Home → Opinion → Interviews → Does AI Have an Alignment Problem? → Full Text

Does AI Have an Alignment Problem?

By The New York Times

June 8, 2021

[article image]

Brian Christian is an author who holds degrees in philosophy, computer science, and poetry from Brown University and the University of Washington.

In an interview, Christian discusses ideas from his recent book on artifcial intelligence (AI), The Alignment Problem. The term "alignment problem" originated in economics as a way to describe the fact that the systems and incentives we create often fail to align with our goals.

That's a central worry with AI, too: that we will create something to help us that will instead harm us, in part because we didn't understand how it really worked or what we had actually asked it to do.

From The New York Times
View Full Article


No entries found