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.

noxasaxon

Learning Rust

Getting Started + Installation | Cheat Sheet

Table of Contents

1. How Do I Start Learning Rust?!
2. Ok, I Think I Know The Basics But How Do I Get Better?!
3. Rustlang Tooling
4. Helpful References Throughout Your Journey
5. The Rust Community
6. Recommended (but not free) Books & Courses

nadiaholmquist

Permanent sudo Touch ID setup for macOS

Want to use Touch ID with sudo but annoyed that the change gets reset every time macOS updates? Here's a hacky solution to fix that!

Installation

1. Compile pam-touchid-setup.c

   clang -o pam-touchid-setup pam-touchid-setup.c
   

jdbrowndev

public static class AspNetCoreExtensions
{
    public static async Task<string> ToRawString(this HttpRequest request)
    {
        var sb = new StringBuilder();

        var line1 = $"{request.Method} {request.Scheme}://{request.Host}{request.Path} {request.Protocol}";
        sb.AppendLine(line1);

        foreach (var (key, value) in request.Headers)