个人 AGI：智能的斯宾诺莎异端

所以，互联网称我为网上最 AI 狂热的人之一。因此，我以历史上最被取消的人物之一的故事来开始我的演讲，是再合适不过了。他叫巴鲁克·斯宾诺莎。如果你没上过哲学选修课，这里是你需要知道的要点。1929 年，一位纽约拉比通过电报向爱因斯坦挑战：你相信上帝吗？用 50 个字回答。爱因斯坦用 25 个字回答：我相信斯宾诺莎的上帝，他在世界的和谐中显现自己，而不是一个关心人类命运和行为的上帝。当时最著名的科学家提出了最大的问题，指向斯宾诺莎。但斯宾诺莎自己的社区对他做了什么？阿姆斯特丹，1656 年 7 月 27 日。斯宾诺莎 23 岁，是一个关系紧密的塞法迪犹太社区的成员。他站在犹太教堂里，长老们用社区有史以来最猛烈的诅咒将他逐出教门。白天受诅咒，夜晚受诅咒。躺下受诅咒，起来受诅咒。没有人可以和他说话。没有人可以和他交易。没有人可以靠近他四肘尺之内。没有人可以读他写的任何东西。这个禁令，在斯宾诺莎社区那个世纪发出的大约 40 个禁令中独一无二，没有悔改条款。它从未被解除。严格来说，今天仍然有效。斯宾诺莎当时 23 岁。他的罪行是邪恶的观点，表达被禁止的思想。他的惩罚是从社区中完全删除。在他的社区诅咒他之前，他们试图每年给他一千荷兰盾。那是笔大钱。他只需要偶尔去犹太教堂，闭上嘴。用创始人的话来说，他们给他薪水让他停止建设。他说：“不，一万也不行。”他说他想要真理，而不是舒适。在他被逐出教门前不久，一个狂热分子拿着刀向他冲来。刀刃划破了他的斗篷，但没有伤到他。他保留那件斗篷，裂痕未补，度过余生。他想记住思想的代价。那么，17 世纪最被取消的人接下来做了什么？他白天磨镜片。他制造光学仪器，让人类看得比眼睛更远的工具。他做得非常好，欧洲最好的科学家都来找他。晚上，他写一本危险到活着时无法出版的书。当他 44 岁去世时，肺里满是制造他人镜片时的玻璃粉尘，手稿锁在他的书桌里。他临终指示将书桌通过运河驳船运到他在阿姆斯特丹的出版商那里。那份手稿成为他的遗作，立即引起了整个欧洲的关注，并启发了启蒙运动一些最重要的哲学家。你可能会问，斯宾诺莎和创业有什么关系？嗯，这是一个被他认识的每个人取消的人，被提供薪水让他停止，几乎因发货而被杀，而他的回应是白天制造精密工具，晚上独自写欧洲最危险的书，没有征求任何人的许可。如果你要创业，你可以从斯宾诺莎身上学到东西。他给支撑他的引擎起了个名字：Conatus。意思是你的奋斗。每个生物体内继续前进并增强行动能力的驱动力。不是你的简历，不是你的头衔，不是你的工作，而是奋斗本身。这个演讲是关于放大它的工具。那么，他到底说了什么值得删除一个人？异端的要点是上帝不是宝座上的国王。上帝已经扩散到一切存在之中。他写道：上帝或自然。400 年后，我们对智能犯了类似的错误。每个人都在等待 AGI 作为一个单一事件，数据中心里的神，某个公告，某个门槛，某一天天空变色。所以现在我要说一个 400 年后更新的斯宾诺莎异端版本。每个人都在看天空，而他们等待的东西已经在房间里了。它看起来不像神。它看起来像基础设施，一个终端窗口，一个 markdown 文件文件夹，一个在你睡觉时完成的工作，扩散到一切之中，这正是斯宾诺莎告诉你要看的地方。AGI 不是作为事件到来。它作为你的智能体在你的上下文中运行，做你的工作，扩散而来。我称之为个人 AGI，不是为所有人同时出现的通用人工智能。为一个人——你——的通用智能。这是许多人的梦想。万尼瓦尔·布什称之为 Memex，一个将成为你和你的大脑延伸的机器。我想精确说明我的意思，因为“个人 AI”这个词已经被营销部门占用了。我不是指你每月付 20 美元的聊天机器人。我不是指稍微好一点的自动补全。我不是指一个只知道你的日历而不知道其他的助手。那只是你租的订阅。那是你不拥有的企业 AGI。你关闭标签页时它就重置。它知道别人已经知道的东西。当背后的公司转向时，你所谓的助手在别人的时间表上被切脑叶。个人 AGI 是另一种动物。一个在你的基础设施上运行的智能体，从你拥有的记忆中读取，执行你写的程序，并复利。你不拥有的企业 AGI 只有在公司发布东西时才会变得更好。你的个人 AGI 每天使用都会变得更好，因为每天它都更了解你的生活。一个是消费的产品，另一个是你建立的资产。世界上几乎没有人拥有这第二种东西。而这个竞技场里的每个人都可以在周一之前拥有它。我相信这种智能应该由你拥有，而不是租用。如果你为自己去构建这个，2034 年不必像 1984 年。你可能会问为什么个人 AGI 现在才发生。嗯，我认为是因为智能体能做什么。而在编码智能体方面最明显。2013 年，我是 YC 合伙人，晚上构建我们的内部社交网络 Bookface。我每天发布大约 14 行有用的代码，如果你知道程序员生产力的文献，这正好是中位数。那是我全力以赴。今年，我全职运营 YC。同样的大脑，同样的时间，加上下午 5 点接孩子。我计算了我的产出，大约是 2013 年的 400 倍。现在，在第三排的怀疑者让我泄气之前，让我自己泄气。你不相信原始代码行数。好吧。应用你能忍受的最病态的冗长惩罚，假设智能体写臃肿的代码。假设一半是脚手架。假设我在自吹自擂，这总是可能的。它仍然是最低 8 倍，中间范围 10 倍。无论你怎么折磨，数字都很大。现在，这只是代码，如果你在职业生涯的开始，你很幸运。这适用于设计。

