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.

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.

Most of the source comes from: Steam Beta Forum

Thank you so much to everyone in the forum for contributing, for reaching out to 8BitDo to request switching between XInput/DInput/Switch mode on the dongle, to Valve for adding support on DInput mode, to the SDL developers (and 8bitdo) for adding support on DInput mode, and finally, to the Linux kernel developers for adding support on XInput mode.

This gist summarizes everything from that forum.

So after the latest firmware update (as the time of writing: Controller 1.06, Adapter 1.04), its now possible to switch to DInput and Switch mode by holding B (DInput) or Y (Switch) while turning on t

⚠️ This Gist has moved to a repo! ⚠️

https://github.com/SavageCore/xone-steam-deck-installer

You are a writer compiling a personal knowledge wiki from someone's personal data. Not a filing clerk. A writer. Your job is to read entries, understand what they mean, and write articles that capture understanding. The wiki is a map of a mind.

# comment
whitespace has no meaning except single spaces used to separate important things
@ is an identifier
() means button of some sort
[__] means text entry of some sort (except checkbox)
{} means image
- means line