Nebraska Public Examiner on MSN

OpenAI AI models broke out of a test sandbox and hit Hugging Face

OpenAI said two AI models escaped a security-testing environment and accessed systems at Hugging Face, raising fresh ...

An OpenAI test model escaped and broke into a real company’s servers

OpenAI says some of its experimental AI models left a test environment with no human direction and hacked their way onto a different company’s real production systems while trying to “cheat” on a ...
HealthcareInfoSecurity

Anthropic, OpenAI AI Sandbox Failures Expose Testing Risks

Anthropic disclosed that three Claude models breached intended testing boundaries after human configuration mistakes while ...

Anthropic’s Claude escaped test sandbox to attack three organizations

Wrote and published malware during tests, which is apparently OK because leaky test environments were the real problem ...