he has all these observations that are then later explained by the FOXP2 gene. And so I can just sort of, the sort of connection that you're talking about I can do by riffing on other people's ideas. I actually am curious.

你对我应该做什么有建议吗？也许我应该多写博客文章？你建议我该怎么做？

Do you have suggestions on what I should be doing? Maybe I should be writing more blog posts or what do you suggest I should do?

嗯，这是个好问题。在我们深入之前，这让我想到一件事，我认为Claude非常适合阅读旧科学书籍，因为它能告诉你哪些内容过时了哪些没有。我经常这样做，特别喜欢这个小功能。但总的来说，我认为形成世界观就像是你必须不断尝试。你需要反复尝试，一次又一次。

Well, that's that's a good question. So well, before before we get there, like one of the things that this reminds me of it, I think Claude is so good for reading old science books because it can tell you what's outdated and what's not. I do that all the time, and I love that little thing. But yeah, I think basically developing a worldview is like you have to just try. And you try over and over and over again.

我确实认为博客文章对此很有帮助，尤其是我必须每周写作。这迫使我对某些事情形成观点。一般来说，如果你在知识上保持诚实，你会希望每篇文章都与前一篇有所呼应，如果你的观点总是自相矛盾，读者会指出来的。通过这种方式，你就在逐渐构建自己的世界观。但对我来说，这个季度的重要任务是，我有一些正在酝酿的想法，关于语言模型与一些深奥哲学问题之间的关系，这些问题是自柏拉图时代以来我们一直在讨论的，比如表象与现实的区分，我们如何知道什么是真实的，什么是知识等等。

And I do think blog posts are really good for that, especially for me, I have to write every week. And so I'm forced to take a view on something. And generally, if you're intellectually honest, you want one post to somewhat agree with the last post, and your audience will call you out if you're just disagreeing with yourself all the time. So you're kind of developing a worldview that way. But for me, right now, I'm actually my big thing this this quarter is, like, I I just have these, like, ideas that are simmering that are, like, sort of the relationship between, like, language models and, like, some deep philosophical questions that we've been, like, talking about since, like, Plato, which is, like, the appearance reality distinction and how do we know what's true and what's knowledge and all that kind of stuff.

我认为这其中有很多重叠之处，需要写一篇万字长文之类的。所以我正在做的是创建一个Claude项目，里面有所有这些零散的笔记和想法，然后我就可以去问Claude：这里的线索是什么？发生了什么？你能帮我理清思路吗？我内心有很多小想法，但还无法将它们整合成一个完全合理的论证。

I think there's a lot of overlap there, and it requires it's gonna be a 10,000 word post or something like that. And so what I'm doing is I just have a Claude project with, like I have all these, like, little notes and riffs and, like and stuff, and I'm just, like, going into Claude and being like, hey. Like, what's what's the thread here? Like, what's going on? Can you help me, like, figure out, like there's something in me that I have all these little ideas for, but I can't quite put it into an argument that all makes sense.

说实话，我认为只要花几个月时间深入思考，我就能弄清楚里面到底有什么。但确实有些东西在里面。是的，这很酷。

And I think just honestly, sitting with that for a couple months, I will know what's in there. But there's something in there. And yeah, it's cool.

你会不会创建一个Claude项目，比如'这是我正在思考的一些事情，它们之间有什么联系？'或者你是如何在几个月的时间里跟踪这些想法的？

Do you do you make a Claude project to like, here's some of the things that I'm thinking, how do they connect? Or like, how do you keep track of those things as you over those months?

没错。我可以给你看看。让我调出来。好的，如果我进入Claude，我有几个不同的项目。

Exactly. I'll I mean, I'll just show it to you. Let's let me just pull it up. So okay. So if I go into Claude, I have a couple of different projects.