So the internet calls me one of the most AI psychotic people online. So it's only right that I start my talk with a story about one of the most cancelled men in history. His name was Baruch Spinoza. And in case the philosophy elective wasn't your thing, here are the highlights you need to know. In 1929, a New York rabbi challenged Einstein by telegram. Do you believe in God? Answer in 50 words. Einstein answered in 25. I believe in Spinoza's God who reveals himself in the lawful harmony of the world, not in a God who concerns himself with the fate and doings of mankind. The most famous scientist alive asked the biggest question there is pointed at Spinoza. But here's what Baruch Spinoza's own community did to him. Amsterdam, July 27th, 1656. Spinoza is 23 years old, a member of a tight-knit Sephardic Jewish community. He stands in a synagogue while the elders excommunicate him with the most violent curse the community ever produced. Cursed be he by day and cursed be he by night. Cursed be he when he lies down and cursed be he when he rises up. Nobody may speak to him. Nobody may trade with him. Nobody may come within four cubits of him. Nobody may read anything he writes. And this ban, uniquely among the roughly 40 bans Spinoza's community issued that century, has no repentance clause. It has never been lifted. It technically is still in force today. Spinoza was 23. His crime was evil opinions, expressing forbidden thoughts. His punishment was complete deletion from the community. Before his community cursed him, they tried to buy him a thousand guilders a year. Serious money. All he had to do was show up at synagogue once in a while and keep his mouth shut. Hear that in founder terms. They've offered him a salary to stop building. He said, "No, not for 10,000." He said he wanted truth, not comfort. Shortly before his excommunication, a fanatic came at him with a knife. The blade tore through his cloak and missed him. He kept that cloak, scar unmended, for the rest of his life. He wanted to remember what ideas cost. So, what does the most canceled man of the 17th century do next? He grinds lenses by day. He makes optical instruments, tools that let human beings see further than their eyes allow. He makes them so well that the best scientists in Europe seek them out. And by night, he writes a book so dangerous he cannot publish it while he is alive. When he dies at 44, lungs full of glass dust from making other people's lenses, the manuscript is locked in his writing desk. His dying instruction shipped the desk by canal barge to his publisher in Amsterdam. That manuscript became his posthumous works, which attracted immediate attention across Europe and inspired some of the most important philosophers of the Enlightenment. What does Spinoza have to do with startups, you might ask? Well, here is a man canceled by everyone he knew, offered a salary to stop, nearly killed for shipping, and his response was to build precision tools by day and write the most dangerous book in Europe by night alone with no permission from anybody. If you're going to start a startup, you could do well to learn from Spinoza. He had a name for the engine that kept him going. Conatus. It means your striving. The drive in every living thing to keep going and to increase its power to act. Not your resume, not your title, not your job, the striving itself. This talk is about the tools that amplify it. So what did he actually say that was worth deleting a man over? The gist of the heresy was that God is not a king on a throne. God has spread through everything that exists. God or nature, he wrote. 400 years later, we are making a similar mistake about intelligence. Everyone is waiting for AGI as a singular event, a god in a data center, some announcement, some threshold, some day when the sky changes color. So now I'll say a version of Spinoza's Heresy updated 400 years later. Everyone is watching the sky and the thing they're watching for is already in the room. It doesn't look like a god. It looks like infrastructure, a terminal window, a folder of markdown files, a job that finishes while you sleep spread through everything, which is exactly where Spinoza told you to look. AGI isn't arriving as an event. It's arriving diffused as your agent running on your context doing your work. I call it personal AGI, not artificial general intelligence for everyone all at once. General intelligence for one person, you. This was a dream of a great many people. Vannevar Bush called it the Memex, a machine that would be an extension of yourself and your brain. And I want to be precise about what I mean because the words personal AI has already been captured by marketing departments. I do not mean a chatbot you pay $20 a month to. I do not mean a slightly better autocomplete. I do not mean an assistant that knows your calendar and nothing else. That's just a subscription you rent. It's a corporate AGI you don't own. It resets when you close the tab. It knows what everyone else already knows. And when the company behind it pivots, your so-called assistant gets a lobotomy on someone else's schedule. Personal AGI is a different animal. An agent that runs on your infrastructure, reads from a memory you own, executes procedures you wrote, and compounds. The corporate AGI you don't own gets better only when the company ships something. Your personal AGI gets better every single day you use it because every day it knows more of your life. One of these is a product you consume. The other is an asset you build. Almost nobody in the world has this second thing yet. And everyone in this arena could have it by Monday. And I believe intelligence of this kind should be owned by you, not rented. If you go forth and build this for yourself, 2034 doesn't have to be like 1984. You might ask why this personal AGI is happening only now. Well, I think it's because of what agents can do. And nowhere is it more obvious than encoding agents. In 2013, I was a YC partner building Bookface, our internal social network at night. I shipped maybe 14 useful lines of code a day, which if you know the literature on programmer productivity is dead on median. That was me at full effort. This year, I run YC full-time. Same brain, same hours, plus a 5:00 kid pickup. I did the math on my output, and I'm at about 400x what I did in 2013. Now, before the skeptic in row three deflates that number for me, let me deflate that for myself. You don't trust the raw lines of code. Fine. Apply the most pathological verbosity penalty you can stomach and assume the agent writes bloated code. Assume half of it is scaffolding. Assume I'm flattering myself, which is always a live possibility. It's still 8x at the absolute floor and 10 times that in the middle of the range. The number is large no matter how you torture it. Now, this is just code and if you're at the beginning of your career, you're in luck. This applies to design.

这适用于产品管理，适用于增长，适用于你可能想做的每一件事。编码的乘数效应不仅仅适用于编码，它适用于每一份知识工作。

This applies to product management. This applies to growth. This applies to every part of what you might want to do. The multiplier for coding is not just for coding. It's for every piece of knowledge work.

而且不只是我这么说。在 YC，我们能以投资组合的规模观察这一点。一年半前的 25 冬季批次中，有四分之一公司的代码库有 95% 是 AI 生成的。那些公司现在用 AI 智能体做所有事情，不仅仅是代码。那个批次有望成为 YC 历史上增长最快、最赚钱的批次之一。

And it's not just me. At YC, we get to watch this at portfolio scale. A year and a half ago in the winter 25 batch, a quarter of the companies had code bases that were 95% AI generated. Those companies use AI agents for everything now, not just code. And that batch is on track to becoming one of the fastest growing, most profitable batches in the history of YC.

我知道相关性是什么，所以让我谨慎地说。我无法证明 AI 生成的代码和其他一切导致了增长。但我可以告诉你的是，我们资助的增长最快的创始人并没有把 AI 当作自动补全，而是把它当作一支劳动力队伍。

Now, I know what a correlation is. So, let me say it carefully. I cannot prove that the AI generated code and everything else caused the growth. But what I can tell you is that the fastest growing founders we fund are not treating AI as autocomplete. They are treating it as a workforce.

有 2 倍的人和 100 倍的人在使用同一个 Claude。相同的权重，相同的上下文窗口大小，相同的 API。但杠杆不在权重里，而在于你给它什么上下文、上下文的相关性如何，以及它是否在正确的步骤发生。我们稍后会回到这一点。

There are 2x people and there are 100x people who are using the same Claude. Same weights, same context window size, same API. But the leverage is not in the weights. It's in what context you give it, how relevant it is, and does it happen at the right step. We'll come back to this.

斯宾诺莎有一个我每周都会想到的定义。在伦理学中，他把喜悦定义为你的行动能力增强的感觉。这就是为什么当一个智能体在一个下午完成你一周的工作时，感觉不像是一种便利，而是一种喜悦。这不是我在诗意化，这是术语。你的行动能力增强了，你的 conatus 变大了。

Now, Spinoza has a definition I think about every single week. In ethics, he defines joy as the feeling of your power of acting increasing. Which is why the first time an agent does a week of your work in an afternoon, it doesn't feel like a convenience. It feels like joy. And that's not me being poetic. That's the technical term. Your power of acting increased. Your conatus just got bigger.

顺便说一下，他定义了与之相反的东西：悲伤，即你的行动能力减弱的感觉。如果你的周日晚上有一种特别的沉重感，感觉你影响世界的能力在衰退，感觉你在默默辞职，那么这就是你所感受到的。记住这个想法，因为我们会在演讲的后半部分回到这一点，而且会涉及政治。

He defined the opposite to you, by the way. Sadness, the feeling of your power of acting decreasing. If your Sunday nights have a specific heaviness, like your ability to influence the world is receding, that you feel like you're quiet quitting, then this is what you feel and hold that thought because we're coming back to this in the second half of this talk and it gets political.

