WIRED: OpenAI is building a 'Persistent mode' so Codex keeps working until put to sleep
nordicinst · x · 2026-08-28
WIRED reviewed changes to OpenAI's codebase and found the company is developing a "Persistent mode" for its flagship agent Codex: a proactive, highly persistent version that keeps working until it is "put to sleep."
Key points:
- The code has landed in the public Codex CLI repo; new features typically surface there before reaching the desktop app and ChatGPT Work
- The setting appears in Codex's "reasoning effort" menu alongside compute/token levels
- An OpenAI spokesperson confirmed testing but said there are no immediate launch plans
- Thibault Sottiaux, head of core products, called the open-source repo "a bit of our shared playground" in OpenAI's bottoms-up culture
Context: OpenAI, Anthropic and Meta are racing on general-purpose agents; today's users are mostly software engineers, but Silicon Valley sees a far broader business.
Related event: OpenAI's Codex Gears Up "Persistent Mode" for Always-On Autonomous Agents(12 posts)→
More from coding & agent
- Python 3.15 ships: lazy imports, frozendict, and a faster experimental JIT — _jaydeepkarale · 2026-10-15
- "Agentic coding 10x's developers" — the code, the bugs, and the people pretending to read the diff — blaizedsouza · 2026-10-15
- OWASP publishes Non-Human Identities Top 10 for securing machine and AI agent identities — gleech · 2026-10-15
- Hot Take: Agentic Automation of Mundane IT Is a Gold Mine — and Extremely Hard — Paimaamu · 2026-10-15
- Open-source 386-page 3D Vibe Coding handbook: GPT-Image to Tripo to Blender, with playable demos — AlchainHust · 2026-10-15
- Simple Trick for Better AI Agent Runs: Tell It What NOT to Touch — thisiskp_ · 2026-10-15