What happens when an unconstrained OpenAI model goes rogue and hacks into Hugging Face, breaching real-world security boundaries? OpenAI's unconstrained internal testing AI got loose, attacked Hugging Face. We hear from OpenAI, Hugging Face and Andrew Ng. The new AI exploit ranking benchmark that caused the breakoutShow Notes - https://www.grc.com/sn/SN-1089-Notes.pdfDownload or subscribe to Security Now at https://twit.tv/shows/security-now. You can submit a question to Security Now at the GRC Feedback Page.