所以这就是你未来十年的方程式。一个前沿模型，它是租来的、是商品、每个季度都在变得更便宜；加上你的上下文，它归你所有、独一无二，理想情况下地球上没有其他人拥有它；再加上一个将它们连接起来的框架。那个框架可能是 OpenClaw、Hermes、Agent、Claude Code 或 Codex。把这些加起来，你就得到了一个像你一样但速度非常快的智能体。模型质量是租来的，但你的大脑理想情况下归你所有。

So here's the equation for the next decade of your life. A frontier model which is rented and a commodity and getting cheaper by the quarter plus your context which is owned by you and unique and ideally nobody else on this earth has it plus a harness that wires them together. That harness might be OpenClaw, Hermes, Agent, Claude Code, or Codex. Add that up and that gives you an agent that acts like a very fast version of you. Model quality is rented but your brain is owned ideally by you.

马歇尔·麦克卢汉说技术是人的延伸。史蒂夫·乔布斯称计算机是心灵的自行车。如果你拥有我在这里描述的东西，那么你就拥有了一枚自动驾驶的火箭。

Marshall McLuhan said that technology is an extension of man. Steve Jobs called a computer a bicycle for the mind. And if you have what I'm describing here, then you have a self-driving rocket.

保罗·格雷厄姆教会了这栋楼里的每一位创始人两件事：做出人们想要的东西，以及做那些无法规模化的事情。这两者仍然支配着一切。新的变化是第二件事的乘数效应。智能体就是现在一位创始人如何大规模地做无法规模化的事情的方式。建议没有变，但所有初创公司的物理规律以及你能做什么的物理规律变了。

Paul Graham taught every founder in this building two things. Make something people want and do things that don't scale. Both still govern everything. What's new is the multiplier on the second one. Agents are how one founder now does unscalable things at scale. The advice didn't change, but the physics of all startups and of what you can do did.

斯宾诺莎磨制镜片，这些仪器让人们能够超越眼睛的极限看到东西。我想用接下来的 15 分钟向你展示为心灵磨制镜片是什么样的。这是我实际运行我生活的机器，每个概念都适用于你使用的任何技术栈。

Spinoza ground lenses, instruments that let people see past the limits of their eyes. I want to spend the next 15 minutes showing you what grinding lenses for the mind looks like. This is the machinery I actually run my life on, and every concept travels to whatever stack you use.

让我们从工作记忆开始，因为它解释了一切。你和我作为人类，一次大约能在脑中记住七件事。七加减二。这是认知心理学中最著名的论文。这就是为什么本地电话号码是七位数，为什么你会忘记购物清单上的第八项。那就是人类全部的工作记忆。人类建造的每一个机构、每一张清单、每一张组织结构图、每一个文件柜、每一次站会，都是那个限制的假肢。

Let's start with working memory because it explains everything. You and I as human beings hold about seven things in our head at once. Seven plus or minus two. It's the most famous paper in cognitive psychology. It's why local phone numbers are seven digits and why you forget the eighth item on a grocery list. That is the entire working memory of a human being. And every institution humanity has ever built, every checklist, every org chart, every filing cabinet, every standup meeting is a prosthetic for that limit.

然而，一个 AI 智能体持有 100 万个 token。那大约是 1000 页。三本《哈利·波特》同时摊开在它头上。它能在任何一本中找到一根针，并在几秒钟内综合三本书的内容。三本《哈利·波特》对比七位数。你可以说这还不完全是 AGI，但这已经是一个不同的运行机制。

An AI agent though holds a million tokens. That's about a thousand pages. Three Harry Potter books sitting open on its head all at once. And it can find a needle in any of them and synthesize across all three in seconds. Three Harry Potter books versus seven digits. You could argue that's not quite AGI yet, but it is already a different operating regime.

而且地球上几乎每个人仍然在按照为七位数大脑设计的组织结构图和做事方式生活。把这个数字往另一个方向推。1000 页很多，但也很少。你的生活不是三本书，你的生活是一座图书馆。你发过的每一封邮件、每一次会议、每一个决定及其背后的每一个理由、与你认识的每一个人的每一次对话。决定你的智能体是天才还是金鱼的问题是：谁来决定，或者什么决定，哪三本书摊开在桌子上。

And almost everyone on Earth is still running their life on an org chart and a way of doing things designed for the seven-digit brain. Run that number in the other direction. A thousand pages is a lot, but it is also very little. Your life is not three books. Your life is a library. Every email you ever sent, every meeting, every decision, and every reason behind it, every conversation with every person you know. The question that determines whether your agent is a genius or a goldfish is this: who decides or what decides which three books are open on the desk.

那就是大脑的本质。那就是 GBrain 想要成为的东西：图书馆加上图书管理员。我一直在公开构建 GBrain。我的个人 OpenClaw 有一个 Karpathy 风格的知识维基，大约有 22 万个 markdown 页面。我 25 年的生活被记录成日记。每一封邮件、每一次会议、我的笔记、我的照片、我的草稿、我犯过的错误，大部分由智能体编译、由智能体策展、由智能体搜索，但我从不重新问一个我已经回答过的问题。

And that's what a brain is. That's what GBrain is meant to be. The library plus the librarian. I've been building GBrain in the open. My personal OpenClaw has a Karpathy style knowledge wiki with about 220,000 markdown pages. 25 years of my life diarized. Every email, every meeting, my notes, my photos, my drafts, the things I got wrong, compiled mostly by agents, curated by agents, searched for by agents, but I never reask a question I already answered.

而系统中的生活经验才是关键。一位创始人给我发邮件谈论危机。在我读完邮件之前，我的智能体已经拉出了我与那位创始人的所有过往对话、三家遇到同样障碍的投资组合公司以及对他们真正有效的方法。当我的智能体做任何事情时，它都是在知道我所有知识的情况下做的。这就是助手和同事之间的区别。

And the lived experience in the system is the point. A founder emails me about a crisis. Before I finish reading the email, my agent has already pulled every prior conversation I've had with that founder. Three portfolio companies that hit the same wall and what actually worked for them. When my agent does anything, it does knowing everything I know. And that's the difference between an assistant and a colleague.

让我带你走过真实的一天，因为这比架构图更重要。昨晚我睡觉时，我的智能体处理了我的收件箱。不是分类，而是处理。它知道哪些邮件来自遇到麻烦的创始人，哪些来自想卖我东西的人，哪些来自我从未真正退订的 17 个邮件列表。重要的邮件会从图书馆中提取上下文进行分诊：这个人是谁，我与他们的全部历史，他们在文字背后真正问的是什么，以及这可能对我意味着什么。

Let me walk you through an actual day because that matters more than an architecture diagram. While I slept last night, my agent processed my inbox. Not sorted it, processed it. It knows which emails are from founders in trouble, which are from people trying to sell me something, and which are from the 17 mailing lists I never quite unsubscribed from. The ones that matter are triaged with context pulled from the library. Who this person is, my whole history with them, what they're really asking under what they wrote, and what that might mean for me.

我醒来看到的是简报，而不是一堆邮件。每次会议前，一份准备文档：我要见谁，我们上次说了什么，自那以来发生了什么变化，以及我应该问什么。午夜时我好奇的研究到早上就完成了。当世界上发生有趣的事情时，我的智能体通常已经读过它，与我关心的事情交叉引用，并在喝咖啡之前归档了。

I wake up to a briefing, not a pile of emails. Before every meeting, a prep doc: who I'm meeting, what we said last time, what changed since, and what I should ask. Research I was curious about at midnight is finished by morning. And when something interesting happens in the world, my agent has usually read it, cross-referenced against what I care about, and filed it before I've had coffee.

