Running autoresearch Hands-On — Overnight Experiments on a Single GPU

Running autoresearch Hands-On — Overnight Experiments on a Single GPU

In Part 1, we looked at how Karpathy's autoresearch is structured. Here's the three-line summary:

1. A single train.py contains the GPT model + optimizer + training loop.
2. An AI agent (Claude Code, etc.) modifies this file, trains for 5 minutes, and keeps the change if val_bpb improves — otherwise discards it.
3. program.md defines the agent's behavior rules. Humans only edit this markdown file.

In Part 2, we'll set up the environment, launch the agent, and analyze the results from an overnight run.

Environment Setup — Getting Started

Requirements

You don't need an H100. It runs on 4090, A100, 3090, and more. The difference is how many tokens get processed within the fixed 5-minute budget. We'll cover GPU-specific tuning later.