Coherent Extrapolated Volition

Coherent Extrapolated Volition (CEV) is a proposed approach to the Friendliness problem in artificial intelligence and roboethics.

Rather than a Friendly AI being designed directly by human programmers, it is to be designed by a seed AI programmed to first study human nature and then produce the AI which humanity would want, given sufficient time and insight to arrive at a satisfactory answer. [ [http://singinst.org/upload/CEV.html] ] The appeal to an objective though contingent human nature (perhaps expressed, for mathematical purposes, in the form of a utility function or other decision-theoretic formalism), as providing the ultimate criterion of "friendliness", is an answer to the meta-ethical problem of defining an objective morality; extrapolated volition is intended to be what humanity objectively would want, all things considered, but it can only be defined relative to the psychological and cognitive qualities of present-day, unextrapolated humanity.

Making the CEV concept precise enough to serve as a formal program specification is part of the research agenda of the Singularity Institute for Artificial Intelligence. [ [http://singinst.org/research/researchareas] ]

References