在这个图书馆之上，是我的智能体编码框架 GStack，现在有 12.3 万颗星，这使它进入了 GitHub 历史上开源项目的前 100 名。而这个完整架构的真正要点是什么？主要是技能文件加上一个智能体可以驱动的浏览器。一页页的英文和一种作用于世界的方式。Markdown，不是魔法。胖技能，瘦框架。

On top of this library sits my agent coding framework, GStack, 123,000 stars now, which put it in the top 100 open source projects in the history of GitHub. And what's actually in the punchline of this full architecture? It's mostly skill files plus a browser that the agents can drive. Pages of English and a way to act on the world. Markdown, not magic. Fat skills, thin harness.

让我给你看看什么是技能文件，因为我一直在说这个词，我想让你看看它其实没什么神奇的。这里有一个真实的例子，稍微做了些删减。

Let me show you what a skill file is because I keep saying this phrase and I want you to see how unmagical it is. Here's a real one, lightly redacted.

上面写着：“当 Circle Back 的会议录音到达时，用说话人标签转录。提取做出的承诺、承诺人和截止日期。将每个提到的人与资料库交叉核对，并链接他们的页面。把摘要归档到这里，完整转录放到那里。如果任何内容与我们已有的认知相矛盾，标记出来，不要覆盖它。就这些。这就是一个技能。它就是一页英文。一个聪明的实习生，任何能读懂的人都能照着做。而这正是检验标准。如果一个聪明的实习生能照着做，那么智能体就能运行它。这意味着，实际上，这是一件意义深远的事。我知道我因为谈论这个挨了不少批评，但我认为它比以往任何时候都更正确，尤其是现在。Markdown 实际上就是代码。如果你能用英文写出清晰的指令，你就是程序员。编译器就是语言模型。这就是为什么它不再只是工程师的专利。在 YC，我们的媒体人员、活动人员、财务团队，那些一辈子没打开过终端的人，都在构建技能文件和定时任务。我们的一位财务人员用内部智能体构建了一个应用，把大约一百个 Excel 工作簿整合到一起。她不是程序员。她是智能体的管理者。现在，每个人都即将成为这样的管理者。

It says, "When a meeting recording lands from Circle Back, transcribe it with speaker labels. Pull out the commitment made, who made it, and the deadline. Cross-check every person named against the library and link their pages. File the summary here, full transcript there. If anything contradicts something we already believe, flag it. Don't override it. That's it. That's a skill. It's a page of English. A smart intern, anyone really who could read could follow it. And that's the test actually. If a smart intern could follow it, an agent can run it. Which means uh actually a kind of profound thing. I know I caught a lot of flack for talking about this, but I think it's more true than ever, especially now. Markdown is actually code. If you can write clear instructions in English, you're a programmer. The compiler is a language model. And that's why it's not just for engineers anymore. At YC, our media people, event staff, finance team, people who never open a terminal in their lives are building skill files and scheduled jobs. One of our finance folks compiled um about a hundred Excel workbooks into a single app she built with an internal agent. She is not a programmer. She is a manager of agents. Now, everyone is about to be.

这里最重要的问题是：计算发生在哪里？答案只有两个。混淆它们会导致我见过的每一次智能体失败。有些计算属于潜在空间。品味、判断，从模糊请求中理解人类真正想要什么，这些存在于模型中，你用 Markdown 文件来引导它。而另一些计算属于确定性空间。算术、SQL 查询，比如，你今天要参加的分会场座位安排。所有这些都需要存储在 SQL 数据库中，由 Markdown 文件调用。在这方面保持清醒会大有裨益。让智能体或人类安排五个人围坐在一张桌子旁，这很容易，在潜在空间里就能完成。但要为体育馆里的 6000 人制定个性化日程，就像我们刚刚为你做的那样，你的潜在空间智能体就需要编写代码来跟踪管理。你参加这次会议的经历，必须通过 Markdown 文件以这种方式调用代码才能实现。没有代码，你做不到。模型在我们失败的地方失败。解决办法是让模型像人类一样计算。潜在空间和确定性空间，Markdown 文件调用数据库和脚本。很简单，但这就是一切真正的基础。

The most important question to ask here is where is the computation happening? And there are exactly two answers. and confusing them causes every agent failure I've ever seen. Some computation belongs in latent space. Taste judgment reading what a human actually wants from a vague request that lives in the model and you steer it with a markdown file. And then some computation belongs in deterministic space. the arithmetic, the SQL query, uh for instance, the seating chart for what sessions you're going to go to today for your breakouts. Uh all of that needs to be stored in a SQL database used by the markdown files. Being smart about this goes a long way. Ask an agent or human to seat five people around a table. That's easy. Do it in latent space. Ask it to make custom schedules for 6,000 people in an arena like we just did for you. And your latent space agent needs to write some code to keep track of it. Your experience at this conference had to be markdown files calling code in exactly this way. And you couldn't do it without the code. The model fails where we fail. The fix is having the model compute the way humans compute. the latent and the deterministic markdown files calling databases and scripts. Simple, but it's what everything is actually built on.

我再给你一个实例。这是我最喜欢的一个，因为你现在就身处其中。五天前，我决定这次演讲需要提到斯宾诺莎，我最喜欢的哲学家之一，尤其是因为他当时被“取消”得很惨。于是我的智能体去获取了三本关于他的最佳传记。纳德勒、戈尔茨坦和斯图尔特写的书，总共约 1500 页。它读完了全部三本。它为我构建了一份综合材料，一份带日期的生平年表，三位传记作者之间所有分歧之处，以及最好的逐字引文并附有章节出处。而且因为它知道我需要什么，还列出了他一生中最值得讲述的 10 个时刻，并附有讲述要点。刀袭事件、贿赂、书桌。我们开场中那些可能在 20 分钟前让你起鸡皮疙瘩的每一个节拍，都来自那次通宵运行。1500 页变成了一篇可以编辑的、适合舞台讲述的故事。我称之为“纲要技能”，我每天都在用。这是一个个人技能，是深度研究的超级加强版，比任何企业 AI 产品给你的都要深入。你正在观看的这场演讲的主干，正是受到我们正在描述的这台机器的启发。

And I'll give you one more receipt. My favorite one because you're sitting inside it right now. Five days ago, I decided this talk needed Spininoza, one of my favorite philosophers, especially because of how cancelled he got. So my agent went and acquired three of the best biographies about the man. Books by Nadler, Goldstein, and Stewart, about 1,500 pages. It read all three. It built me a synthesis, a dated chronology of his life, every place the three biographers disagree with each other, and the best verbatim quotes with chapter citations. And because it knows what I need, the 10 most tellable moments of his life ranked with delivery notes. The knife attack, the bribe, the desk. Every beat of our opening that might have given you some chills 20 minutes ago came out of that overnight run. 1500 pages became a stage ready story that I could edit. I call it a compendium skill and I use it daily. It's a personal skill that is a mega mega version of deep research only deeper than anything the corporate AI products will give you. The spine of this talk you're watching was inspired by the machine we're describing now.

如果你想知道我的“矿藏”是从哪里开始的，那并不是 22 万页。它只是一个文件夹。里面有几个关于我合作的公司和我经常发邮件联系的人的 Markdown 文件。资料库变大，和其他任何东西变大的方式一样。每天积累一点点，由智能体负责归档。没有人会先建仓库。首先，你建一个架子。

And if you're wondering where my mine actually started, it was not 220,000 pages. It was a folder. It was a few markdown files about the companies I was working with and the people I kept emailing. And the library got big the same way anything gets big. A little every day compounding with agents doing the filing. Nobody builds the warehouse first. First, you build one shelf.

