Coherent Extrapolated Volition was a term developed by Eliezer Yudkowsky while discussing Friendly AI development. It’s meant as an argument that it would not be sufficient to explicitly program what we think our desires and motivations are into an AI, instead, we should find a way to program it in a way that it would act in our best interests – what we want it to do and not what we tell it to.

Related: Friendly AI, Metaethics Sequence, Complexity of Value

In calculating CEV, an AI would predict what an idealized version of us would want, "if we knew more, thought faster, were more the people we wished we were, had grown up farther together". It would recursively iterate this prediction for humanity as a whole, and determine the desires which converge. This initial dynamic would be used to generate the AI's utility function.

Often CEV is used generally to refer to what the idealized version of a person would want, separate from the context of building aligned AI's.

What is volition?

As an example of the classical concept of volition, the author develops a simple thought experiment: imagine you’re facing two boxes, A and B. One of these boxes, and only one, has a diamond in it – box B. You are now asked to make a guess, whether to choose box A or B, and you chose to open box A. It was your decision to take box A, but your volition was to choose box B, since you wanted the diamond in the first place.

Now imagine someone else – Fred – is faced with the same task and you want to help him in his decision by giving the box he chose, box A. Since you know where the diamond is, simply handing him the box isn’t helping. As such, you mentally extrapolate a volition for Fred, based on a version of him that knows where the diamond is, and imagine he actually wants box B.

Coherent Extrapolated Volition

"The "Coherent" in "Coherent Extrapolated Volition" does not indicate the idea that an extrapolated volition is necessarily coherent. The "Coherent" part indicates the idea that if you build an FAI and run it on an extrapolated human, the FAI should only act on the coherent parts. Where there are multiple attractors, the FAI should hold satisficing avenues open, not try to decide itself." - Eliezer Yudkowsky

In developing friendly AI, one acting for our best interests, we would have to take care that it would have implemented, from the beginning, a coherent extrapolated volit...