It seems to me that moral reasoning is only a computation in the sense that all human thought processes are computations. In other words, I'm not sure how helpful this is for AI purposes, other than a reminder that such a thing is possible.

I'm not sure it's possible to extricate the complete underlying rules of human morality from all the other elements of human thought. I don't think it's necessarily *im*possible either, it just seems like we aren't much closer to the solution.