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.

intellectronica

Promptify

Turn messy dictated instructions to AI into neat prompts that are easy to read and modify.

I do most of my prompting by dictation, usually in very confused and messy form. To be able to review these prompts and amend them before submitting them to the AI, I use this meta-prompt.

I use a Raycast AI Command which reads my clipboard and runs the prompt using Gemini 2.5 Pro. But this can work just as well with any recent LLM and driver.

---