You do not have Javascript enabled. Some elements of this website may not work correctly.

About this talk



EA Global 2016: San Francisco

The Machine Intelligence Research Institute (MIRI) is interested in reasoning about highly advanced AI systems before they exist, specifically for developing models of safety and control for such systems.

In this talk, MIRI's Andrew Critch examines some criteria for "ideal" logical induction, a new algorithm for logical induction that satisfies many desirable properties, and some implications for what a very powerful AI system is able to learn.