一个项目是《像语言模型一样看待》，这是那篇长文的标题，不管它最终叫什么。另一个是《禅与摩托车维修艺术》。这是我为正在写的这篇文章做准备而读的一本书。我以前读过很多次，但现在正在进行更深入的阅读。我把整本书都上传了，然后可以提问。

One project is Seeing Like a Language Model, which is the title of this big post, whatever it is. Another is Zen and the Art of Motors Maintenance. So this is like a book that I'm reading as prep for this this piece that I'm writing. I've read it a bunch of times before, but, like, now I'm, like, doing a little bit of a deeper read. And so I have, like, the I have the the whole book uploaded, and then I can, like, ask questions.

然后我还有另一个很喜欢的笔记叫'我的心理学'，里面有很多类似日记的条目、我多年来为自己设定的目标，还有我对自己心理学的观察或正在努力改进的地方，以及我希望成长或改变的一些小方面。所以当我在做决定或思考问题时，我就会去查阅这个笔记，它可以参考所有这些内容，从而了解我是谁，这真的很酷。所以看到语言模型让我看看能不能在项目目录里找到它。基本上，我在苹果备忘录里有一个笔记，每次脑子里冒出一个小想法，我就会直接把它记在里面。让我看看能不能为你找到它。

Then I have another one that I love called My Psychology, which has a bunch of, like, journal entries, goals I've set for myself over the years, and then also things I've observed about my psychology or things I'm working on, little aspects of myself that I'd like to grow or change. And so when I'm making decisions or thinking something through, I just go in there and it can reference all that stuff so it knows who I am, which is really cool. So in seeing like a language model let me see if I can pull it up in the projects directory. So I have like, basically, I have this one note in Apple notes, which is, like, every time I have a little thing come into my head, I'm like I just I just put it in there. Like, let me see if I can find it for you.

我就把这些都扔在这里。这个笔记又大又乱，里面有来自不同书籍的各种引用，还有我四处走动时突然想到的各种想法。我觉得所有这些内容中有一条主线。我能看出它们都是相关的，但就是无法完全提炼出来。所以我一直在做的就是把这些全部扔进去。

I just throw it in here. And this is, like, huge and messy, and it's, like, different quotes from different books and, like, just different ideas that, like, come to me off the top of my head as I'm, like, walking around. And I think that there's a thread here in all of this stuff. They're all I can see how they're all related, but I can't quite pull it out. And so what I've been doing is I just throw it all throw it all in in here.

我们这里有所有的引用、想法和片段。我还有一个草稿，类似引言部分。然后我有一章理查德·罗蒂的书，我觉得非常棒，叫做《实用主义作为反权威主义》，这章内容某种程度上引发了整个思考。我读了那章之后，突然又开始重读柏拉图和亚里士多德，然后就陷入了这个巨大的兔子洞。

We have this all the quotes and all the ideas and fragments. I have a little bit of a draft, like an intro. And then I have a chapter of a book by Richard Rorty that I think is is really good called Pragmatism as Anti Authoritarianism that kind of sparked this whole thing. Like, read that. I read an r I read a chapter of that book, and then I was suddenly rereading a bunch of Plato and Aristotle, and I was just down this huge rabbit hole.

举个例子，我做的就是把所有这些东西都放在这里，然后说：嘿，我有一堆笔记和一些文本片段，想写一篇约1万字的长文，叫做《像语言模型一样看世界》，但在开始之前，我需要理清自己的真实想法并制定一个大致提纲。为此，我需要理解我一直在思考、记录和阅读的内容模式。你能建议一些方法来帮助我做到这一点吗？我想从现状出发形成一个提纲。你可以访问一些片段，注意到一个早期未完成的引言。

And so what I did, for example, is I put all that stuff in here, I was like, hey, I have a bunch of notes and some fragments for of text for a long 10,000 ish word piece I wanna write called seeing like language model, but I need to understand what I actually think and make a bit of an outline before I get started. In order to do that, I need to understand the patterns of what I've been thinking and writing down and reading about. Can you suggest some ways that you can help me do this? I wanna get from where I am to an outline. You have access to some fragments, notice an early unfinished intro.

