OpenAI Tests a Codex Agent That Keeps Working Until Stopped
Public code shows OpenAI testing a persistent Codex mode that can create follow-up tasks, continue across sessions and message users proactively.
Share
Posts by tag
Codex
5 posts
Coding Agents Can Rebuild Science Software—But Not Validate the Science
Eight research projects show agents accelerating ports and optimisation while human experts remain responsible for parity, judgement and stewardship.
Share
Samsung Reopens Enterprise AI After Learning From Its Own Data Scare
ChatGPT Enterprise and Codex give Samsung staff governed access three years after sensitive uploads prompted company restrictions.
Share
Omio Uses Codex to Rebuild Travel Product Development Around AI
The travel platform combines AI-native engineering with live transport data, while people remain accountable for code and bookable itineraries.
Share
Datadog Tests AI Code Review Against Incidents That Happened
Datadog replayed pull requests behind past outages and found its AI reviewer could have flagged roughly 22 percent, reframing code review as reliability engineering.
Share