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

ncdulo

#!/usr/bin/env bash

# Enable or disable Intel Turbo-Boost
# Requires msr kernel module to be built and loaded
# Will ask for root privileges when the time comes
# Copied, with love, from:
# https://notepad2.blogspot.com/2014/11/a-script-to-turn-off-intel-cpu-turbo.html

if [[ -z $(which rdmsr) ]]; then
    echo "msr-tools is not installed. Run 'sudo apt-get install msr-tools' to install it." >&2

natelandau

#  ---------------------------------------------------------------------------
#
#  Description:  This file holds all my BASH configurations and aliases
#
#  Sections:
#  1.   Environment Configuration
#  2.   Make Terminal Better (remapping defaults and adding functionality)
#  3.   File and Folder Management
#  4.   Searching
#  5.   Process Management