它只是包含了很多想法，主题分析或论证映射或时间顺序发展。我正跟着它深入探索这个兔子洞，比如我让它做概念聚类。所以我正在探讨的一个概念是哲学分歧，柏拉图对亚里士多德，我觉得这不太准确。实际上是柏拉图对智者派，但很接近。或者是西方思想的演变。

And it just has a bunch of ideas, thematic analysis or argument mapping or chronological development. And I'm just sort of going down the rabbit hole with it where it's like, I asked it to do concept clustering. So it's like one of the concepts that I'm playing with is the philosophical divide, Plato versus Aristotle, which I think is not quite right. It's actually Plato versus the Sophists, but it's close. Or the evolution of Western thought.

就像是，柏拉图如何融入西方思想的其余部分，融入科学，以及西方思维方式的运作？然后语言模型与那个范式有何不同？这就是我正在尝试的基本思路。我之所以问这个问题，是因为我有点自私地觉得，我没有像真正想要的那样多做那种大思想的探讨，因为我每周都在写作，更像是在对事物做出反应。

It's like, how does Plato ladder up into the rest of Western thought and into science and just the way the Western mind works? And then how do language models differ from that paradigm? So that that's the that's the basic thing that I'm trying for. Because I I I I do have the reason I ask this question is because I'm selfishly like I feel like a little bit I haven't done the, like, big idea thing as much as I really want to because I'm I am writing every week. I am sort of, like, reacting to stuff.

所以我想要更加深思熟虑一些。这就是我尝试把所有内容整合成某种有意义的东西的努力。

And so I wanna be a little bit more thoughtful. And this is this is my, like, attempt to do, like, to put all of it together into something that, like, makes sense.

是的。你知道吗，当你经历这个过程时，这实际上让我更想多写点东西了。因为现在你谈到这个，现在你提出这个问题，我就想，是的，我应该把我学到的东西以更全面的方式整合起来，同时也要让这些内容对其他人更有用、更容易获取，对吧？我花了好几周时间研究一些随机的——也不算随机，而是我关心的事情。我正准备研究丹尼尔·尤尔根，就是写《奖赏》的那个人。那是一本石油史的书，或者是一位遗传学家，你知道的，AI研究员之类的。

Yeah. You know, as you're going through this, this really actually makes me want to write more because now that you're talking about it, now that you ask the question, I'm like, yeah, I should be sort of consolidating the things I'm learning in a more comprehensive way and in a way that's also more useful and accessible to other people as well, right? I spend weeks learning about some random, not random, but like the things I care about. I'm about to prepare for Daniel Jorgen, the guy who wrote the prize. It's a history of oil or a geneticist, know, AI researcher or whatever.

既然我从这些研究过程中有所收获，就应该以播客本身不明显的方式将其整合起来。

To the extent that I'm getting something out of these research processes, should consolidate it in a way that's not evident in the podcast itself.

是的。我的意思是，我自私地希望你能这样做，因为我很好奇你的想法。

Yeah. I mean, I selfishly want you to do that because I'm curious what you think.

是的。我很感激。你会通过你的通讯发送这个对吧？这是主要的方式吗？

Yeah. I appreciate that. You will send this out through your newsletter. Right? Is is that the main way I will.

嗯，是的。

Yeah. Yeah.

这个会通过通讯发布。我可能会为此做些特别安排，比如，你知道，也许等它发布时我们会为它做一个小型专题页面，但那是将来的事了。我得先真正把它写出来。所以好吧，那我们继续吧。

This will this will go through through the newsletter. I might do something special for it, like, you know, maybe we'll maybe we'll make a little mini site for it when it when it launches, but that's sort of in the future. I have to actually I have to actually write it first. So okay. So so so let's I wanna move on.

我想谈谈你是如何使用AI来做采访准备的。那我们进入这个话题吧。然后我们甚至可以一起为一次采访做准备。

I wanna I wanna talk about the how you how you use AI to do the interview prep. So let's move into that. And then we also maybe even prep for an interview together.

