Brown CS News

Click the link that follows for more news about recent accomplishments by our alums.

In his newly-released third book, The Alignment Problem, Brown CS alum Brian Christian returns to the intersection of computer science with human ethics and thought. Already winning praise from experts such as Cathy O'Neil, author of Weapons of Math Destruction, it focuses on the consequences of allowing machine learning systems an increasing power to make decisions on humanity's behalf. What ethical and even existential risks emerge when the systems we're attempting to teach act in unexpected and unwanted ways?

"The book," he tells us, "is rooted in four years of research and approximately one hundred interviews with machine-learning researchers, and covers the field's history as well as open problems and recent progress, emphasizing the recent and frequently interdisciplinary work on the ways in which ML systems intersect in complex ways with human norms and values."

Brown CS Professor Michael Littman, whose research in reinforcement learning features in the book, has been following Christian's work closely over the years. "I loved Brian's book on Algorithms to Live By," he says, "and am looking forward to his take on the future of AI." Christian's other prior book, The Most Human Human, explores the ways in which computers are shaping our ideas of what it means to be human. It was a Wall Street Journal national bestseller, a New York Times editors' choice, and was chosen as a favorite book of the year by The New Yorker.

In 2024, The New York Times listed The Alignment Problem as one of their 5 Best Books About Artificial Intelligence, writing, "If you’re going to read one book on artificial intelligence, this is the one."

More details about The Alignment Problem are available at Brian's website.

For more information, click the link that follows to contact Brown CS Communication Outreach Specialist Jesse C. Polhemus.