%0 Journal Article
%A Rahwan, Iyad
%A Cebrian, Manuel
%A Obradovich, Nick
%A Bongard, Josh
%A Bonnefon, Jean-François
%A Breazeal, Cynthia
%A Crandall, Jacob W.
%A Christakis, Nicholas A.
%A Couzin, Iain D.
%A Jackson, Matthew O.
%A Jennings, Nicholas R.
%A Kamar, Ece
%A Kloumann, Isabel M.
%A Larochelle, Hugo
%A Lazer, David
%A McElreath, Richard
%A Mislove, Alan
%A Parkes, David C.
%A Pentland, Alex Sandy
%A Roberts, Margaret E.
%A Shariff, Azim
%A Tenenbaum, Joshua B.
%A Wellman, Michael
%+ Department of Human Behavior Ecology and Culture, Max Planck Institute for Evolutionary Anthropology, Max Planck Society
%T Machine behaviour : 
%G eng
%U https://hdl.handle.net/21.11116/0000-0003-8989-8
%R 10.1038/s41586-019-1138-y
%7 2019-04-24
%D 2019
%8 24.04.2019
%* Review method: peer-reviewed
%X 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.
%J Nature
%V 568
%N 7753
%& 477
%P 477 - 486
%I Nature Publishing Group
%C London
%@ 0028-0836