OpenAI Is Developing a ‘Persistent’ AI Agent
OpenAI is testing a new 'Persistent mode' for its Codex AI agent that allows the model to work on tasks indefinitely until manually stopped. This feature aims to move AI agents beyond simple query-response interactions toward autonomous task completion.
Why it matters
Persistent AI agents represent a significant shift in utility, potentially enabling automation of complex, multi-step workflows that currently require human intervention.
OpenAI is developing a proactive, highly persistent version of its flagship AI agent, Codex, WIRED has learned.
The article reports on technical developments and corporate strategy without taking a political stance or using loaded language.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in