OpenAI DevDay talk: how Codex ran autonomously for 1,000 hours, plus agent tips
reach_vb · x · 2026-11-05
At OpenAI's DevDay Exchange in London, OpenAI's VB sat down with John Crickett to discuss how startups can get the most out of Codex:
- Long-running AI agents: Codex ran autonomously for 1,000 hours;
- practical context management and choosing the right models per task;
- tips for building faster, and what OpenAI for Developers entails.
Useful material for developers building workflows around coding agents.
More from coding & agent
- Developer ships Drivr Glass: voice-first Grok cabin bot now displays cards in-car — bfrench · 2026-11-06
- Traveler says Grok bot planned and paid for his months-long Asia trip from just two context files — eptwts · 2026-11-06
- Aware lets you summon AI anywhere with @aware instead of a chat window — HaijunXia · 2026-11-06
- GitHub MCP server to replace server instructions with Agent Skills, aiming to save tokens — DanWahlin · 2026-11-06
- GitHub launches Copilot Fusion, a runtime router that auto-picks models and execution patterns — adnan_hashmi · 2026-11-06
- DIY AI Employee Factory: The 'Employee Zero' Template That Survives Crashes and Model Swaps — leebase65 · 2026-11-06