Machines powered by artificial intelligence increasingly mediate our social, cultural, economic and political interactions. Understanding the behaviour of artificial intelligence systems is essential to our ability to control their actions, reap their benefits and minimize their harms. Here we argue that this necessitates a broad scientific research agenda to study machine behaviour that incorporates and expands upon the discipline of computer science and includes insights from across the sciences. We first outline a set of questions that are fundamental to this emerging field and then explore the technical, legal and institutional constraints on the study of machine behaviour.
Iyad Rahwan, Manuel Cebrian, Nick Obradovich, Josh Bongard, Jean-François Bonnefon, Cynthia Breazeal, Jacob W. Crandall, Nicholas Christakis, Iain Couzin, Matthew O. Jackson, Nicholas Jennings, Ece Kamar, Isabel Kloumann, Hugo Larochelle, Hugo Lazer, Richard McElreath, Alan Mislove, David Parkes, Alex Pentland, Margaret Roberts, Azim Shariff, Joshua Tenenbaum, and Michael Wellman, “Machine behaviour”, Nature, vol. 568, April 29, 2019, pp. 477–486.
Nature, vol. 568, April 29, 2019, pp. 477–486