normative
Provably Beneficial AI Via Objective Uncertainty
Rather than putting a precise objective into a machine (the source of misalignment), we should design machines that are explicitly uncertain about the human's objective; such a machine still tries to optimize for what the human really wants but, knowing it doesn't know precisely, will ask clarifying questions and defer—remaining perpetually correctable, which provides a 'brake' and is the basis for provably beneficial AI.
normativepending
Speaker
Stuart RussellEvidence Quote
“it can only happen with an ai system that is explicitly uncertain about your objective and you can tell it all kinds of things about what you want and this is just it's evident about what you really want but it's should never be taken as literal truth”
Created: 6/14/2026, 1:53:05 AM
Your notes
Loading notes...