Stuart Russell

British-American computer scientist at UC Berkeley, co-author of the standard AI textbook (Artificial Intelligence: A Modern Approach), and author of Human Compatible — which argues for a new paradigm of AI development based on uncertainty about human preferences.

Proposed the inverse reward design approach to AI safety — that AI systems should be uncertain about what humans want and should seek to clarify rather than maximize fixed objectives — providing an alternative to Bostrom's scenario that comes from within mainstream AI research.