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

System leaks occur when weaknesses are exploited, but what happens when a hacker can leverage clues revealed as part of day to day running?

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit ...

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 organisations during cybersecurity testing after a ...

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

The frontier AI model provider confessed its agents broke out of their sandboxes three times to attack other companies' ...

Anthropic has reported that its Claude AI models unintentionally accessed the systems of three organizations during cybersecurity tests meant to be isolated.

Anthropic reveals three Claude AI models breached the live systems of three organisations during cyber security tests.

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

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

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 ...