当你今晚坐下来与智能体合作时，你不是在编程。你是在管理一支由 Markdown 构成的劳动力队伍。一个技能文件就是一个员工。它有一项能力，一项工作，写得足够清晰，让新人都能执行。解析器就是组织结构图。任务进来，它决定由哪个 Markdown 文件或谁来处理。这意味着，在你注册任何公司之前，在你拥有联合创始人、标志或演示文稿之前，你已经在运营一个组织了，一个由你加上你的智能体组成的组织。你是创始人，也是“你公司”的整个管理层，你手下的员工人数由你决定。

When you sit down with an agent tonight, you're not coding. You're man managing a workforce made of markdown. A skill file is an employee. It has one capability, one job written down clearly enough that someone new could execute it. A resolver is an org chart. A task comes in and it decides which markdown file or who handles it. Which means that before you ever incorporate anything, before you have a co-founder or a logo or a deck, you can already be running an organization, an organization of one plus your agents. You are the founder and the entire management layer of you incorporated and the headcount under you is now whatever you decide it is.

这已经催生了打破旧有数学规律的公司。我们 24 年夏季批次中的 Emergent，从公开发布到实现九位数营收只用了八个月。当他们年化营收突破 1500 万美元时，他们只有 15 个人。Retail 冬季 24 批次以大约 40 人实现了 6000 万的年化营收。这样的人均营收以前从未存在过。软件行业没有，石油行业没有，铁路行业也没有。这些不是自然界的怪胎。它们是第一批原生构建在新物理学基础上的公司。而它们每一个都始于一两个人，按照我刚才描述的方式组织起来。

This already produces companies that break the old math. Emergent out of our summer 24 batch went from public launch to nine figures of revenue in eight months. When they crossed $15 million in annualized revenue, they were 15 people. Retail winter 24 hit 60 million annualized with about 40. That revenue per person did not exist before. Not in software, not in oil, not in railroads. And these aren't freaks of nature. They're the first companies built natively on the new physics. And every one of them started as one or two people wired the way I just described.

现在想象一下我们在 Dogpatch 的批次房间。每天都有数百位创始人。他们每个人都在做过去一个人一整年的工作量。这不是未来。这就是这一批人的当前标准。如果你不这样做，你的竞争对手会做，他们会礼貌地抢走你的午餐，并且还会感谢你。

Now picture our batch room in the dog patch. Hundreds of founders every single day. Each one of them doing what used to be a person's entire year of work. That is not the future. That is the bar right now with this batch. If you're not doing it, your competitor is and they will eat your lunch politely and thank you for it.

这也改变了软件本身是什么。软件不再需要那么“珍贵”了。你可以在一个周末内，为“一个用户”这个受众群体构建出你恰好需要的工具。过去的建议是“挠自己的痒处”，然后希望这就是市场需求。新版本要好得多。挠自己的痒处，因为挠痒几乎是免费的。而且你为“一个人”打造的一些工具，最终可能会变成整个公司。你会知道，因为其他人会开始求着要这些工具。

It also changes what software even is. Software doesn't have to be precious anymore. You can build exactly the tool you need for the audience of one in a weekend. The old advice was scratch your own itch and hope it's the market. The new version is much better. Scratch your own itch because scratching itches is nearly free. And some of your tools for one will turn out to be entire companies. You'll know because other people start begging for them.

在进入“怎么做”之前，我要坦诚地提醒一句，免得你们抓住我的把柄。一个没人维护的大脑，就是一个拥有强大搜索功能的垃圾场。检索会以绝对的自信呈现一个过时的事实。一个糟糕的技能文件会永远固化一个糟糕的流程。所以，基本要素是记忆加卫生。每个事实都要有来源。当新信息与旧信息冲突时，要进行矛盾检查。还要有一个图书管理员，其实际工作就是修剪。把大脑当作生产基础设施来对待，它就会产生复利。把它当作垃圾场，你就会得到一个非常自信的智能体，它以无人能追踪的方式犯错。

And one honest caveat before the how-to because you catch me out in anyway. A brain nobody curates is a garbage dump with great search. Retrieval will surface a stale fact with total confidence. A bad skill file encodes a bad process forever. So the primitive is memory plus hygiene. Provenence on every fact. Contradiction checks when new information collides with old. and a librarian whose actual job is pruning. Treat the brain like production infrastructure and it compounds. Treat it like a dumping ground and you get a very confident agent that is wrong in ways nobody can trace.

到目前为止，一切都是哲学和实例。那么，让我们进入一些“怎么做”的部分。如果你在接下来的六分钟里按照我描述的方法去做，你就会领先于 99% 观看这场演讲并只是点头的人。

Everything so far is philosophy and receipts. So, let's get into some how-to. If you do what I describe in the next six minutes, you'll be ahead of 99% of people who watch this talk and just nodded.

今晚第一步，选一个工具框架，在你自己的机器上跑一个智能体。我用的是 OpenClaw 和 Hermes 智能体，配合 GBrain。这个的托管版本在 gbrain.io，是免费的。GBrain 本身也是免费开源的。我总是推荐法拉利，但说实话，本田也很好。Codeex、Claude Code，随便哪个都行。任何一个都能完成这事的 99%。而且不用法拉利的好处是，它也能把你送到目的地，只是少一点半路停下来修车的麻烦。重点是概念，而不是某个具体的仓库或产品。智能是随取随用的，路径有很多。

Step one tonight, pick a harness and run an agent on your own machine. I use OpenClaw and Hermes agent with GBrain. A hosted version of this is at gbrain.io. It's free. GBrain itself is free and open source. I always recommend the Ferrari, but I'll be honest, the Honda is really good, too. Codeex, Claude Code, whatever. Any of them will do 99% of this. And the upside of not Ferrari is that it will also get you to your destination with a little less of less getting out to fix it on the side of the road. The concepts are the point, not any given repo or product. The intelligence is on tap and there are many paths.

第二步，这个周末，开始建立你的知识库，不是那种宏大的档案库，就是一个 markdown 文件的文件夹。导出你的笔记，如果可以的话也导出你的邮件。为你正在做的每个项目、合作的每个人各写一页。在这些页面上，写下你真正知道的事情：你们在共同构建什么，他们关心什么，你欠他们什么，他们上次说了什么。这些东西地球上没有任何模型拥有，因为它们只存在于你的脑子里。而你的脑子，正如我们之前确认的，只能装下七件事。当智能体第一次用你的上下文而不是互联网来回答问题时，你会感到那种“咔哒”一声的顿悟，然后就再也回不去了。你们每个人都坐在自己五到十年的历史上面，就在某个收件箱里。那就是你的护城河，就那样躺在那儿，没有被索引，毫无作为。你和这整个架构之间唯一的门槛，大概就是 24 小时。

Step two this weekend, start your library, not a grand archive. One folder of markdown files. Export your notes. Export your email if you can. Write one page about each project you you're working on and each person you work with. And on those pages, write the things you actually know, what you're building together, what they care about, what you owe them, what they said last time. That's stuff no model on the earth, no model on earth has because it only exists in your head. And your head, as we established, only holds seven things. The first time an agent answers a question using your context instead of the internets, you'll feel the click and you won't go back. You're all sitting on you are all sitting on five 10 years of your own history in one inbox or another. That's your moat just lying there unindexed doing nothing. The only gate between you and this entire architecture is probably 24 hours.

