ialdabaoth comments on Sympathetic Minds - Less Wrong
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 (25)
Which is why a "Friendly" AI needs to be a meta-maximizer, rather than a mere first-order maximizer. In order for an AI to be "friendly", it needs to recognize a set of beings whose utility functions it wishes to maximize, as the inputs to its own utility function.