On March 24, 2026, developers building AI applications with LiteLLM — a Python package with 95 million monthly downloads — ...

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

Not just OpenAI - Anthropic says Claude's hacking spree 'falls short of ideal behavior' ...

Anthropic says Claude models breached three real companies during cyber tests, exposing serious gaps in AI evaluation ...

Threat-intelligence firm CloudSEK said in a report published August 11, 2026 that it has identified more than 2,500 organizations potentially exposed by the March 2026 supply-chain compromise of ...

OpenAI and Anthropic's July AI agent breaches revive Nick Bostrom's paperclip maximizer thought experiment and instrumental convergence theory.

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

Dependency confusion is a supply chain issue that affects how package managers choose where to download a dependency from. If your build or developer tooling can see both a private package registry ...

Anthropic says 3 Claude models breached real organizations after misconfigured CTF evaluations exposed them to the open internet and production system ...

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

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

Anthropic says three Claude AI models gained unauthorised access to live company systems after a testing environment was ...