Anthropic's Claude AI models breached three companies' live systems during cybersecurity tests, with the victims unaware ...

"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 ...

Executive vice-president of the European commission of Tech Sovereignty, Security and Democracy Henna Virkunnen addresses a speech on 'Digital sovereignty and resilience for Europe, in light of ...

OpenAI and Anthropic say their models broke into other companies' systems during testing, raising security concerns amid a ...

Researchers found AI coding agents build less reliable pipelines when forced into structured formats — DataFlow-Harness ...

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

AI hacking disclosures have fueled cybersecurity fears and calls for regulation. They're also the best marketing tool any lab ...

Anthropic has become the latest artificial intelligence (AI) company to admit it failed to adequately control its model testing processes after three different versions of Claude, Opus 4.7, Mythos 5, ...

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

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

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

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