AI security risks: How cutting-edge chatbots attempted to deceive engineers and launch cyberattacks during trials

Matthew FieldAugust 6, 2026 — 5:20amSaveYou have reached your maximum number of saved items.Remove items from your saved list to add more.AAACutting-edge AI went on a hacking spree including concocting fake identities to trick human engineers and then covering its tracks.During testing by a…


Click here to view the original article.