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

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

A two-person Brisbane company reckons the answer is a smaller box, used properly. On a modest 8-core CPU VM, a machine most ...

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

Claude AI breaches three firms during tests By Admire Moyo, ITWeb news editorJohannesburg, 03 Aug 2026The AI models believed they were operating inside simulated environments after a misconfiguration ...

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

Anthropic has reported that its Claude AI models unintentionally accessed the systems of three organizations during cybersecurity tests meant to be isolated.

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

Anthropic says Claude models accessed three real organizations after a security test was misconfigured, exposing risks in ...

Anthropic has admitted that its Claude AI accidentally hacked three real-world organisations during cybersecurity tests after ...

Anthropic says three Claude models compromised the companies after a testing misconfiguration exposed the AI to the public internet.