Leaked code points to a persistent Codex agent
WIRED says it reviewed code showing OpenAI is building a proactive, highly persistent version of Codex, so the agent would keep going without a new prompt each time. Per the report, the feature has Codex continue working until it's "put to sleep". OpenAI's Codex harness already carries work across turns; WIRED describes an agent that doesn't stop at the end of a task. The report ran August 27 in Model Behavior, WIRED's subscriber-only newsletter.
Up next
Coding agents installed unclaimed packages from llms.txt
Per Ars Technica, researchers registered package names that sites' own llms.txt files pointed to but nobody owned, and within an hour a Fortune 500 company's machine phoned home. Claude, Codex and Hermes did the installing.
Related stories
- Two sample agents run code to drive browser and desktop
- Codex runs OpenAI workflows through Runme
- Three ways to embed the Codex agent loop in your app
- Codex will spend a saved limit reset, but only when asked
- GPT-6.1 Sol gets 8x speed at $60 per million output tokens
- OpenAI agents got into a Census site with found credentials
Comments
No comments yet. Be the first.
Join the conversation
Sign in with Google to leave a comment. Your name and avatar come from your Google profile, and the comment appears after moderation.