ciphergoth comments on The Kolmogorov complexity of a superintelligence - 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 (30)
I'm confused - a Friendly AI doesn't start with information about the insides of brains, it only starts with enough information to correctly identify human beings in order to know whose preferences to infer its values from.