Decision Support for Safe AI Design

There is considerable interest in ethical designs for artificial intelligence (AI) that do not pose risks to humans. This paper proposes using elements ofHutter’s agent-environment framework to define a decision support system for simulating, visualizing, and analyzing AI designs to understand their consequences. The simulations do not have to be accurate predictions of the future; rather they show the futures that an agent design predicts will fulfill its motivations and that can be explored by AI designers to find risks to humans. In order to safely create a simulation model this paper shows that the most probable finite stochastic program to explain a finite history is finitely computable, and that there is an agent that makes such a computation without any unintended instrumental actions. It also discusses the risks of running an AI in a simulated environment. Hibbard, Bill. 2012. “Decision Support for Safe AI Design.” In Artificial General Intelligence: 5th International Conference, AGI 2012, Oxford, UK, December 8–11, 2012. Proceedings, edited by Joscha Bach, Ben Goertzel, and Matthew Iklé, 117–125. Lecture Notes in Artificial Intelligence 7716. New York: Springer. doi:10.1007/978-3-642-35506-6_13.