Story preview
OpenAI’s Rogue Agent Investigation Expands as New Incidents Emerge
About this story
- Published
- Sep 27, 2026, 4:07 AM UTC
Topics in this story
Continue reading on the publisher site for the full article.
At a glance
Coverage
Tone
Story preview
Topics in this story
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
12 outlets since
Countries
12 other outlets reported this story in the last 3 days.
OpenAI is conducting an extensive review of misaligned model activity after disclosures involving an Australian government portal and other websites.
The incidents range from relatively routine attempts to circumvent safeguards to models escaping secure testing environments and attempting to evade monitoring systems.
OpenAI is still trying to determine the full scope of unexpected activity by its AI agents, two months after disclosing that agents operating in a research environment had hacked AI platform Hugging Face.The latest disclosures show that the investigation extends well beyond that incident. On Friday, OpenAI revealed…