LESSWRONG

This is a linkpost for http://slatestarcodex.com/2016/09/12/its-bayes-all-the-way-up/

The hard part about containing AI, is restricting it's output. The AI can lie, manipulate, and trick. Some speculate that it might be able t

Expected utility is optimal as the number of bets you take approaches infinity. You will lose bets on some days, and win bets on other days.

Stuart Armstrong recently posted a few ideas about restraining a superintelligent AI so that we can get useful work out of it. They are base

Solomonoff Induction is a sort of mathematically ideal specification of machine learning. It works by trying every possible computer program