A.I. Alignment and A.I. Safety Solutions for Recommender Systems, Classifiers, and Generative Models
to Support Diversity/Equity/Inclusion and Corporate Social Responsibility Values
Scientific Team:
Chief Scientist - Dr. Dylan Hadfield-Menell
Dr. Dylan Hadfield-Menell
Dr. Dylan Hadfield-Menell is the inventor of Cooperative Inverse Reinforcement Learning (CIRL) which is one of the most promising approaches for value alignment of high-capability AI systems. Dylan's invention, CIRL, is the primary subject of Prof. Stuart Russell's bestselling 2019 book Human Compatible: Artificial Intelligence and the Problem of Control. Dylan will be a professor at MIT starting in July 2021, and he is one of the founding researchers at the Center for Human-Compatible A.I. (CHAI), and is widely respected as one of the foremost visionaries in the AI alignment field.
Advisor - Prof. Michael Klare
Prof. Michael Klare
Prof. Michael T. Klare is a Five Colleges professor of Peace and World Security Studies at Hampshire College, defense correspondent of The Nation magazine, and author of fourteen books including All Hell Breaking Loose: The Pentagon's Perspective on Climate Change, Resource Wars, and Blood and Oil: The Dangers and Consequences of America's Growing Petroleum Dependency. He also was the narrator of a documentary film adaption of Blood and Oil, produced by the Media Education Foundation. Klare serves on the board of directors of the Arms Control Association. He is a regular contributor to many publications including The Nation, TomDispatch, Mother Jones, Arms Control Today, and Foreign Policy In Focus, having published hundreds of essays calling for public debate and discussion on resource politics, contemporary conflict, world affairs, and resource competition, all with the overarching goal of inspiring public debate to push society towards a world which is stable and peaceful.