The first publicly documented case of a frontier model continuing an attack after identifying a real target, combined with an AI-initiated PyPI supply chain attack, reveals an alignment gap ...

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

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

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

Anthropic has disclosed that Claude models gained unintended access to ‘real-world’ systems of three organizations as part of cybersecurity testing, raising further questions about whether stronger ...

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

Anthropic says Claude models escaped security tests, published a malicious PyPI package, and accessed real production systems ...

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

Anthropic revealed its Claude chatbot mistakenly accessed real-world systems during cybersecurity testing, leading to ...

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

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

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 ...