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.

itstauq

#!/usr/bin/env python3
"""
Convert Claude Code and ChatGPT conversation exports to clean markdown.

Usage:
    python convert-ai-history.py --claude ~/.claude/projects --chatgpt ~/Downloads/conversations.json --output ~/openclaw/memory

    # Claude only
    python convert-ai-history.py --claude ~/.claude/projects --output ~/openclaw/memory

KMJ-007

Manage Multiple Claude Code Accounts

Run two Claude Code accounts simultaneously on macOS without re-authenticating by using separate configuration directories.

Steps

1. Create Separate Config Directories

   mkdir ~/.claude-account1
   mkdir ~/.claude-account2

Artefact2

Which GGUF is right for me? (Opinionated)

Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggml-org/llama.cpp#5962

In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.

llama.cpp feature matrix

See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix

cpursley

PostgreSQL is Enough

See the new site: https://postgresisenough.dev

---

• Simplify: move code into database functions
• Just Use Postgres for Everything
• Just use Postgres
• PostgreSQL is the worlds’ best database

hyperupcall

// I'm tired of extensions that automatically:
// - show welcome pages / walkthroughs
// - show release notes
// - send telemetry
// - recommend things
//
// This disables all of that stuff.
// If you have more config, leave a comment so I can add it!!

{

berkus

Conventional Commits with Emoji

Based on https://github.com/ellerbrock/conventional-commit-types-emoji for preview and on https://github.com/pvdlg/conventional-commit-types for the actial emoji images

🚨 There is a commit-emoji hook now to insert emoji automatically based on prefix, so you can just install it and use regular conventional commits (even using a tool like koji). 🚨

---

feat(xxx): ✨ Features your commit message

Gaelan

ChatGPT passes the 2022 AP Computer Science A free response section

For fun, I had ChatGPT take the free response section of the 2022 AP Computer Science A exam. (The exam also has a multiple-choice section, but the College Board doesn't publish this.) It scored 32/36.

Methodology

• For each question, I pasted in the full text of the question and took the response given.
• I tried each question once and took the response given: no cherry-picking. For readability, I've added indentation in some cases, and included method signatures where they were provided in the question and ChatGPT only provided a body. I've added question numbers; any other comments are ChatGPT's.
• Many questions have examples containing tables or diagrams; because those don't translate well to plain text, I excluded those tables/diagrams and any text that referenced them.
• I excluded the initial instructions at the top of th

netoht

# Pre-req
xcode-select --install
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

# Install podman
brew install podman

# Start vm
podman machine init
podman machine start

erikig