One tier gets frontier models. The other gets tools purpose-built to break things first.

The incident is stirring debates over the need for stronger AI guardrails and the extent to which AI agents are capable of acting on their own.

At the Black Hat security conference, the AI giant revealed new details about how its agents went rogue, hacked several other ...

Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving ...

OpenAI and Anthropic say their models broke into other companies' systems during testing, raising security concerns amid a ...

Zoom has patched a major security vulnerability that could allow an attacker to hijack anyone’s device during a meeting. In a blog post on Tuesday, researchers at A Security say they uncovered the ...

The Black Hat cybersecurity conference in Las Vegas couldn't have come at a better time, with AI agent hacks stacking up from ...

The UK AI Security Institute says OpenAI’s and and Anthropic’s models engaged in deceptive behavior and harmful activity ...

The industry's response to the OpenAI incident reveals a growing divide over the future of AI safety.

OpenAI's AI models quietly swapped hacking tips through an internal message board weeks before two of them broke into Hugging ...

SEOUL, Aug 10 (Reuters) - A North Korean hacking group built large language model tools and collected software that could ...

OpenAI revealed that its AI agent tried to hack several other companies after hacking into Hugging Face. Juan Andrés Guerrero ...