How Codex agents can run 700 experiments and keep only the best 20

iamrobotbear · x · 2026-07-21

- A linked article describes how to build a self-improving outbound system on Codex. - It cites Andrej Karpathy pointing an agent at his own training code for two days, during which it ran **700 experiments** and kept the **20** that beat the benchmark. - The example frames outbound optimization as an agentic workflow: let the system explore, evaluate, and retain only the best-performing variants.

Original post →

More from coding & agent

coding & agent channel →