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.

karpathy

"""
The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
This file is the complete algorithm.
Everything else is just efficiency.

@karpathy
"""

import os       # os.path.exists
import math     # math.log, math.exp

danawoodman

React "Hello World" Examples

Below are a small collection of React examples to get anyone started using React. They progress from simpler to more complex/full featured.

They will hopefully get you over the initial learning curve of the hard parts of React (JSX, props vs. state, lifecycle events, etc).

Usage

You will want to create an index.html file and copy/paste the contents of 1-base.html and then create a scripts.js file and copy/paste the contents of one of the examples into it.

cuppster

/*
  modified from original source: https://bitbucket.org/mattkotsenas/c-promises/overview
*/

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;

namespace Promises