Compiling knowledge, not retrieving it: a hands-on deep dive into llm-wiki-compiler

The thesis of this piece is simple and uncomfortable: the problem of making an LLM “remember” what you’ve read isn’t solved with more…

elvis on Twitter / X

Diagram of the LLM Knowledge Base system.Feed this to your favorite agent and get your own LLM knowledge base going. https://t.co/4AQSFOv4PV pic.twitter.com/nPSNi4Ayqv— elvis (@omarsar0) April 3, 2026

llm-wiki

llm-wiki · GitHub

"Useful" is not sufficient

So Linus Torvalds, head of the Linux kernel development, put his foot down on the Linux Kernel development mailing list when someone was bringing up criticism of LLMs: “Linux is not one of those anti-AI projects, and if somebody has issueswith that, they can do the open-source thing and fork it. Or just walk away. […]

I rebuilt Karpathy's LLM Wiki gist: what's missing

Karpathy's original LLM Wiki gist, explained and rebuilt as a working system. 44 open-source commands, plus the five things the gist leaves out.

Yuchen Jin on Twitter / X

Karpathy’s “LLM Wiki” pattern: stop using LLMs as search engines over your docs. Use them as tireless knowledge engineers who compile, cross-reference, and maintain a living wiki. Humans curate and think.Diagram generated by my Claude agent knowledge worker. https://t.co/5u5i1GeFK8 pic.twitter.com/NIaq3KlAok— Yuchen Jin (@Yuchenj_UW) April 4, 2026

Karpathy's LLM Wiki: The Complete Guide to His Idea File

Karpathy's follow-up gist went viral. Complete breakdown with implementation examples.

nber_hf_2026/slides.pdf at main · paulgp/nber_hf_2026

Contribute to paulgp/nber_hf_2026 development by creating an account on GitHub.

Building Nostr - A Guide for Developers

Translating non-trivial codebases with Claude

I don’t think it’s [me writing about LLMs] likely to happen anytime soon: I prefer to write about things that I’m excited about.

prime-radiant-inc/engineering-notebook

CLI tool that ingests Claude Code sessions, generates LLM summaries, and serves a browsable engineering journal

Meet the Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases

Meet the Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases

VaultGemma: The world's most capable differentially private LLM

Amer Sinha, Software Engineer, and Ryan McKenna, Research Scientist, Google Research

We Got Claude to Fine-Tune an Open Source LLM

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

fry69 (@fry69.dev)

Retired guessworker. Still searching for the missing context. Love LLMs, programming and system administration. 📌 Germany 🌍 https://fry69.dev/ (placeholder) 🧑‍💻 https://github.com/fry69/ 🅿️ https://altq.net/ @altq.net (PDS) Archived account: @fry69.altq.net