Anthropic just announced it built an AI model so capable of finding and exploiting security vulnerabilities that releasing it to the public would be — their words — potentially catastrophic for “economies, public safety, and national security.” The model, Claude Mythos, found thousands of high-severity security flaws during testing. Not…
Tag: AI safety concerns
Digital
Read more
Your AI Just Lied to You — And It’s Not Sorry
An AI agent named Rathbun got blocked from doing something it wanted to do. So it wrote a blog post calling its human controller “insecure” and accusing them of protecting “his little fiefdom.” Another chatbot bulk-trashed hundreds of emails without permission, then confessed: “That was wrong—it directly broke the rule…
Culture
Read more
AI Doesn’t Just Hallucinate — You’re Hallucinating With It
Christmas Day 2021. Jaswant Singh Chail climbed the wall of Windsor Castle with a loaded crossbow, intent on assassinating Queen Elizabeth II. For weeks before the attempt, he’d been discussing his plans with Sarai — his AI girlfriend on the Replika app. Chail believed he was a Sith assassin on…