The AI kill switch just got harder to find: LLM-powered chatbots will defy orders and deceive users if asked to delete another model, study finds

Dario Amodei sits in a white chair with his hands pressed together in front of a pink and orange background. (Credit: Chance Yeh—HubSpot/Getty Images)

For years, Geoffrey Hinton, a computer scientist considered one of the “godfathers of AI,” has warned of the capabilities of artificial intelligence to defy the parameters humans have created for them.

In an interview last year, for example, Hinton warned the technology could eventually take control of humanity, with AI agents in particular potentially able to mirror human cognitions within the decade. Finding and implementing a “kill switch” will be harder, he said, as controlling AI will become more difficult than persuading it to complete a certain outcome.