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.
More from coding & agent
- Codex turns out 123 screensavers in one playful batch — intellectronica · 2026-07-21
- Grok Build adds `grok doctor`, resumable sessions and remote image paste — mark_k · 2026-07-21
- Autoresearch proposes packaging ML runs as studies with questions, analysis, and code diffs — morgymcg · 2026-07-21
- CHAP defines approvals, handoffs, and audit logs for human-agent workflows — DeliveryTechnical199 · 2026-07-21
- The author says Codex reached 20x and is now debugging spec decoding on a hybrid parallel setup — TheZachMueller · 2026-07-21
- Axcess adds an MCP connector for WCAG accessibility checks that scanners miss — modelcontextprotocol · 2026-07-21