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.

redoPop

# This is a template .gitignore file for git-managed WordPress projects.
#
# Fact: you don't want WordPress core files, or your server-specific
# configuration files etc., in your project's repository. You just don't.
#
# Solution: stick this file up your repository root (which it assumes is
# also the WordPress root directory) and add exceptions for any plugins,
# themes, and other directories that should be under version control.
#
# See the comments below for more info on how to add exceptions for your