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.

jph00

Hypermedia Systems: book summary

This is a summary of "Hypermedia Systems" by Carson Gross, Adam Stepinski, Deniz Akşimşek. Summary created by Jeremy Howard with AI help.

• Website for the book
• The revolutionary ideas that empowered the Web
• A simpler approach to building applications on the Web and beyond with htmx and Hyperview
• Enhancing web applications without using SPA frameworks

1: Hypermedia: A Reintroduction

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)_/¯

yoavg

Some remarks on Large Language Models

Yoav Goldberg, January 2023

Audience: I assume you heard of chatGPT, maybe played with it a little, and was imressed by it (or tried very hard not to be). And that you also heard that it is "a large language model". And maybe that it "solved natural language understanding". Here is a short personal perspective of my thoughts of this (and similar) models, and where we stand with respect to language understanding.

Intro

Around 2014-2017, right within the rise of neural-network based methods for NLP, I was giving a semi-academic-semi-popsci lecture, revolving around the story that achieving perfect language modeling is equivalent to being as intelligent as a human. Somewhere around the same time I was also asked in an academic panel "what would you do if you were given infinite compute and no need to worry about labour costs" to which I cockily responded "I would train a really huge language model, just to show that it doesn't solve everything!". We

anuraghazra

Variables

const shade = 100;
type Shade = 100;

Functions

DavidWells

/* Ultra lightweight Github REST Client */
// original inspiration via https://gist.github.com/v1vendi/75d5e5dad7a2d1ef3fcb48234e4528cb
const token = 'github-token-here'
const githubClient = generateAPI('https://api.github.com', {
  headers: {
    'User-Agent': 'xyz',
    'Authorization': `bearer ${token}`
  }
})

DavidWells

/* Using a JavaScript proxy for a super low code REST client */
// via https://dev.to/dipsaus9/javascript-lets-create-aproxy-19hg
// also see https://towardsdatascience.com/why-to-use-javascript-proxy-5cdc69d943e3
// also see https://github.com/fastify/manifetch
// also see https://github.com/flash-oss/allserver
// and https://gist.github.com/v1vendi/75d5e5dad7a2d1ef3fcb48234e4528cb

const createApi = (url) => {
  return new Proxy({}, {
    get(target, key) {

marco-prontera

var icqLibrary = icqLibrary || {};
icqLibrary.queue = icqLibrary.queue || [];

icqLibrary.queue.push(() => {
  console.log('Queue 1');
});
icqLibrary.queue.push(() => {
  console.log('Queue 2');
});

oliverjumpertz

<dialog open>
  <form method="dialog">
    <p>Do you want to confirm your action?</p>
    <div class="right">
      <input class="btn" type="submit" value="Ok" />
      <input class ="btn" type="submit" value="Cancel" />
    </div>
  </form>
</dialog>

mrtcmn

@supports (-webkit-backdrop-filter: none) or (backdrop-filter: none) {
  .blurred-container {
    -webkit-backdrop-filter: blur(10px);
    backdrop-filter: blur(10px);
  }
}

/* slightly transparent fallback for Firefox (not supporting backdrop-filter) */
@supports not ((-webkit-backdrop-filter: none) or (backdrop-filter: none)) {
  .blurred-container {