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.

johannaratliff

Context

This is for programmers who want to ramp on Go, without resources that reiterate programming fundamentals. This would not be a good list of resources for folks who are learning to program using Go as their first language. Some resources that I dismiss here would be super valuable for newer folks. This is a selection of resources for those who understand programming fundamentals in a different language already.

Advice

1. First steps = Tour of Go
2. Don't waste time on Go Fundamentals-type books - it all lives in tour of Go.
3. Consider joining the Gophers Slack
4. When you need help, the Go Playground allows you make a quick scratch file and share it. Others trying to help can run your code easily this way.