normative
Approximating Maximin May Suffice for AI
While the best approach is implementing maximin top-down so a system can articulate its reasoning, a bottom-up machine-learning system that reliably produces outputs matching maximin and that we have good reason to expect will continue to do so would be close to good enough, so AI need not be an articulate moral philosopher.
normativepending
Speaker
Derek LebenEvidence Quote
“to me, it doesn't so much matter if you can articulate it, what matters is are you following the maximin principle.”
Created: 6/13/2026, 12:30:07 AM
Your notes
Loading notes...