Squark comments on In what language should we define the utility function of a friendly AI? - Less Wrong Discussion
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (22)
Presumably the extrapolated values will also include preference for slow, gradual transitions. Therefore the AI will make the transition gradual.