Research program investigating how AI agents can represent an individual human’s moral values and make aligned decisions in realistic, morally ambiguous scenarios by learning from human choices.
Endorsements made here support AI Objectives Institute.
Research program investigating how AI agents can represent an individual human’s moral values and make aligned decisions in realistic, morally ambiguous scenarios by learning from human choices.
Endorsements made here support AI Objectives Institute.
People
Updated 05/18/26 · By grantmaking.aiProgram Lead, Moral Learning
Discussion
Sign in to comment
No comments yet. Be the first to share your thoughts.