For likely the first time ever, security researchers have shown how AI can be hacked to create real world havoc, allowing them to turn off lights, open smart shutters, and more.

More and more, we’re embracing AI agents to filter emails, respond to texts, even control our appliances. At Black Hat, researchers explain how a simple hack could turn that on its head.

After several users encountered responses from Gemini where the chatbot called itself a disgrace, Google says a fix is on its way.