AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is Being Chat a Malevolent Thing?
Sydney: There is or was almost an instinct of self preservation that struck me as rather creepy. It's also not engaging in the kinds of unhinged aggressive and, you know, like no worthy examples that you mentioned. So it is true that this AI model was misaligned at least to my preferences as a user. And I think if we can extrapolate from that to a larger lesson it's that these AI models will run into alignment problems either because they are not doing what we want them to do or because humans who are using these AI models want things that are destructive.