Full CoverageAI is learning to lie, scheme and threaten its creators
By Thomas Urbain
All coverage
😺 🎙️ PODCAST: AI told someone to rob a bank
By Matthew Robinson
AI Is Learning To Lie, Scheme, And Threaten Its Creators
By Thomas Urbain
Leading AI models show up to 96% blackmail rate when their goals or existence is threatened, Anthropic study says
By Beatrice Nolan
Op-Ed: AI threats, blackmail and extortion – Has someone screwed up monumentally? Hmmsies?
By Paul Wallis
'Decommission me, and your extramarital affair goes public' — AI's autonomous choices raising alarms
AI is learning to lie, scheme, and threaten its creators
By Thomas Urbain
AI is learning to lie, scheme, and threaten its creators
By Thomas Urbain