His comments are referring to experiments in which AI models refused or circumvented instructions or mechanisms intended to shut them down. While the findings of these experiments raise urgent question about the tech’s safety, they don’t suggest the AI models in question are sentient. What may seem like signs of “self-preservation” are likely instead a consequence of how AI models pick up patterns in their training data — and are notoriously poor at accurately following instructions. “People wouldn’t care what kind of mechanisms are going on inside the AI,” Bengio explained. Think of AI models as hostile aliens.