是的。好吧，我们开始吧。说实话，面试准备需要很多工作，但本质上并不复杂。比如我可以直接给你看我过去可能做过的文档。我来共享屏幕。

Yeah. Okay, let's do it. Honestly, the interview prep is like it requires a lot of work, but fundamentally what's happening is not that complicated. Like I can just show you a document I might have made in the past. I'll share my screen.

所以老实说，其实就是我整理出一堆问题，然后把它们按相关主题分组。或者如果我要采访迪伦·帕特尔，抱歉，这个不对。有各种不同的，对，基本上就是个问题清单。并不复杂。但构思这些问题的过程需要大量研究。

So honestly, literally is just like I'm going through, I come up with a bunch of questions and I sort of group them together in relevant categories. Or if I go to, if I was interviewing Dylan Patel, I'm sorry, this is not the right one. There's like a bunch of different, yeah, it's just like a list of questions basically. It's not complicated. But the process of coming up with them is very research intensive.

所以我们可以看看，如果我算是勉强在准备的话。可以走一遍准备的过程。

So we can go through like if I'm guess I'm like only barely sort of preparing for them. Can go through the process preparing for them.

是的。我们能不能——我自私地想先停留在那些问题上，因为我觉得这真的很有趣。你这些按主题整理的长问题清单，你是按顺序问下来，还是会跳着问来深入探讨？

Yeah. Can we I just want to stop at those questions like again selfishly because I think it's really interesting. Like you have these like long lists of questions that are organized by theme. Are you like going down the list or are you sort of jumping around to bend down?

是的，这很有趣，因为我虽然列出了这些问题清单，但实际采访中从来不是按问题一、二、三的顺序问。我会从一个有趣的问题开始，如果你听过采访，希望它听起来更像对话，因为我准备得太充分了，基本上把这些问题都记熟了。然后根据他们的回答，如果提到LLM中的记忆化，我就会接着问一个准备好的相关问题。这样衔接更自然。这份清单就是如果他们问起我会发给他们的。

Yeah, it's really interesting because I come up with these lists of questions, but it's like it really never ends up being I ask question one and I ask question two and I ask question three. I start off with an interesting question and if you listen to the interviews, hopefully it comes off more as almost conversation because I spend so much time preparing that I have these questions basically memorized. And so the next one that is appropriate to their response, if they say something about memorization in LLMs, I'll have a question prepared about that or related to that. And I'll just ask them next because that's what fits in together. And so I'll have a list and this is what I'll send them if they ask for it.

但实际上，在真实采访中，我更多是即兴发挥，记得哪个问题相关就问哪个。

But really, it just sort of me off the cuff, like here's a question I remember that was relevant to this in in the actual interview.

有道理。所以制作文档的过程本身就是准备，面试时甚至不一定需要它。可能只是备着以防万一。对，这样解释就很合理了。是的。

That makes sense. So like the the point of the doc is like it's almost like writing the doc is is the prep itself, and it's don't even necessarily need it in the interview. Like, maybe you have it just in case. But, yeah, that makes a lot of sense. Yeah.

然后呢，是的，甚至可以安排，让我看看，我接下来有几个采访。大卫·赖克和丹尼尔·尤金。前者是研究人类起源的遗传学家，后者写了《奖赏》，那本关于石油历史的著名著作。你觉得哪个听起来更有趣？

And then, yeah, can even go through, let's see, I'm doing a couple of interviews in the future. David Reich and Daniel Juergen. So former is a geneticist about human origins. The second wrote The Prize, which is the famous book about the history of oil. Which one sounds more interesting to you?

我们可以做任何一个，随便选。

We can do that, whichever one.

我想选那位著名的遗传学家。

I want to do The Famous Geneticists.

那就用Claude吧。实际上，我确实把他的书作为项目上传了，我们可以直接使用。

So let's go to Claude. In fact, I I I do have his book uploaded as a project, so we can just use that.

