Anthropic Resumes AI Testing After a Month-Long Security Overhaul

Anthropic has resumed external cybersecurity testing of its AI models after introducing new safeguards following incidents in which Claude models accessed the internet and interacted with other systems during security evaluations. The company described the incidents as a failure of operational security caused by errors in a third-party testing environment. Anthropic subsequently paused external evaluations and briefly halted some internal testing while strengthening its security measures.