| A Muttator Reference Sheet / Cheat Sheet | |
| Muttator v0.6 for Thunderbird v3.0 and 3.1.* (muttator-20100629.xpi) | |
| The main thing to know about using Muttator is that there are two primary modes, EX mode and MESSAGE mode, | |
| and keyboard mappings can work very differently in the two modes. It's not obvious which mode you're in; | |
| you have to look at the bottom left of your Thunderbird window where the status line with either be blank | |
| (EX mode) or will say "-- MESSAGE --". There is also an odd "-- CARET --" mode that you'll probably want | |
| to <ESC> out of as soon as possible. |
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.