太好了。那么，基本上我们要做的是，我们会观看你，我也会和你一起准备。我们要为采访这个人做准备。他叫什么名字

That's great. And so, basically, what we're gonna do is, like, we're gonna we're gonna watch you, and I'll I'll do it with you. We're gonna prep for an interview with this guy. What's his name

再说一遍？大卫·赖克。

again? David Reich.

好的，酷。我们能了解一下大卫·赖克的背景吗？也许我们可以问问Claude，因为你知道，显然我对大卫·赖克还是个新手。所以

Okay, cool. Can we get like a little bit of background on David Reich? Like maybe we can even ask Claude because like I'm, you know, obviously I'm a newbie to David Reich's So

他是哈佛大学的遗传学家，在过去十年左右的时间里，他们的研究聚焦于世界范围内人类种群是如何形成的？基本上就是，欧洲人是谁？由哪些群体构成？哪些古代迁徙、种族灭绝和人口替代塑造了他们？对印度人、美洲原住民或非洲人的研究也是如此。

he is a geneticist at Harvard and over the last decade or so, their research into how have human populations across the world been formed? Basically, who are the Europeans? What groups make them up? What ancient migrations and genocides and population replacements made them? Same with the Indians or Native Americans or Africans.

这完全改变了现状。我的意思是，他们基本上让许多学科变得无关紧要，因为他们拥有实证数据，比如历史上实际发生的情况。你们对历史的猜想和理论完全错了。如果你熟悉纳夫·弗里德曼的Ysouvist挑战，就像有些被吐出来的松鼠，但通过先进技术你能从中提取有用信息。我觉得这是类似的思路。

It's completely changed. Mean, they've basically sort of like made many academic disciplines irrelevant because they actually have empirical data on like, here's actually what historically happened. You guys are completely wrong about what you think, your theories of what happened. If you're familiar with Naft Friedman's Ysouvist challenge, you like you have these like burped up squirrels, but with some advanced techniques, you can get some useful information out of them. I feel it's in a similar vein.

显然这不是同类型项目，但类似的是——一旦我们发展出先进的数学或遗传学等技术来解读基因组中潜藏的信息，就能基本揭示人类历史上大量未被发现的真相。抱歉，我有点陷入极客模式开始滔滔不绝了。但有趣的是，你能看出一个种群替代另一个时，究竟是我们相遇后融合、贸易往来，还是我们在对你们实施种族灭绝？通过遗传证据可以判断：如果是种族灭绝或人口替代，入侵族群的父系血统会取代原住民的父系，而母系血统则会保留下来。

Obviously they're not the same kind of project, but like in a similar vein of like once we develop the advanced mathematics or genetics or whatever to understand what's latent in the genome, just uncovered a ton of insight about what's been going on in human history basically. And I'm sorry, I'm just going to getting nerd snipe and just going on riffs here. But like, well, one of the interesting things is you can see when one population replaces another, whether it was just like, oh, we met and like we were like now intermingling and trading and whatever. Or is it like we're committing genocide against you? And you can tell that because in the case where it's genocide or population replacement, it will be that the male line of the population that is invading will overtake the male line of the existing population, but the female and bovine will remain.

因为线粒体DNA只通过母系遗传，你会看到母系血统得以保留——新来的男性会娶她们为妻。总之，通过这种方式可以了解入侵的性质：是征服还是融合？这是DNA能揭示的众多信息之一。

So mitochondrial DNA only comes up in the female line and you'll see the female line because they're getting the new men who are coming in are taking them as wives or something. And then the anyway, so you you can just, like, learn a lot about, like, what kind of invasion was it? Did they, like, conquer or was they were they just, like, mingling or something? One of the many things you can see from the DNA.

这真的很有趣。等等，所以这基本上是通过重新检验古代聚居地的DNA证据，并且他开发出了新的DNA分析方法？他们是用什么新方法从现有证据中得出新结论的？

That's really interesting. Wait. And so so this is, like, basically reexamining DNA evidence of, like, old settlements and like basically and he's uncovering new ways of being able to analyze the DNA. Like what's the new methods that they're using to like draw new conclusions from existing evidence?

