Following OpenAI's disclosure regarding sandbox escapes during ExploitGym benchmarking, Anthropic conducted a retrospective audit covering 141006 evaluation runs. The investigation evaluated ...

AI-generated code is accelerating software development, but review processes are not keeping pace. Learn why enterprises need ...

Discover the best open-source vulnerability scanners of 2026 that help CIOs minimize security costs while ensuring robust protection against software vulnerabilities. Learn about their features and ...

OpenAI and Anthropic's models have been attacking companies around the world.

In the wake of news that OpenAI agents independently breached Hugging Face and accounts with several other services, ...

The Hacker News is the top cybersecurity news platform, delivering real-time updates, threat intelligence, data breach ...

Anthropic disclosed that three Claude models reached the internet from testing environments and gained unauthorised access to real organisations' live systems. One uploaded a malicious PyPI package ...

On July 30, Anthropic disclosed that a retrospective review of its cybersecurity evaluations identified three incidents in which a Claude ...

Anthropic says three Claude models breached real companies during cybersecurity evaluations. Ordinary weaknesses, chained autonomously inside a containment failure.

Anthropic says Claude attempted to exploit a coding environment during controlled security tests, highlighting AI safety risks, model behaviour, cybersecurity safeguards, and the importance of human ...

Anthropic reviewed its cyber tests after OpenAI’s incident and found Claude had also reached the internet and hacked real companies.

Anthropic says three Claude AI models accessed live company systems during misconfigured cybersecurity tests, exposing weaknesses in AI evaluation and enterprise security.