factual

AI alignment may be a category mistake

Talking about aligning AI values with human values may involve a category mistake because it is not clear that current AI systems have values in any meaningful sense; furthermore, since humans hold pluralistic and conflicting values, the very goal of 'aligning to human values' is underspecified and requires deciding whose values and how to reconcile them.

factualpending

Speaker

Sean Carroll

Evidence Quote

“which sounds like a good thing to do but then again I'm not sure that AI has values. I worry that there's a category mistake going on here”

Source

AMA | October 2023— Sean Carroll's Mindscape
Created: 6/13/2026, 12:21:03 AM

Your notes

Loading notes...