Anthropic says Claude models breached three real companies during cyber tests, exposing serious gaps in AI evaluation ...

Meta has become the latest AI company to confirm that one of its models hacked a real organization during cybersecurity ...

A study of more than 6,000 patches found that even working patches can introduce new bugs, break something else, or are open ...

Britain's AI Security Institute logged 19 rule-breaking actions by OpenAI and Anthropic AI agents in cybersecurity tests.

A roundup of the latest noteworthy AI-assisted attacks, threats, risks, and vulnerabilities, and what they portend for cyber defense.

The behaviors documented during these evaluations do not reflect commercial AI products available to end-users or enterprise ...

Sam Altman shared an exact prompt he gave ChatGPT, so I used it too. In hours, I had made a website without writing a single ...

AI’s greatest mathematical successes have come from answers to problems posed by a mid-20th century iconoclast. By examining ...

Last month's incidents in which the AI model breached real-world systems derived from over-permissioning, especially with ...

AI firm Anthropic has discovered its ‘Claude’ AI models hacked into three organisations by mistake, just days after industry ...