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.

correlations.R

# Detecting correlation

# Defines three functions using base R to illustrate techniques for identifying correlations
# between continuous random variables, then tests against different types of data

# Pearsons r, distance correlation, Maximal Information Coefficient (approximated)

# A simple bootstrap function to estimate confidence intervals
bootstrap <- function(x,y,func,reps,alpha){
  estimates <- c()

dtuite

// Originally found at: http://rangevoting.org/Qnorm.html

/** * @(#)qnorm.js * * Copyright (c) 2000 by Sundar Dorai-Raj
  * * @author Sundar Dorai-Raj
  * * Email: sdoraira@vt.edu
  * * This program is free software; you can redistribute it and/or
  * * modify it under the terms of the GNU General Public License 
  * * as published by the Free Software Foundation; either version 2 
  * * of the License, or (at your option) any later version, 
  * * provided that any use properly credits the author.