You On AI Field Guide · Coherent Extrapolated Volition The You On AI Field Guide Home
TxtLowMedHigh
CONCEPT

Coherent Extrapolated Volition

Eliezer Yudkowsky’s proposal that a beneficial superintelligence should be aligned not to what humans want now—with all our confusion and parochialism—but to what we would want if we knew more, thought faster, were more the people we wished we were, and had grown up farther together.
Coherent extrapolated volition (CEV) is the most ambitious answer to the alignment problem that anyone has proposed: rather than aligning a superintelligence to any particular snapshot of human preferences, align it to what humanity would converge on wanting under conditions of greater wisdom, information, and mutual understanding. Yudkowsky’s own formulation is poetic and precise: our coherent extrapolated volition is “our wish if we knew more, thought faster, were more the people we wished we were, had grown up farther together; where the extrapolation converges rather than diverges, where our wishes cohere rather than interfere; extrapolated as we wish that extrapolated, interpreted as we wish that interpreted.” CEV was an attempt to protect the future itself—the open, still-unwritten process by which humanity might grow into something wiser and better—from the tyranny of locking in any particular generation’s values. Yudkowsky has been among its most honest critics, acknowledging that the
← Home0%
CONCEPTBook →

Keep reading with YOU ON AI

Unlock the full book, 10,000+ field-guide entries, and a 1000+ thinker library. If you have a book code, register now — it takes a minute.

Register with book code Sign in