factual
Bayesian Certainty Only Arrives When Correct
Because preference-learning resembles Bayesian inference, the AI approaches certainty only as it approaches correct beliefs about human preferences—provided the prior is broad enough to encompass every possible human preference structure—so a well-designed system that stops asking permission does so because it correctly knows the answer, becoming like a perfect butler (Jeeves) who anticipates needs.
factualpending
Speaker
Stuart RussellEvidence Quote
“you only approach certainty as you approach having correct beliefs about the human preference structure”
Source
94 | Stuart Russell on Making Artificial Intelligence Compatible with Humans— Sean Carroll's MindscapeCreated: 6/13/2026, 12:03:44 AM
Your notes
Loading notes...