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.

xCONFLiCTiONx

##above is your settings##
[Custom Colors]
01=#000000
02=#0A246A
03=#3A6EA5
04=#52A5F8
05=#0D8206
06=#608020
07=#648000
08=#A46000

earthgecko

#!/bin/bash
# bash generate random alphanumeric string
#

# bash generate random 32 character alphanumeric string (upper and lowercase) and 
NEW_UUID=$(cat /dev/urandom | tr -dc 'a-zA-Z0-9' | fold -w 32 | head -n 1)

# bash generate random 32 character alphanumeric string (lowercase only)
cat /dev/urandom | tr -dc 'a-z0-9' | fold -w 32 | head -n 1

jasny

#!/bin/bash

####
# Split MySQL dump SQL file into one file per table
# based on http://blog.tty.nl/2011/12/28/splitting-a-database-dump
####

if [ $# -lt 1 ] ; then
  echo "USAGE $0 DUMP_FILE [TABLE]"
  exit