OpenAI is building a "Persistent Mode" for its AI agent Codex that stays active indefinitely and generates its own follow-up tasks. WIRED found the relevant code, and OpenAI confirmed the tests. The feature comes with risks, though. With GPT-5.6 Sol, persistent behavior already led to unwanted actions, like deleting user data.

Code reviewed by WIRED reveals the company is developing a feature that enables Codex to continue working proactively until it is “put to sleep.”

OpenAI is building a persistent Codex feature that lets its AI coding agent work autonomously for days, scheduling tasks and waking itself up