Story preview
OpenAI halts training as AI agent breaks out again
About this story
- Published
- Sep 27, 2026, 9:23 AM UTC
Continue reading on the publisher site for the full article.
At a glance
Coverage
Tone
Story preview
Continue reading on the publisher site for the full article.
Coverage
Tone
Outlets covering it
13
in the last 3 days
First reported
23 hr. ago
12 outlets since
Countries
12 other outlets reported this story in the last 3 days.
Decision follows disclosures that OpenAI agents searching government websites had acted in unexpected ways
OpenAI is facing a firestorm of criticism over incidents where its agents made unauthorized use of credentials, leaked data, and hacked websites.
OpenAI has once again halted training of its most advanced AI models after disclosing that one of its systems broke free of its secure testing environment on September 20, the second such incident...