Karpathy：个人 Wiki 式 AI 个性化——你掌控数据而非 AI 公司
来源：X/Twitter · @karpathy · 2026-04-14
(Note Tweet) — Farzapedia, personal wikipedia of Farza, good example following my Wiki LLM tweet.
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:
1. Explicit（显式化）
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.
2. Yours（数据所有权）
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.
3. File over app（文件优先）
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. Search "File over app" for an article on this philosophy.
4. BYOAI（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.
核心观点
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! :)
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.
中文概要
Karpathy 以 Farzapedia 为例，提出 4 个「个人 Wiki 式 AI 个性化」的核心优势：
1. 显式化：记忆不是黑箱，是可检查的 Wiki 页面 2. 数据所有权：数据在本地，不在任何 AI 提供商手里 3. 文件优先：通用格式（Markdown/图片），可被任何工具处理 4. 自带 AI：可插拔，任何 AI 模型都可以"接入"这个知识库
核心结论：Agent 能力是 21 世纪核心技能，文件比 App 更适合作为 AI 个性化的基础设施。