Claude Code and Codex Run Research Autonomously

willccbb · x · 2026-07-13

Prime Intellect conducted an "automated AI research" experiment, allowing Claude Code (Opus 4.7) and Codex (GPT 5.5) to run autonomously on the nanoGPT speedrun optimizer track using idle compute.

The results included:

The focus here is not a model release, but rather a demonstration of a workflow using coding agents to automate research and optimization.

Original post →

More from coding & agent

coding & agent channel →