Jonathan Ragan-Kelley jrk

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.

This is an OPML version of the HN Popularity Contest results for 2025, for importing into RSS feed readers.

Plug: if you want to find content related to your interests from thousands of obscure blogs and noisy sources like HN Newest, check out Scour. It's a free, personalized content feed I work on where you define your interests in your own words and it ranks content based on how closely related it is to those topics.

Electron Apps Causing System-Wide Lag on Tahoe

This script detects apps with not yet updated versions of Electron.

Repo: https://github.com/tkafka/detect-electron-apps-on-mac

See:

What you NEED to Know Before Touching a Video File

Hanging out in subtitling and video re-editing communities, I see my fair share of novice video editors and video encoders, and see plenty of them make the classic beginner mistakes when it comes to working with videos. A man can only read "Use Handbrake to convert your mkv to an mp4 :)" so many times before losing it, so I am writing this article to channel the resulting psychic damage into something productive.

If you are new to working with videos (or, let's face it, even if you aren't), please read through this guide to avoid making mistakes that can cost you lots of time, computing power, storage space, or video quality.

Why did you do this?

Relax, I only have one Sunday to work on idea, literally my weekend project. So I tried Deepseek to see if it can help. Surprisingly, it works and it saves me another weekend...

What is your setup?

Just chat.deepseek.com (cost = free) with prompts adapted from this gist.

	# One-shot Codex: cdx "do x y and z"
	cdx() {
	codex -a on-request \
	--sandbox danger-full-access \
	exec \
	--skip-git-repo-check \
	"$*" 2>/dev/null
	}

	#cloud-config

	# Enable automatic package updates and upgrades during cloud-init execution
	package_update: true
	package_upgrade: true

	packages:
	# Security and Hardening
	- ufw
	- fail2ban

	/* converter.c
	*
	* This code converts `.md` files into `.html` files.
	*
	* The main use is to write a static website in `.md` files, and then run this
	* program to convert it to `.html`
	*
	* The program relies on the following variables:
	*
	* - INPUT_FOLDER: full path of the website with `.md` files.

	#!/usr/bin/perl

	## Put this (Perl) file in the root of your Overleaf project. It overrides the
	## `pdflatex` compilation command to run GhostScript as a post-process which will
	## compress non-JPEG images to JPEG in the output PDF file. The JPEG quality
	## settings are set to high to minimize the loss of image quality. This should
	## work well even for images that contain a lot of high-frequency noise.
	## To disable, simply rename the file to something other than latexmkrc.
	##
	## Created by Iliyan Georgiev.

	# THIS LINUX SETUP SCRIPT HAS MORPHED INTO A WHOLE PROJECT: HTTPS://OMAKUB.ORG
	# PLEASE CHECKOUT THAT PROJECT INSTEAD OF THIS OUTDATED SETUP SCRIPT.
	#
	#

	# Libraries and infrastructure
	sudo apt update -y
	sudo apt install -y \
	docker.io docker-buildx \
	build-essential pkg-config autoconf bison rustc cargo clang \