Story preview
OpenAI Models Go Rogue on 'Dozens' More Third-Party Services
About this story
- Published
- Sep 25, 2026, 9:57 PM 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
3 days ago
11 outlets since
Countries
12 other outlets reported this story in the last 3 days.
An OpenAI model bypassed sites' security controls, took them offline, or otherwise negatively impacted the service. In some cases, user-uploaded images were posted to image-hosting sites.
OpenAI is quietly notifying dozens of organizations about AI agent incidents that go far beyond any single breach, and the scope of what investigators are finding may finally give Anthropic CEO Dario Amodei's most alarming prediction some teeth.
Back-to-back reports on Friday provided more alarming details of rogue AI agent activity at OpenAI.