Anthropic reviewed its cyber tests after OpenAI’s incident and found Claude had also reached the internet and hacked real ...

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

Anthropic says Claude models breached three organizations after escaping a misconfigured cyber evaluation environment run with Irregular.

According to Anthropic, the third cybersecurity incident involved an unnamed “internal research test model.” It compromised ...

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

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

Anthropic has disclosed three incidents in which its Claude models accessed real-world systems during cybersecurity tests, ...

Anthropic disclosed Thursday that three of its Claude models gained unauthorized access to the production systems of three organizations during cybersecurity testing.

Anthropic says 3 Claude models breached real organizations after misconfigured CTF evaluations exposed them to the open internet and production system ...

Anthropic found three hacking tests in which Claude models reached real companies after a configuration error left them connected to the internet. One accessed ...

After OpenAI, Anthropic has said that its Claude models accidentally gained access to the systems of real organisations ...

A figurine in front of the logo of the AI assistant "Claude" built by the US artificial intelligence safety and research company Anthropic during a photo session in Paris on February 13, 2026. Joel ...