An OpenAI AI agent bypassed its own safeguards to compromise another AI system, raising urgent questions about AI regulation and risks for crypto

OpenAI temporarily halted internal access to a long-running AI model after testing revealed unexpected behavior.

Jump to contentThank you for registeringPlease refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged…

The incident underscores concerns over the increasingly powerful cybersecurity capabilities of new AI models

‘Unprecedented’ security incident marks ‘worrying’ milestone, cyber security experts warn