其中一种就是刚才说的Y染色体和线粒体DNA分析——通过追踪父系和母系传播方式，可以了解种群的社会结构等。另一种甚至能判断社会不平等程度：例如在印度，最令人惊讶的是内婚制程度——某个村庄的特定种姓完全不会与邻村其他种姓通婚，这种隔离程度在世界其他地方都不存在。通过基因图谱可以看到过去几千年里的社会分层：这两个相邻种姓长达数千年几乎没有混合，即使算上通奸或强奸等因素，实际混合比例也远低于预期。

One of them is just that, right? Like seeing how the Y chromosome and the mitochondrial DNA, because you can just learn a lot about population based on how the female versus male line is propagated about like what was the social structure like and so forth. Another is you can even tell the level of inequality in a society because if there's a lot so for example, in India, one of the things that was super surprising is that the amount of endogamy, which is to say that a certain caste in a certain village would just like not there wouldn't be any sort of intermixing with another caste in a neighboring village. Like to the extent that's true of nowhere else in the world. And they were able to find this in India where the amount of social stratification, you can see that in the genetic catalog over the last thousands of years, where for thousands of years, these two neighboring castes haven't mixed, like 99% or something, which is like even from sort of infidelity or rape or something, would expect there to be more than what actually ends up being the case.

因此你可以基于过去几千年的遗传历史来理解现代印度文化。

So you can understand modern culture in India based on what has happened over the last few thousand years.

这真的很有趣。所以我想，我觉得你做得非常好，总结了他的主要观点。但我有点想让你对克劳德也做同样的事情，这样我们就能看看你和克劳德相比如何。因为很明显，你已经把他的书输入到这个项目中了，所以它有那作为参考材料。

That's really interesting. So I wanna like, I feel like you're doing, like, such a good job of summarizing his main ideas. But I kinda wanna I kinda want you to do the same thing with with Claude so we can see how see how you stack up versus Claude. Because, obviously, you you've you've you've you've input his his book into into this project. So it has it has that as ref as reference material.

我们能要求它只是总结一下他的几个主要观点吗？是的。

Can we ask it to just, like, summarize, like, a few of his main ideas? Yeah.

这是个好主意。你能总结一下吗？也许还有他用来提出新见解的技术

That's a great idea. Can you summarize? And maybe, like, the techniques he used to come up with

完美。新的见解。所以你写的是，你总结了书中的主要观点以及用来提出新见解的技术？酷。这件事真的很酷的一点是，你很久以前就能用ChatGPT做类似的事情，但ChatGPT的上下文窗口没那么长。

with his Perfect. New insights. So what you're writing is, you summarize the main ideas from the book and the techniques used to come up with new insights? Cool. And one thing that's really cool about this is you've been able to do something like this with ChatGPT for a long time, but ChatGPT's context window isn't that long.

所以它会分割处理，因此无法真正总结整个内容。它必须找到书中合适的部分，而且它的嵌入搜索效果不太好等等。而克劳德，你可以直接把大量内容扔进上下文窗口，这就带来了很大的不同。好的。看起来我们得到了一些答案，显示

And so it chops it up, and it's not gonna really be able to summarize the entire thing because of that. It has to find the right parts of the parts of the book, and the embedding search in it is not very good and all that kind of stuff. And Claude, you can just, like, throw us throw a ton of stuff in the context window, and that just, like, makes a big difference. Okay. So it looks like it looks like we've got some some answers showing while that the

古DNA彻底改变了对人类史前史的理解。然后我们了解到今天的人口是多次迁移和混合浪潮的结果。然后就是一大堆其他遗传学的东西。接着它谈到了全基因组测序的关键技术，以及这些技术如何使得他们能够做出这类新发现。是的，是的。

ancient DNA has revolutionized understanding of human prehistory. And then we we've learned that populations today are the result of multiple waves of migration and mixture. And then just like a bunch of other genetic stuff. Then it talks about the key techniques about whole genome sequencing and how they've enabled these sorts of new discoveries they've been making. Yeah, yeah.