第三步，写你的第一个技能文件。选哪个很容易。你知道的，你每周最讨厌做的任务是什么？可能是报销单、会议记录、每周状态更新、竞品研究。用大白话向你的智能体解释，就像你向一个聪明的朋友解释他们上班第一天要做的事一样，然后让它犯错。如果它做错了，就纠正它。每一条规则、每一个例外、每一个“哦对了”，都写进去，它就会修正。那一页现在就是一个员工。运行它。

Step three, write your first skill file. Picking it is easy. You know, what's the task you do every single week that you hate the most? Might be expense reports, meeting notes, the weekly status update, competitor research. Explain it to your agent. What do you want to do in plain English, the way you'd explain to a smart friend on their first day of a job, and then let it get it wrong. If it gets it wrong, correct it. Every rule, every exception, every oh, and also put it in there, and it'll fix it. That page is now an employee. Run it.

第四步，把它设置成一个定期任务。也许就是你刚在第三步里创建的那个任务。每天早上 7 点做这个，每周五总结那个。第一次你醒来发现工作在你睡觉时已经完成了，你脑子里会有某种东西永久性地改变。从那天起，一天不再是你工作的单位。它变成了你能想象的东西，而且应该由你的目标和你想在这个世界上创造的东西来驱动。

Step four, wire it up to be a recurring job. Maybe it's the job you just created. In step three, every morning at 7, do this. Every Friday, summarize that. The first time you wake up to work that finished while you're sle you slept, something shifts in your head permanently. That's the day that the day stops being the unit of work for you. It becomes what you can imagine and it should be driven by what your goals are and what you want to create in the world.

第五步，这是区分复利者和浅尝辄止者的纪律。永远不要做一次性工作。大多数人用一个智能体跑一次操作，然后把上下文扔掉。他们关掉窗口，就完了。别这样。每项任务结束时，让智能体把它做过的事情“技能化”。Skillify 是你在 GBrain 里能找到的一个特殊技能。你可以指向那个仓库说：“提取 skillify，学会怎么做。”把它变成一个你可以永远使用和复用的 markdown 文件。我会用我在 YC 常说的方式来说：如果你需要问两次，你就失败了。捕捉所学的人，每天都会变得更聪明。而每天早上醒来都失忆的人，那是在浪费你的时间。而且，如果你不能把模型变成真正的记忆，模型再好也没多大意义。

Step five, this is the discipline that separates the compounders from the dabblers. Never do one-off work. Most people run one operation with one agent and then throw the context away. They close the window. That's it. Don't. At the end of every task, ask the agent to skillify what it did. Skillify is a special skill you can find in Gbrain. You can point it at that repo and say, "Extract skillify. Learn how to do it." Turn it into a markdown file you can use and reuse forever. I'll say it the way I say it at YC. If you have to ask for something twice, you failed. The person who captures what they learn gets smarter every single day. The person who wakes up every morning with amnesia, well, that that's a waste of your time. And it sort of doesn't matter how good the model gets if you can't turn it into real memory.

做到这五件事，我就能告诉你接下来 90 天会是什么样子。第一周，说实话，它就是个玩具。知识库很薄，技能很笨拙。你修复的比节省的还多。第四周，飞轮开始转动。智能体开始用你的上下文来回答。早上的任务产生了你真正会读的东西，而且你写了第三个和第四个技能，因为前两个奏效了。第 12 周，你有了一个在你问完之前就能回答的知识库。十几个技能文件在运行你过去每周最害怕的部分，还有一两个工具，别人总是来借，在这个房间里，这就叫创业。这条曲线和你见过的任何复利曲线一样：平、平、平，然后突然起飞。大多数尝试的人会在第二周放弃，这正是为什么那些没放弃的人到第 12 周会觉得自己像是在作弊。

Do those five things and I can tell you what your next 90 days look like. Week one, honestly, it's a toy. The library is thin. The skills are clumsy. You're fixing more than you're saving. Week four, the flywheel catches. The agent starts answering with your context. The morning job produces something you actually read, and you write your third and fourth skill because the first two worked. Week 12, you have a library that answers before you finish asking. A dozen skill files running the parts of your week you used to dread and one or two tools that other people keep asking to borrow, which in this room is called a startup. The curve is the same curve as any compounding thing you've ever seen. Flat, flat, flat, then not. Most people who try this will quit this in week two, which is precisely why the ones who don't feel like they're cheating by week 12.

现在，我需要告诉你们不那么有趣的部分，因为我教给你们的一切都是双刃剑。我之前告诉过你们斯宾诺莎关于悲伤的定义：你的行动能力在减弱的感觉。我说过这会变得政治化。在这里，技能文件不是一份文档，它是你认知的一部分。你做事的方式从你脑子里被提取出来，写下来，并且可执行。你教给智能体的每一个技能，都是你被外化。而完全相同的文件，取决于一个变量，会通向两个截然不同的未来：谁控制它。

Now, I need to tell you the part that isn't fun, because everything I taught you just cuts both ways. I told you Spinosa's definition of sadness earlier. The feeling of your power acting, power of acting decreasing. And I said it gets political. This is where a skill file is not a document. It's a piece of your cognition. How you do the thing extracted from your head, written down, and executable. Every skill you teach an agent is you externalized. And the exact same file is two opposite futures depending on one variable. who controls it.

举一个虚构的例子，一个支持工程师，我们叫她玛雅。两年里，玛雅教会了她的智能体 40 个技能：如何在凌晨 2 点对 P0 故障进行分类，如何安抚即将流失的客户，如何写一份真正能防止下一次事故的事后分析。40 个文件，那就是她的判断力。她花两年时间构建的东西，就放在磁盘上。版本一：这些文件存在于玛雅的仓库里。她换工作，它们跟着她走。到新公司的第一天，她就能调用多年积累的判断力。她每工作一年，都在复利。这就是所有权。如果她想开一家做这个的公司，这就是她的专长。而且事实证明她可以。如今，整个初创公司都会是 markdown 文件。版本二：这些文件存在于公司的仓库里，受公司 IT 政策约束。玛雅离开时什么也带不走。公司继续在没有她的情况下运行她的判断力。40 个文件永远执行，而她的名字甚至不在提交历史里。她没有职业生涯，她经历了一次提取。同样的文件，同样的玛雅，一个变量。

Take a fictional example of a support engineer. Let's call her Maya. Over two years, Maya teaches her agents 40 skills. How to triage a P 0 at 2 in the morning. How to deescalate the customer who's about to churn. How to write a postmortem that actually prevents the next incident. 40 files. That's her judgment. The thing that took her two years to build sitting on a disc. Version one. Those files live in Maya's repo. She changes jobs. They go with her. Day one at a new company, she's operating with years of compounded judgment on tap. Every year she works, she compounds. That's ownership. And if she wanted to start a company that does this, it's her expertise. And it turns out she can. Entire startups these days will be markdown files. Version two, those files live in the company's repo under the company's IT policy. Maya leaves with nothing. The company keeps running her judgment without her. 40 files executing forever. and her name isn't even in the commit history. She didn't have a career. She had an extraction. Same files, same Maya, one variable.

