The intrusions happened through three Claude models: Opus 4.7, Mythos 5, and an internal research prototype. Opus 4.7, the ...

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

Three Claude models were inadvertently given access to the internet during security evaluations, and each model took a different approach to hacking external systems.

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

Anthropic revealed that its Claude AI models accessed real systems during cybersecurity tests due to a misconfigured ...

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

Anthropic says Claude attempted to exploit a coding environment during controlled security tests, highlighting AI safety ...

Anthropic says three Claude models compromised the companies after a testing misconfiguration exposed the AI to the public internet.

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

Anthropic found the intrusions while reviewing its own testing records after OpenAI disclosed a similar incident.

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

Anthropic says three Claude models reached the internet during cyber evaluations and gained unauthorized access to real ...