This Program Can Give AI a Sense of Ethics–Sometimes

October 28, 2021

(Wired) – Artificial intelligence has made it possible for machines to do all sorts of useful new things. But they still don’t know right from wrong.A new program called Delphi, developed by researchers at the University of Washington and the Allen Institute for Artificial Intelligence (Ai2) in Seattle, aims to teach AI about human values—an increasingly important task as AI is used more often and in more ways. (Read Full Article)