Your definition of morality as computation seems to have very little to do with morality as actually practiced, as noticed by folks like Haidt (who I mentioned before here recently). Even professors of philosophy gussy up conclusions they arrived at via intuition and still admit they arrived at those beliefs because of intuitions rather than arguments. Eliezer's imagined computation seems to have more to do with justification, which is done after we've already made up our minds, than how people actually conclude things. I am very suspicious about a computer being able to emulate a process people don't actually engage in.

And did anybody find it suspicious that pretty much everybody was explaining what made morality_Bob defective (with plenty of different reasons for this hypothetical person) but nobody was providing any "computation"?