How do humans, for example, read a philosophy book and update their views about what they value about the world?
Could there not be AI value drift in our favor, from a paperclipper AI to a moral realist AI?
How do humans, for example, read a philosophy book and update their views about what they value about the world?
Could there not be AI value drift in our favor, from a paperclipper AI to a moral realist AI?