Ian Maurmann ian-maurmann

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.

Disclaimer: I'm in the Top 1% of StackOverflow contributors with 23,315 rep points.

I asked 1 high-quality question in 2024, and it was closed almost immediately, and I haven't engaged with the site since.

If someone with 20,000+ karma has their nicely-formatted questions closed so quickly, what must the newbies and rank-in-file encounter? This is probably a big reason why it's declining.

	/**
	* Multibyte String Pad
	*
	* Functionally, the equivalent of the standard str_pad function, but is capable of successfully padding multibyte strings.
	*
	* @param string $input The string to be padded.
	* @param int $length The length of the resultant padded string.
	* @param string $padding The string to use as padding. Defaults to space.
	* @param int $padType The type of padding. Defaults to STR_PAD_RIGHT.
	* @param string $encoding The encoding to use, defaults to UTF-8.