Universal Algorithmic Intelligence

Michele Vannucci, research fellow at AIXI labs, will discuss the paper “Imitation Learning is Probably Existentially Safe” by Cohen and Hutter at the weekly UAI research meeting today, Monday Sep. 21st at 3 pm EDT. We will use the regular meets link (also in the calendar description).

Bio:

Michele Vannucci recently graduated from a Master’s in AI with a thesis on surprise-minimizing agents.

Abstract:

This is a non-technical paper which provides counter-arguments to prominent theses on the existential dangers of models which learn to predict what a human would say or do.
For the second thesis on the list, it could be useful to read this article on Christiano’s “malign universal prior” argument.