Lwdthe1

[
	{ "city": "Abbeville", "state": "Louisiana" },
	{ "city": "Aberdeen", "state": "Maryland" },
	{ "city": "Aberdeen", "state": "Mississippi" },
	{ "city": "Aberdeen", "state": "South Dakota" },
	{ "city": "Aberdeen", "state": "Washington" },
	{ "city": "Abilene", "state": "Texas" },
	{ "city": "Abilene", "state": "Kansas" },
	{ "city": "Abingdon", "state": "Virginia" },
	{ "city": "Abington", "state": "Massachusetts" },

loilo

export function magicMethods (clazz) {
  // A toggle switch for the __isset method
  // Needed to control "prop in instance" inside of getters
  let issetEnabled = true

  const classHandler = Object.create(null)

  // Trap for class instantiation
  classHandler.construct = (target, args, receiver) => {
    // Wrapped class instance

DavidKuennen

(function (context, trackingId, options) {
    const history = context.history;
    const doc = document;
    const nav = navigator || {};
    const storage = localStorage;
    const encode = encodeURIComponent;
    const pushState = history.pushState;
    const typeException = 'exception';
    const generateId = () => Math.random().toString(36);
    const getId = () => {

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.