Skip to content

Instantly share code, notes, and snippets.

View yoctozepto's full-sized avatar

Radosław Piliszek yoctozepto

View GitHub Profile

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.

@aaronmdjones
aaronmdjones / freenode-resign-letter.txt
Created May 19, 2021 10:20
My resignation from freenode
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA512
My resignation from freenode staff
==================================
I joined the freenode staff in March 2019 [1].
Before I joined the staff, Freenode Ltd was sold [2] to a person named
Andrew Lee as part of a sponsorship deal. The informal terms of that