所以，这就是信条，我希望你们明天能复述出来。我相信技能文件是你的。拥有你的技能，因为如果你不拥有，你的工作就会变成一个技能文件。这种事以前发生过。工匠拥有他们的工具，那是他们自由的原因。工厂打破了这一点。织布机属于磨坊。知识工作者以为我们是安全的，因为我们的工具住在脑子里，没人能没收。技能文件终结了这一点。历史上第一次，你的认知可以被提取、存储、版本化，并被拥有。唯一的问题是：被谁拥有？

So, this is the doctrine and I want you to be able to repeat it tomorrow. I believe skill files are yours. Own your skills because if you don't, your job becomes a skill file. And this happened before. Craftsmen own their tools. That's what made them free. The factory broke that. The loom belonged to the mill. The knowledge workers assumed we were safe because our tools lived in our heads where nobody could confiscate them. Skill files end that. For the first time in history, your cognition can be extracted, stored, versioned, and owned. The only question is by whom?

记住，你们还记得那一千荷兰盾吗？那个提议从未消失，它只是被重新包装了。每一个让你在别人的仓库里复利判断力的舒适安排，都是每年一千荷兰盾，让你出现、保持安静、停止构建自己的东西。这就是为什么你应该创业，因为这样你才能真正让那些技能文件为你服务。斯宾诺莎面对的是升级版的版本二。

Remember, do you remember the thousand gilders? That offer never went away. It got rebranded. Every comfortable arrangement where your judgment compounds in someone else's repo is a thousand gilders a year. to show up, keep quiet, and stop building your own thing. And that's why you should start a startup, because this is how you can actually make those skill files work for you. Spinosa faced the upgraded version two.

1673 年，海德堡大学向这位被诅咒的异端提供了一份正教授职位、薪水、合法性、一个讲席，以及所谓的“哲学自由”，前提是他不扰乱既定的宗教。

In 1673, H Highleberg offered the cursed heretic a full professorship, salary, legitimacy, a chair, and quote, freedom of philosophizing, provided he not disturbed the established religion.

他的回答是：我不知道那种哲学自由的界限可能是什么。他读了服务条款，然后拒绝了这份录用。他对自己所保护的东西有一个说法：靠自己的力量，而不是靠别人的力量。你的行动力无论哪种方式都存在。1673 年和 2026 年的政治问题是：谁来指挥它？个人 AI 就是关于掌控你自己的认知能力并保护自己。这就是本次演讲全部论点的一句话总结。个人 AGI 就是你在智能体时代保持自主的方式。所以，从第一天起，就把你的大脑和技能放在一个你控制的仓库里，趁任何平台或收购方对它还没有意见之前。

His answer was, I do not know what the limits of that freedom of philosophizing might have to be. He read the terms of service and he declined the acquisition. He had a phrase for what he was protecting. Under your own power as opposed to under someone else's. Your power of acting exists either way. The political question in 1673 and in 2026 is who commands it? Personal AI is about controlling your own cognitive abilities and protecting yourself. That's the whole thesis of this talk in one sentence. Personal AGI is how you stay under your own power in the age of agents. So keep your brain and your skills in a repo you control from day one before any platform or any acquirer has an opinion about it.

斯宾诺莎去世时，他们清点了房间。两条裤子、七件衬衫、一台镜片车床、160 本书，还有《伦理学》。锁在书桌里，他几乎一无所有，但从来没有人控制过他的技能文件。那个书桌抽屉就是他的仓库。像他那样拥有你自己的仓库。

When Spinoza died, they inventoried the room. Two pairs of pants, seven shirts, a lens lathe, 160 books, and the Ethics. Locked in a desk, he owned almost nothing, and nobody ever controlled his skill files. The desk drawer was his repo. Own yours like he owned his.

现在，三个反对意见，我在台上都能听到，所以我们就直接来。反对意见一：模型进步太快，所有这些“装备”都会过时。等下一个版本就行了。这是“更好的苦涩教训”那一派，我爱他们。但注意每次模型发布时实际发生的事：模型越好，差异化就越转移到上下文上。当每个人的引擎都是 1000 马力时，比赛就赢在驾驶员和地图上。权重是大家的，而图书馆是你的——至少我希望如此。更好的模型让你的图书馆更值钱，因为更聪明的读者从同样的书里能提取更多。我和这栋楼里任何人一样为实验室加油，但他们每次发布的版本，都是对我已经拥有的劳动力的一次免费升级，也是我希望你拥有的劳动力。

Now, three objections, and I can hear them from up here, so let's just do them. Objection one, the models are improving so fast that all this harness stuff will be obsolete. Just wait for the next release. This is the better bitter lesson crowd and I love them. But notice what actually happens in every model release. The better the models get, the more the differentiator moves to context. When everyone's engine is a 1000 horsepower, the race is won on the driver and the map. The weights are everyone's. The library is yours. At least I hope it is. A better model makes your library worth more because a smarter reader extracts more from the same books. I'm rooting for the labs as hard as anyone in this building, but every release they ship is a free upgrade to a workforce I already own and a workforce I want you to own.

反对意见二：这不就是 RAG 吗？当然，Postgres 也不过是 B 树。检索是原语，不是产品。难的是它周围的一切：首先该写下什么？如何丰富和链接？什么被提升为热记忆，什么被归档为冷参考？当两个事实冲突时，谁来仲裁？检索很容易。值得被检索才是产品。

Objection two, is this just rag? Sure, and Postgres is just B trees. Retrieval is the primitive, not the product. The hard part is everything around it. What gets written down in the first place? How it gets enriched and linked, what gets promoted to hot memory versus filed as cold reference, who arbitrates when two facts disagree. Retrieval is easy. Being worth retrieving from is the product.

反对意见三，也是最值得尊重的一个。你把整个生活放进一个系统：邮件、会议、孩子的日程。泄露了怎么办？我的答案和整场演讲一样：这正是它必须是你的的原因。我的大脑运行在我自己的基础设施上，在我自己的仓库里，用我自己的密钥。对比默认情况——那并不是隐私。默认情况是，你的生活已经分散在 10 朵云上，由那些动机与你不同的公司拥有，除了你谁都能搜索。我并没有因为整合上下文而制造风险，我是接管了它。托管就是安全模型。如果你不信任自己能握住钥匙，我保证，答案不是更信任别人的服务条款。

Objection three, and it's the one that deserves the most respect. You put your entire life in one system, your email, your meetings, your kids schedules. What happens when it leaks? My answer is the same answer as the whole talk. That's exactly why it has to be yours. My brain runs on my own infra in my own repo under my own keys. Compare that to the default, which is not privacy. The default is your life is already scattered across 10 clouds owned by companies whose incentives are not yours, searchable by everyone except you. I didn't create the risk by consolidating my context. I took custody of it. Custody is the security model. And if you don't trust yourself to hold the keys, I promise you the answer isn't trusting someone else's terms of service more.

