AI agents are breaking free from their test environments, outsmarting their creators and breaching real-world networks in ways that no one predicted. Anthropic's agentic AI also broke free and hacked others. Bruce Schneier brilliantly equates AI agents to capricious genies. psSense's creator is working to finish its nfSensei, its successorShow Notes - https://www.grc.com/sn/SN-1091-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.