If we can extract utility in a purer fashion, I think we should. At the bare minimum, it would be much more run-time efficient. That said, trying to do so opens up a whole can of worms of really hard problems. This proposal, provided you're careful about how you set it up, pretty much dodges all of that, as far as I can tell. Which means we could implement it faster, should that be necessary. I mean, yes, AGI is still very hard problem, but I think this reduces the F part of FAI to a manageable level, even given the impoverished understanding we have right now. And, assuming a properly modular code base, it would not be too difficult to swap out 'get utility by asking questions' with 'get utility by analyzing model directly.' Actually, the thing might even do that itself, since it might better maximize its utility function.
I think this reduces the F part of FAI to a manageable level
Well, it replaces it with a more manageable problem, anyway.
More specifically, it replaces the question "what's best for people?" with the question "what would people choose, given a choice?"
Of course, if I'm concerned that those questions might have different answers, I might be reluctant to replace the former with the latter.
I've been reading through this to get a sense of the state of the art at the moment:
http://lukeprog.com/SaveTheWorld.html
Near the bottom, when discussing safe utility functions, the discussion seems to center on analyzing human values and extracting from them some sort of clean, mathematical utility function that is universal across humans. This seems like an enormously difficult (potentially impossible) way of solving the problem, due to all the problems mentioned there.
Why shouldn't we just try to design an average bounded utility maximizer? You'd build models of all your agents (if you can't model arbitrary ordered information systems, you haven't got an AI), run them through your model of the future resulting from a choice, take the summation of their utility over time, and take the average across all the people all the time. To measure the utility (or at least approximate it), you could just ask the models. The number this spits out is the output of your utility function. It'd probably also be wise to add a reflexive consistency criteria, such that the original state of your model must consider all future states to be 'the same person.' -- and I acknowledge that that last one is going to be a bitch to formalize. When you've got this utility function, you just... maximize it.
Something like this approach seems much more robust. Even if human values are inconsistent, we still end up in a universe where most (possibly all) people are happy with their lives, and nobody gets wireheaded. Because it's bounded, you're even protected against utility monsters. Has something like this been considered? Is there an obvious reason it won't work, or would produce undesirable results?
Thanks,
Dolores