OpenAI's DevDay: a Codex agent ran over 1,000 hours keeping builds and tests passing
OpenAI · youtube · 2026-11-11
At OpenAI DevDay 2026, Aaron Friel (Engineering Acceleration) and Vaibhav Srivastav (Developer Experience) presented "What Will You Build With Coding Agents That Don't Quit?", centered on a Codex run that spent over 1,000 hours keeping builds and tests passing. The session covers choosing recurring tasks, improving feedback, managing token budgets, and deciding when engineers should step in.
More from coding & agent
- Skill Files Are the New Free Courses: $500 Expert Tutorials Now Exist as Markdown on GitHub — heyneighbor · 2026-11-11
- Why Harness Design May Become the System Design of the Agentic AI Era — kmeanskaran · 2026-11-11
- Alibaba ships Qwen Code 1.0, now runs three competing coding tools; Qwen4 Max Preview panned — teortaxesTex · 2026-11-11
- 'Compaction amnesia': how context compression quietly erases agent memory in long sessions — malliktwts · 2026-11-11
- Meituan's LongCat-2.5 tops 3DCodeBench at 55.4, open-sourced under MIT — dr_cintas · 2026-11-11
- Gemini 4 Carbon scores 57.3 vs top model's 58 at 1/4.5 the cost in real-repo bug test — koraykv · 2026-11-11