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.

ravarcheon

// ==UserScript==
// @name         the horse that stands in your way
// @namespace    http://tampermonkey.net/
// @version      2026-03-01
// @description  no more than 2 minutes of twitter. the first minute is a clear view, the second minute is where the horse slowly fades in. third minute and beyond there is nothing to see except horse
// @author       You
// @match        http://*.x.com/*
// @match        https://*.x.com/*
// @match        http://*.instagram.com/*
// @match        https://*.instagram.com/*

willccbb

# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
"""
citation:

@misc{brown2025grpodemo,
  title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
  author={Brown, William},

OrionReed

// 3D Dom viewer, copy-paste this into your console to visualise the DOM as a stack of solid blocks.
// You can also minify and save it as a bookmarklet (https://www.freecodecamp.org/news/what-are-bookmarklets/)
(() => {
  const SHOW_SIDES = false; // color sides of DOM nodes?
  const COLOR_SURFACE = true; // color tops of DOM nodes?
  const COLOR_RANDOM = false; // randomise color?
  const COLOR_HUE = 190; // hue in HSL (https://hslpicker.com)
  const MAX_ROTATION = 180; // set to 360 to rotate all the way round
  const THICKNESS = 20; // thickness of layers
  const DISTANCE = 10000; // ¯\\_(ツ)_/¯

gd3kr

/*
the twitter api is stupid. it is stupid and bad and expensive. hence, this. 

Literally just paste this in the JS console on the bookmarks tab and the script will automatically scroll to the bottom of your bookmarks and keep a track of them as it goes. 

When finished, it downloads a JSON file containing the raw text content of every bookmark. 

for now it stores just the text inside the tweet itself, but if you're reading this why don't you go ahead and try to also store other information (author, tweetLink, pictures, everything). come on. do it. please?
*/

ayoubzulfiqar

Go - The Ultimate Folder Structure

Organizing your Go (Golang) project's folder structure can help improve code readability, maintainability, and scalability. While there is no one-size-fits-all structure, here's a common folder structure for a Go project:

project-root/
    ├── cmd/
    │   ├── your-app-name/
    │   │   ├── main.go         # Application entry point
    │   │   └── ...             # Other application-specific files

Yimiprod

/**
 * This code is licensed under the terms of the MIT license
 *
 * Deep diff between two object, using lodash
 * @param  {Object} object Object compared
 * @param  {Object} base   Object to compare with
 * @return {Object}        Return a new object who represent the diff
 */
function difference(object, base) {
	function changes(object, base) {

gustavohenke

var svg = document.querySelector( "svg" );
var svgData = new XMLSerializer().serializeToString( svg );

var canvas = document.createElement( "canvas" );
var ctx = canvas.getContext( "2d" );

var img = document.createElement( "img" );
img.setAttribute( "src", "data:image/svg+xml;base64," + btoa( svgData ) );

img.onload = function() {