OpenAI developing persistent AI agent feature for Codex
OpenAI is developing a persistent AI agent feature that allows its Codex system to continue working proactively on tasks rather than waiting for user input after each action. According to code reviewed by WIRED, this agent can operate continuously until it is deliberately halted or 'put to sleep.' This represents a significant step toward more autonomous AI systems capable of independent task completion.
Readers say
How does this story lean?
Outlet ratings above are Trace's curated source map. Vote here (same as on the home feed) — one vote per browser, changeable anytime. Rate individual outlets in the coverage list below.
Comments
0No comments yet. Say what you noticed in the coverage.
Trending