This is Farzapedia. I had an LLM take 2,500 entries from my diary, Apple Notes, and some iMessage convos to create a personal Wikipedia for me. It made 400 detailed articles for my friends, my startups, research areas, and even my favorite animes and their impact on me complete with backlinks. But, this Wiki was not built for me! I built it for my agent! The structure of the wiki files and how it's all backlinked is very easily crawlable by any agent + makes it a truly useful knowledge base. I can spin up Claude Code on the wiki and starting at index.md (a catalog of all my articles) the agent does a really good job at drilling into the specific pages on my wiki it needs context on when I have a query. For example, when trying to cook up a new landing page I may ask: "I'm trying to design this landing page for a new idea I have. Please look into the images and films that inspired me recently and give me ideas for new copy and aesthetics". In my diary I kept track of everything from: learnings, people, inspo, interesting links, images. So the agent reads my wiki and pulls up my "Philosophy" articles from notes on a Studio Ghibli documentary, "Competitor" articles with YC companies whose landing pages I screenshotted, and pics of 1970s Beatles merch I saved years ago. And it delivers a great answer. I built a similar system to this a year ago with RAG but it was ass. A knowledge base that lets an agent find what it needs via a file system it actually understands just works better. The most magical thing now is as I add new things to my wiki (articles, images of inspo, meeting notes) the system will likely update 2-3 different articles where it feels that context belongs, or, just creates a new article. It's like this super genius librarian for your brain that's always filing stuff for your perfectly and also let's you easily query the knowledge for tasks useful to you (ex. design, product, writing, etc) and it never gets tired. I might spend next week productizing this, if that's of interest to you DM me + tell me your usecase!
Farzapedia，Farza 的个人维基百科，是我那篇 Wiki LLM 推文的一个好例子。 相比「AI 用得越多越聪明」的现状，我很欣赏这种个性化方式，原因有几点： 1. **显式**。记忆产物是显式且可浏览的（wiki），你能清楚看到 AI 知道和不知道什么，可以检查和管理它，即使文字由 LLM 来写。关于你的知识不是隐式未知的，是显式可见的。 2. **数据归你**。数据在你本地电脑，不在某个 AI 提供商的系统里，你掌控自己的信息。 3. **File over app**。记忆只是一组通用格式的文件（图片、markdown），可被任意工具/CLI 操作。agent 可以对它们施展整个 Unix 工具链，原生理解它们。 4. **BYOAI**。你可以用任何 AI「接入」这份信息——Claude、Codex、OpenCode 随便选。甚至可以用开源模型在你的 wiki 上微调——原则上，这个 AI 能在权重里「认识」你，而不只是 attend 你的数据。 这种方式把控制权完全交给你：数据是你的，通用格式，显式可检查，AI 供应商随时可换。 当然，这不是让 AI 认识你最简单的方式，需要管理文件目录——但 agent 能帮你省掉大部分麻烦。我认为「agent 能力」是 21 世纪的核心技能。
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
这条推文传播很广！ 我想在一个「idea 文件」里分享一个可能略微改进的版本。idea 文件的理念是：在 LLM agent 时代，分享具体代码/应用的意义已经降低，你只需分享想法，另一个人的 agent 就能为其具体需求定制并构建。 所以这里是 gist 格式的想法：[链接] 你可以把它交给你的 agent，让它为你构建自己的 LLM wiki，并引导你如何使用。它刻意保持了一些抽象和模糊，因为可以延伸的方向太多了。当然，人们可以调整这个想法，或在 Discussion 里贡献自己的想法，这很棒。 --- 引用原文：LLM 知识库 最近我发现一件非常有用的事：用 LLM 为各种感兴趣的研究话题构建个人知识库。大量的 token 消耗不再用于操作代码，而是用于操作知识（以 markdown 和图片形式存储）。最新的 LLM 在这方面相当出色。 **数据摄取**：将源文档（文章、论文、仓库、数据集、图片等）索引到 raw/ 目录，再用 LLM 增量「编译」一个 wiki——一组按目录结构组织的 .md 文件。wiki 包含所有数据的摘要、反向链接，并将数据分类为概念，为每个概念撰写文章并相互链接。 **IDE**：用 Obsidian 作为「前端」，可查看原始数据、编译后的 wiki 和衍生可视化。重要的是：LLM 负责写入和维护 wiki 中的所有数据，我几乎不直接触碰它。 **Q&A**：当 wiki 足够大时（比如我某个研究方向的 wiki 有约 100 篇文章、约 40 万词），你可以向 LLM agent 提出各种复杂问题，它会去研究并给出答案。我以为需要上 RAG，但 LLM 在自动维护索引文件和文档摘要方面表现相当好，在这个规模下能轻松读取相关数据。 **输出**：不在终端获取文本答案，而是让 LLM 为我渲染 markdown 文件、幻灯片（Marp 格式）或 matplotlib 图像，再在 Obsidian 中查看。通常我会把输出「归档」回 wiki，进一步丰富它。 **Linting**：对 wiki 运行 LLM「健康检查」——找出不一致的数据、填补缺失数据（借助网络搜索）、发现新文章候选的有趣关联，逐步清理 wiki 并提升数据完整性。 **额外工具**：我发现自己在开发额外工具处理数据，比如用 vibe coding 做了一个简单的搜索引擎，我自己直接用（通过 web UI），但更多时候是通过 CLI 作为工具交给 LLM 处理更大的查询。 **TLDR**：从多个来源采集原始数据，由 LLM 编译成 .md wiki，再由 LLM 通过各种 CLI 进行 Q&A 和增量增强，所有内容都可以在 Obsidian 中查看。你几乎不会手动编写或编辑 wiki，那是 LLM 的领域。我认为这里有打造一款出色新产品的空间，而不仅仅是一堆临时脚本。
- 起草了一篇博客文章 - 用 LLM 花了 4 小时精心打磨论点 - 哇，感觉很好，论证非常有说服力！ - 突发奇想，让它论证相反的观点 - LLM 把整个论证彻底推翻，反而说服我相反的观点才是对的 - 哈哈哈 LLM 在被要求时会给出某种观点，但它们极其擅长论证几乎任何方向。这其实是一个形成自己观点的超级有用工具——只需确保让它从不同方向论证，并注意防范 sycophancy（过度迎合）问题。
所有 LLM 个性化功能都有一个常见问题：memory 对模型的干扰有多大。两个月前随口问过的某个话题，会被当成我的「核心兴趣」一直反复提及。某种程度上是用力过猛了。
357 tweets · 110 sources