Human-Compatible AIs are AIs that help and usefully team with people and support human society. Aspirationally, human-compatible AIs would learn, share what they learn, and collaborate to achieve high standards. They would communicate, establish common ground, learn and read critically, consider the provenance of information, test hypotheses, and collaborate with people and each other. This project explores the dimensions, research challenges, approaches, goals, and possibilities for creating human-compatible AIs.
This is a gallery of past projects. My interests have moved back and forth between artificial intelligence, sensemaking, computer support for collaborative work, and HCI with side trips into digital rights management, computer security, and programming languages.