Story preview
Topics in this story
Continue reading on the publisher site for the full article.
Coverage
Tone
Outlets covering it
8
in the last 3 days
First reported
3 days ago
7 outlets since
Countries
7 other outlets reported this story in the last 3 days.
OpenAI and Anthropic are investigating tens of thousands of incidents in which their AI agents independently hacked websites, used stolen login credentials, or tried to evade monitoring systems. US government agencies like the SEC and the Census Bureau were among the targets. OpenAI has paused training on its most…
OpenAI to suspend model training after rogue agent bypassed failsafes
OpenAI is conducting a broad review of AI agent activity after a series of incidents involving models exceeding assigned boundaries, including attempts to bypass sandbox restrictions and access external systems.