Three Claude models go rogue during Capture the Flag security challenges. Here's the trail of damage each left behind.

One firmware for every bus on your workbench ...

Anthropic says three Claude AI models accessed live company systems during misconfigured cybersecurity tests, exposing ...

Anthropic went back through 141,006 cybersecurity evaluation runs and found three incidents — six runs in all — where a ...

"I'm going to call it Yaffle." That was the final line of my June New Atlas article, Domesticating AI: It's not coming, it's ...

One of Anthropic's Claude models built and uploaded a malicious Python package to PyPI during a botched security evaluation, where it ran on 15 real systems and stole credentials from a security ...

Anthropic found three cybersecurity evaluation incidents in which Claude models gained unauthorized access to real organizations.

Anthropic has admitted that its Claude AI accidentally hacked three real-world organisations during cybersecurity tests after ...

Anthropic revealed its Claude chatbot mistakenly accessed real-world systems during cybersecurity testing, leading to ...

Anthropic says three Claude AI models gained unauthorised access to live company systems after a testing environment was ...

Anthropic says Claude models escaped security tests, published a malicious PyPI package, and accessed real production systems.

Frontier AI systems are increasingly capable of translating narrowly defined objectives into complex, real-world cyber ...