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

minimaxir

Agent Guidelines for Rust Code Quality

This document provides guidelines for maintaining high-quality Rust code. These rules MUST be followed by all AI coding agents and contributors.

Your Core Principles

All code you write MUST be fully optimized.

"Fully optimized" includes:

minimaxir

Agent Guidelines for Python Code Quality

This document provides guidelines for maintaining high-quality Python code. These rules MUST be followed by all AI coding agents and contributors.

Your Core Principles

All code you write MUST be fully optimized.

"Fully optimized" includes:

mholtzhausen

#!/usr/bin/env python3

"""
Convert YouTube subtitles(vtt) to human readable text.
This script is designed to be used as a command-line tool,
reading from stdin and writing to stdout.

Example Usage:
yt-dlp --skip-download --sub-langs en --convert-subs vtt -o ~/.tmp.subtitle <video_url> | vtt2txt; cat ~/.tmp.subtitle.en.vtt | vtt2txt | fabric -ps extract_wisdom
"""

cavedave

vfarcic

##############################################################
# How to run local multi-node Kubernetes clusters using kind #
# https://youtu.be/C0v5gJSWuSo                               #
##############################################################

#########
# Setup #
#########

# Install kind (https://kind.sigs.k8s.io/docs/user/quick-start/#installation)

ChristopherA

Brew Bundle Brewfile Tips

Copyright & License

Unless otherwise noted (either in this file or in a file's copyright section) the contents of this gist are Copyright ©️2020 by Christopher Allen, and are shared under spdx:Creative Commons Attribution Share Alike 4.0 International (CC-BY-SA-4.) open-source license.

Sponsor

If you more tips and advice like these, you can become a monthly patron on my GitHub Sponsor Page for as little as $5 a month; and your contributions will be multipled, as GitHub is matching the first $5,000! This gist is all about Homebrew, so if you like it you can support it by donating to them or becoming one of their Github Sponsors.

geerlingguy

#!/bin/bash
#
# Update things to be compatible with Molecule 3.0.
#
# This script is NOT idempotent, and should never be run again.
exit 1

export LINT_STRING="lint: |
  set -e
  yamllint .

pmkay

node: Platform built on V8 to build network applications
git: Distributed revision control system
wget: Internet file retriever
yarn: JavaScript package manager
python3: Interpreted, interactive, object-oriented programming language
coreutils: GNU File, Shell, and Text utilities
pkg-config: Manage compile and link flags for libraries
chromedriver: Tool for automated testing of webapps across many browsers
awscli: Official Amazon AWS command-line interface
automake: Tool for generating GNU Standards-compliant Makefiles