Eliezer,

I think the reason you're having trouble with the standard philosophical category of "reasons for action" is because you have the admirable quality of being confused by that which is confused. I think the "reasons for action" category is confused. At least, the only action-guiding norm I can make sense of is desire/preference/motive (let's call it motive). I should eat the ice cream because I have a motive to eat the ice cream. I should exercise more because I have many motives that will be fulfilled if I exercise. And so on. All this stuff about categorical imperatives or divine commands or intrinsic value just confuses things.

How would a computer program enumerate all motives (which according to me, is co-exensional with "all reasons for action")? It would have to roll up its sleeves and do science. As it expands across the galaxy, perhaps encountering other creatures, it could do some behavioral psychology and neuroscience on these creatures to decode their intentional action systems (as it had done already with us), and thereby enumerate all the motives it encounters in the universe, their strengths, the relations between them, and so on.

But really, I'm not yet proposing a solution. What I've described above doesn't even reflect my own meta-ethics. It's just an example. I'm merely raising questions that need to be considered very carefully.

And of course I'm not the only one to do so. Others have raised concerns about CEV and its underlying meta-ethical assumptions. Will Newsome raised some common worries about CEV and proposed computational axiology instead. Tarleton's 2010 paper compares CEV to an alternative proposed by Wallach & Collin.

The philosophical foundations of the Friendly AI project need more philosophical examination, I think. Perhaps you are very confident about your meta-ethical views and about CEV; I don't know. But I'm not confident about them. And as you say, we've only got one shot at this. We need to make sure we get it right. Right?