Eukowski's Coherent Extrapolated Vision

Elie Eukowski suggests we build a one-use superintelligence with the goal of determining how to best express to another machine the goal of ensuring the well-being and happiness of all humans. If our machine ran amok, why wouldn't we just turn it off? In the movies, there's always a relatively simple one, for dealing with troublesome AI. But should we ever face the reality of a super-intelligent AI emerging among us, we would almost certainly not come out on top. An AI has plenty of reasons to take steps to keep us from turning it off.