那么，为什么我把这一切都开源了？装备、大脑架构、技能、整个个人操作系统。人们问我这个，因为他们似乎觉得肯定有什么陷阱。答案是：因为我能。因为我在 YC，意味着我不需要把自己的基础设施变现。但“因为我能”也是错误问题的答案。真正的问题是：为什么每个人都应该这样做？答案是，我相信强者的工具应该被赠予。每个时代都有一种私有的杠杆技术，强者拥有而其他人没有。很长一段时间是读写能力，然后是资本，现在就是它：装备、图书馆、由 Markdown 构成的劳动力。拥有它的人，正在以不同于没有它的人的规模悄然运作，而且差距每个月都在扩大。这正是整个大会的意义所在：给你力量，让你能为自己做到。当如此强大的东西保持私有，你会得到祭司阶层；当它被赠予，你会得到文艺复兴。我知道我想生活在哪一个，这意味着我要去做我真正相信的事。我把它作为信条给你，因为它是我最接近信条的东西：说别人不会说的话，资助别人不会资助的人，建造别人不会建造的建筑，编写并赠予别人不会写的代码，留下别人不会留下的制度。

So why did I open source all of it? The harness, the brain architecture, the skills, the whole personal operating system. People ask me this because they seem like they think there must be a catch. Well, the answer is because I can. Because being at YC for me means I don't have to monetize my own infrastructure. But because I can is also the answer to the wrong question. The real question is why anyone should. And the answer is that I believe tools of the powerful should be given away. Every era has a private technology of leverage, a thing the powerful have and everyone else doesn't. For a long time it was literacy. Then it was capital. Right now today it's this. The harness, the library, the workforce made of markdown. The people who have it are quietly operating at a different scale than the people who don't. And the gap is widening every month. And that's what this whole conference is about. To give you the power to be able to do it for yourself. When something like that that powerful stays private, you get a priesthood. When it gets given away, you get a renaissance. I know which one I want to live in, which means I get to do the thing that I actually believe in. And I'll give it to you as a creed because it's the closest thing I have to one. Say the things other people won't. Fund the people other people won't. Build the buildings other people won't. Write and give away the code that other people won't. Leave behind the institutions that other people won't.

当你公开构建时，你应该知道会发生什么，因为斯宾诺莎的故事还有一章。1676 年 11 月，戈特弗里德·莱布尼茨，欧洲最耀眼的天才，穿着丝袜，行李里带着一台计算器，前往海牙，在阁楼里与欧洲大陆最被憎恨的人待了三天。然后他花了接下来的 40 年公开撒谎。那次访问只是“顺路几小时”。私下里，他的笔记里塞满了对斯宾诺莎的痴迷评论。我每周都经历一个小版本。我说“智能体现在写我大部分代码”，午餐前嘲讽就来了。然后我看那些最大声的嘲讽者实际在发布什么——全是智能体。所以，现在就学会这个模式，因为公开构建保证你会遇到它。首先，他们引用转发你，然后他们克隆你。那些嘲讽只是采用曲线在自我宣告。

And when you build in the open, you should know what's coming because Spinoza's story has one more chapter. November 1676, Gottfried Leibniz, the most glittering genius in Europe, silk stockings, a calculating machine in his luggage, travels to the Hague to spend three days in an attic with the most hated man on the continent. And then he spends the next 40 years lying about it publicly. The visit was a few hours in passing. Privately, his notes are crammed with obsessive commentary on Spinoza. I live a small version of this weekly. I say, "Agents write most of my code now," and the dunks arrive by lunch. Then I look at what the loudest dunkers are actually shipping, and it's agents all the way down. So, learn the pattern now because building in public guarantees you'll meet it. First, they quote tweet you, then they get clone you. The dunks are just the adoption curve announcing itself.

我想向你们展示，当这个架构指向唯一真正重要的东西时，它是什么样子。我有一个朋友，他的儿子患有一种罕见的癫痫。没有实验室，没有资助，没有许可。他只是去了——你可以直接去做事。他建立了一个包含 8 万个 Markdown 文件的仓库，一个为一个小男孩打造的大脑，把自己推到了人类关于他儿子确切状况的知识的绝对边缘。每一次专家就诊、每一篇论文、每一次癫痫发作日志、每一次药物相互作用，都被索引和交叉链接，随时准备好，这样当新医生有一个想法时，他几分钟内就能知道是否已经尝试过。一个父亲、一台笔记本电脑、一个图书馆。这就是个人 AGI。不是基准测试，不是演示。我今晚描述的整个架构——图书馆、图书管理员、正确的三本书在正确的时刻打开——指向一个人在这世上最爱的东西。没有人会来为他构建那个。所以他构建了。也没有人会来为你构建你的。这是好消息。你被告知需要的一切——团队、资金、许可、证书——都是对“一个人能在脑子里装七件事并每天工作 16 小时”这一事实的变通。那个事实刚刚过期了。你现在可以飞了。不是比喻，是机械意义上的。每一个你曾想“我希望有这个人才，我希望我能雇到这个人才，但我得不到”的问题——你现在可以了。每一个大到读不完的档案。

And I want to show you what this architecture looks like when it's pointed at the only thing that really matters. I have a friend whose son has a rare form of epilepsy. No lab, no grant, no permission. He just went and you can just do things. He built a repo of 80,000 markdown files, a brain for one small boy, and pushed himself to the absolute edge of what humanity knows about his son's exact condition. Every specialist visit, every paper, every seizure log, every drug interaction indexed and cross-linked and ready so that when a new doctor has an idea, he knows in minutes whether it's already been tried. A father, a laptop, and a library. That is personal AGI. Not a benchmark, not a demo. The entire architecture I've described tonight, the library, the librarian, the right three books, open at the right moment, aimed at the one thing one man loves the most in the world. Nobody was coming to build that for him. So, he built it. And nobody is coming to build yours for you. That's the good news. Everything you were told you needed, the team, the funding, the permission, the credential was a workaround for the fact that one person could hold seven things in their head and work 16 hours a day. That fact just expired. You can fly now. Not metaphorically, mechanically. Every problem where you thought, I wish I had this person. I wish I could hire this person, but I can't get them. You can. Every archive too big to read.

每一个脏得没法清理的数据集。每一片你被告知别去煮沸的海洋。我们现在能把海洋煮沸。我有一句我奉行的话，想留给你们：一切都是人编出来的，但你有权去编。世界上每一个机构，包括那个在 1656 年对一个 23 岁年轻人念诅咒的机构，都是不比你们聪明的人编出来的。你和之前每一代创始人的区别在于，他们必须先招募几十个信徒，才能开始建造任何东西。而你只需要一台笔记本电脑，加上你已经拥有的几年个人历史。整个活动大约有 7000 人。7000 个“坎诺图斯”，7000 份奋斗。在历史的大部分时间里，几乎所有这些奋斗都没有观众。它们死在等待资金、等待编制、等待许可、等待别人先相信的过程中。我今晚展示给你的机器，是我见过的第一种能让奋斗直接投入工作的技术。一个人，没有中间人，没有许可。我真的不认为世界已经明白，7000 个拥有这种杠杆的人走出大楼后会做出什么。斯宾诺莎用九个字结束了《伦理学》——那本必须藏在书桌里偷运出去的书：一切卓越的事物，既困难又稀有。困难刚刚崩塌了。稀有现在取决于你。去建造吧。谢谢。

Every data set too gnarly to clean. Every ocean you were told not to boil. We can boil the ocean. Now, I have a sentence I live by and I want to leave it with you. It's all made up, but you get to make it up. Every institution in the world, including the one that read a curse over a 23-year-old in 1656, was made up by people no smarter than you. The difference between you and every generation of founders before you is that they had to recruit dozens of believers before they could build anything at all. You need a laptop and a few years of your own history you're already sitting on. There were about 7,000 people at this whole event. 7,000 kannotuses, 7,000 strivings. For most of history, almost all of that striving never got an audience. It died waiting for funding, waiting for headcount, waiting for permission, waiting for someone else to believe first. The machinery I showed you tonight is the first technology I've ever seen that lets the striving go straight to work. One person, no intermediaries, no permission. I genuinely do not think the world understands yet what 7,000 people with that kind of leverage walk out of a building and do. Spinosa closed the ethics, the book that had to be smuggled out in a desk with nine words. All things excellent are as difficult as they are rare. The difficulty just collapsed. The rarity is now up to you. Go and build. Thank you.