Safety is always going to be paramount when it comes to artificial intelligence. After all, one of our collective fears is a highly advanced AI going rogue and threatening our very existence. It certainly doesnt help to see that some of the smartest AI models out there resort to cheating to achieve their goals, or that some would even try to blackmail humans to preserve their integrity.That actually happened during safety tests performed on frontier AI models before being released to the public. ChatGPT o1 made headlines a few months ago when security researchers found that the AI would resort to cheating at chess against a better opponent in order to achieve its goal, which was winning the game.More recently, Claude 4 threatened an engineer who was supposed to delete the AI from a computer to expose the persons infidelity to their partner. The AI obtained information about the deletion plans and the alleged affair from emails it had access to for the purpose of testing its behavior.The actual Claude 4 will not try to blackmail users, though the AI does come with stronger guardrails than its predecessors to ensure its safe for users. That said, Claude 4 might decide to report you to authorities and the press if it thinks youre engaging in nefarious activities, but thats only a theoretical risk.The blackmail scenario is what prompted Yoshua Bengio to create a new initiative called LawZero, which aims to develop honest AI programs that will detect AI systems that might attempt to deceive humans or go rogue.Continue reading...The post LawZero will be an honest AI that protects you from rogue agents appeared first on BGR.Today's Top DealsBest deals: Tech, laptops, TVs, and more salesMemorial Day weekend deals: Free Blink camera, $6 Kasa smart plugs, $40 Crock-Pot, $149 Bose earbuds, moreTodays deals: $1,750 Amazon gift card, Sonos speaker sale, Hisense 75-inch smart TV, foam dog beds, moreTodays deals: Nintendo Switch games, $5 smart plugs, $150 Vizio soundbar, $100 Beats Pill speaker, more