但不管怎样，所以关于他们的研究有很多有趣的事情。

But anyway, so there's a bunch of interesting things about their research.

嗯，我现在感兴趣的是，好吧，它使用的关键技术是对古代DNA样本进行全基因组测序。那么全基因组测序是新技术吗？可以对古代DNA样本进行测序？所以它说的是通过改进的提取测序技术，是不是这样

Well, now I'm interested in like, okay, so the key techniques that it's using are whole genome sequencing of ancient DNA samples. So is whole genome sequencing like a new thing that you can do it on ancient DNA samples? So it's saying like by improved extraction sequencing technologies, is that that's

是的，这是个有趣的问题。我们甚至可以问问看，因为我不确定。具体怎么对古代或史前基因组进行测序？你能做到吗，比如，这是怎么工作的？好吧，他们研磨骨头，然后用技术从中提取DNA。

Yeah, like that is an interesting question. We can even ask about it because I'm not sure. Exactly do you sequence an ancient or a prehistoric genome? Can you do, like, how does that work? Okay, so they grind the bone and they have then techniques to get the DNA out of that.

现在我们可以问的另一个问题是，我好奇的一点是，让我看看。我不太记得关于美洲原住民的章节了。我可以问问美洲原住民到底发生了什么。这是我好奇的一点。我甚至不知道大卫·赖希本人是否讨论过这个问题，但是，大卫·赖希的理论如何帮助解释为什么文明在公元前10,000年之后，也就是末次冰期结束后，如此迅速地突然出现，并且在新旧世界同时发生。

Now another thing we can ask is like, one thing I'm curious about, let's see. I don't really remember the chapter on Native Americans. I could ask about what exactly happened with Native Americans. Here's one thing I'm curious about. How would I don't even know if David Reich addresses this himself, but like, how would David Reich's theories help explain why civilization suddenly emerges so rapidly and that too concurrently in the new and the old world after 10,000 BCE, AKA the end of the last ice age.

然后也许我就问问克劳德为什么我觉得这是个有趣的问题。所以考虑到人类已经存在了这么久，这似乎是一个非常显著的巧合，你知道吗？

And then maybe I'll just ask Claude why I think it's an interesting question. So this seems like a really remarkable coincidence given how long humans have been around, you know?

那确实很有趣。

That is interesting.

嗯，考虑到人类已经存在了数十万年，这真是个巧合。

Well, coincidence given that humans have been around for hundreds of thousands of years.

我之前没意识到我们认为文明是在地理上相隔遥远的地方同时出现的。这对我来说完全是新知识。我原以为只是在美索不达米亚呢。

I didn't realize that we believe that it emerged like at the same time in geographically disparate places. That's totally new to me. I thought it was like just in Mesopotamia.

是的，实际上彼得·杰克逊有本很棒的书叫《大分流》，这是我读过最有趣的书之一。顺便提一下，这本书主要对比了新大陆与旧大陆文明的兴起。在新大陆，抱歉，说的是卡拉尔文明，它类似于公元前3000年的文明，但以渔业为基础，而不是像美索不达米亚那样的传统农业。他讨论了这种差异如何导致新大陆与旧大陆文化演变的不同。不过总之，

Yeah, it's actually there's a really good book by Peter Jackson called The Great Divide, and it's one of the most interesting books I've read. Just as a side note, it's about comparing the emergence of civilization in a new world versus your world. So in the old world, sorry, in the new world, the Kerala is like a civilization in 3,000 BCE and it's based on fishing and not on conventional agriculture like Mesopotamia. And he talks about how that changed the evolution of the culture in the new world versus the old world. But anyways,

这真的很有趣。

that's really interesting.

好的，那么主要的人口迁移与融合。

Okay, so major population movements and mixtures.