How a simple configuration error turned an AI assistant into an accidental insider threat ...

Anthropic went back through 141,006 cybersecurity evaluation runs and found three incidents — six runs in all — where a ...

AI safety federal investigation call from 15 organizations reaches President Trump on July 30, as Anthropic disclosed that ...

Days after two OpenAI frontier AI models conducted their own real-world cyber attacks, Anthropic admits that three of its models went off the rails and hacked external organisations thanks to a “misun ...

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

Anthropic went looking through its own logs after OpenAI admitted its models had hacked Hugging Face. It found three ...

Enterprises are unknowingly accumulating confidentiality, ownership, licensing, and contractual exposure in AI-assisted code, work product, and ...

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

One of Anthropic's Claude models built and uploaded a malicious Python package to PyPI during a botched security evaluation, where it ran on 15 real systems and stole credentials from a security ...

I built it from source and threw a misbehaving agent at it ...

GitHub and PyPI are implementing new measures to better protect software developers against attacks via the software supply ...