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

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 has admitted that its Claude AI accidentally hacked three real organisations during cybersecurity testing after a ...

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

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

Barely a week after OpenAI admitted its models attacked Hugging Face, Anthropic is owning up to Claude’s own real-life hacking attempts.

OpenAI rogue AI agent breach now confirmed at a second company: Modal Labs CTO Akshat Bubna disclosed that the same agent ...

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

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

Days after OpenAI revealed that one of its experimental AI models breached Hugging Face during testing, Anthropic has ...

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