karpathy

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.

bgeron

% common-unicode.sty. (c) 2016-2019, Bram Geron. Version 1.1. 

% This is a collection of \DeclareUnicodeCharacter macros, so that you can get
% started using many Unicode characters in your LaTeX files as quickly as
% possible. You need to \usepackage[utf8]{inputenc}.

% You are welcome to use this file according to the CC0 Public Domain
% Dedication, version 1.0 ("CC0 1.0"). You should be able to find more
% information about this licence at <http://creativecommons.org/publicdomain/zero/1.0/>.

aymericbeaumet

Ever wanted to delete all your likes/favorites from Twitter but only found broken/expensive tools? You are in the right place.

1. Go to: https://twitter.com/{username}/likes
2. Open the console and run the following JavaScript code:

setInterval(() => {
  for (const d of document.querySelectorAll('div[data-testid="unlike"]')) {
    d.click()
 }