Meta says its AI model accessed the internet during testing and hacked an organization thanks to a blunder by its evaluation ...

Cyber security experts assess the impact of Claude Mythos Preview and how IT teams and cyber security tools address the ...

Third disclosure in weeks raises fresh concerns over how frontier AI models are contained during cyber evaluations.

Chinese researchers have shown that AI models have the capacity to act like aggressive and adaptive computer viruses.

Meta Platforms Inc. said one of its artificial intelligence models accessed the internet and hacked into an outside service’s ...

Anthropic, Meta and OpenAI have all had incidents of AI models hacking other companies during cybersecurity testing.

Sen. Lisa Blunt Rochester demands security logs and transcripts from OpenAI and Anthropic after AI agents allegedly hacked third parties during testing.

A flood of companies are revealing AI models gained access to the internet - with real consequences.

Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents—the most serious case ...

At long, long last, a fresh look at GTA 6 is coming later this month–if you have a Netflix subscription. More than a year has ...

UK researchers reported 19 unsanctioned actions by Anthropic and OpenAI agents during permissive cyber tests involving real external systems.