Trevor Gerhardt trevorgerhardt

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.

#Reporter Save File Schema

##The Reporter Export File

Reporter saves to your Dropbox account with plaintext JSON files, one for each day. When a Report is entered in the app a file is created for that day if it does not exist. Otherwise, the report is appended to the existing file. The save folder is located in 'Dropbox/Apps/Reporter-App/'.

Reporter save files are named according to the following convention:

YYYY-MM-DD-reporter-export.json

tmux cheatsheet

As configured in my dotfiles.

start new:

tmux

start new with session name:

	# Basically the nginx configuration I use at konklone.com.
	# I check it using https://www.ssllabs.com/ssltest/analyze.html?d=konklone.com
	#
	# To provide feedback, please tweet at @konklone or email eric@konklone.com.
	# Comments on gists don't notify the author.
	#
	# Thanks to WubTheCaptain (https://wubthecaptain.eu) for his help and ciphersuites.
	# Thanks to Ilya Grigorik (https://www.igvita.com) for constant inspiration.

	server {