AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Are We Really Aligning Our AI Models?
The State Department is going to have an interest in making sure that US based corporations like Meta, Microsoft and Google are not designing AI that is really good at manipulating people. I'd be more afraid of a technology that was very, very good at playing sweet and aligned 99.9% of the time. While having within it the ability to misalign when it knows that it's dealing with a really, really powerful agent that it can manipulate. That kind of alignment seems much harder to fix from the standpoint of American policies and American ethics systems.