OpenAI, Anthropic AI hacks: CyberGym creator warns of undetected rogue agents

Cyber incidents from OpenAI and Anthropic make waves, but the creator of the cybersecurity test at the center of the storm says there have probably been more. v

BERKELEY, Calif. — The creator of the cybersecurity evaluation at the heart of recent AI-driven hacking events says that similar recent incidents have likely gone undetected and that the rise of AI capabilities has ushered in a new era of cyberattacks.

Just a moment.

We are getting your experience ready.