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.

obullxl

import java.awt.AWTException;
import java.awt.Rectangle;
import java.awt.Robot;
import java.awt.Toolkit;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;
import javax.imageio.ImageIO;

public class ScreenSnapshot { 

ufologist

<!-- test pass with CryptoJS v3.1.2 -->
<script src="rollups/tripledes.js"></script>
<script src="components/mode-ecb.js"></script>
<script>
/**
 * Encrypt message by DES in ECB mode and Pkcs7 padding scheme
 *
 * NOTE: DES is weak, please use 3DES(Triple DES) or AES
 * 
 * @param  {String} message

tariqmislam

=================================================================
SETTING UP SSHD AS A SERVICE FOR RUNNING HADOOP DAEMONS ON WINDOWS 7
=================================================================

Steps:

1. Download 'setup.exe' from Cygwin website
2. Right-click on 'setup.exe' 
3. Leave settings as they are, click through until you come to the plugin selection window
	3.1 - Make sure that the installation directory is 'C:\cygwin'