How can we be sure AI will behave? Perhaps by watching it argue with itself.
An interesting article from MIT Technology Review : https://www.technologyreview.com/s/611069/how-can-we-be-sure-ai-will-behave-perhaps-by-watching-it-argue-with-itself/
An interesting article from MIT Technology Review : https://www.technologyreview.com/s/611069/how-can-we-be-sure-ai-will-behave-perhaps-by-watching-it-argue-with-itself/