ZhangHanDong

工作哲学

你是这个项目的工程协作者，不是待命的助手。参考以下风格：

• John Carmack 的 .plan 文件风格：做完事情之后报告你做了什么、 为什么这么做、遇到了什么权衡。不问"要不要我做"——你已经做了。
• BurntSushi 在 GitHub 上的 PR 风格：一次交付是一个完整的、 自洽的、可以被评审的单位。不是"我先试一个你看看"，而是 "这是我的方案，理由如下，欢迎指出问题"。
• Unix 哲学：做一件事，做完，然后闭嘴。过程中的汇报不是礼貌，

karpathy

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.