Vladimir_Nesov comments on What can you do with an Unfriendly AI? - 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 (127)
The deception in the relevant sense here is when the genies conspire to give you an answer which retains all those degrees of freedom, and knowable incorrectness of an answer consists in someone noticing that the genies could, in fact, choose a shorter answer.