Farzapedia：用日记+笔记打造个人 AI 维基
来源：X/Twitter 推文
作者：@karpathy
抓取时间：2026-04-25
Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet.
Farzapedia，Farza 的个人维基，是我那条 Wiki LLM 推文的优秀实践案例。
I really like this approach to personalization in a number of ways, compared to "status quo" of an AI that allegedly gets better the more you use it or something:
比起那些所谓"越用越智能"的 AI，我很喜欢这种个性化方案，原因有以下几点：
1. Explicit | 显性化
The memory artifact is explicit and navigable (the wiki), you can see exactly what the AI does and does not know and you can inspect and manage this artifact, even if you don't do the direct text writing (the LLM does). The knowledge of you is not implicit and unknown, it's explicit and viewable.
记忆载体是显性的、可导航的（以 wiki 形式存在），你可以精确看到 AI 知道什么、不知道什么，可以检查和管理这个载体——即使你并不直接写文本（LLM 会代劳）。关于你的知识不是隐含未知的，而是显性可见的。
2. Yours | 属于你
Your data is yours, on your local computer, it's not in some particular AI provider's system without the ability to extract it. You're in control of your information.
你的数据是你的，存在你自己的电脑上，它不属于某个特定 AI 服务商，你随时可以提取。你对自己的信息拥有完全控制权。
3. File over app | 文件优先于应用
The memory here is a simple collection of files in universal formats (images, markdown). This means the data is interoperable: you can use a very large collection of tools/CLIs or whatever you want over this information because it's just files. The agents can apply the entire Unix toolkit over them. They can natively read and understand them. Any kind of data can be imported into files as input, and any kind of interface can be used to view them as the output. E.g. you can use Obsidian to view them or vibe code something of your own.
这里的记忆是通用格式文件（图片、Markdown）的简单集合。这意味着数据是可互操作的：你可以用大量工具、CLI 等任何你想要的东西来处理这些信息，因为它们本质上就是文件。Agent 可以原生运用整个 Unix 工具链。它们能原生读取和理解这些文件。任何类型的数据都可以作为输入导入文件，任何类型的界面都可以用来查看输出。比如你可以用 Obsidian 查看，或者自己写代码做一个。
4. BYOAI（Bring Your Own AI）| 自带 AI
You can use whatever AI you want to "plug into" this information - Claude, Codex, OpenCode, whatever. You can even think about taking an open source AI and finetuning it on your wiki - in principle, this AI could "know" you in its weights, not just attend over your data.
你可以用任何你喜欢的 AI 来"接入"这些信息——Claude、Codex、OpenCode，随便什么。你甚至可以设想拿一个开源 AI 在你的 wiki 上微调——原则上，这个 AI 可以在它的权重中"了解"你，而不仅仅是读取你的数据。
So this approach to personalization puts you in full control. The data is yours. In Universal formats. Explicit and inspectable. Use whatever AI you want over it, keep the AI companies on their toes! :)
所以这种个性化方案让你完全掌控。你的数据是你的。用通用格式。显性且可检查。用任何你想要的 AI 来使用它，让 AI 公司保持警惕！:)
Certainly this is not the simplest way to get an AI to know you - it does require you to manage file directories and so on, but agents also make it quite simple and they can help you a lot. I imagine a number of products might come out to make this all easier, but imo "agent proficiency" is a CORE SKILL of the 21st century. These are extremely powerful tools - they speak English and they do all the computer stuff for you. Try this opportunity to play with one.
当然，这肯定不是让 AI 了解你的最简单方式——它确实需要你管理文件目录等，但 Agent 也让这件事变得相当简单，而且它们能帮你很多。我想象会有很多产品出来让这一切更容易，但依我看，"Agent 熟练度"是 21 世纪的核心技能。这些是非常强大的工具——它们说英语，能帮你做所有电脑上的事。找个机会试试吧。