I suspect that value systems that simply seek to minimize pain are poor value systems.

Fair enough, as long as you're not presupposing that our value systems -- which are probably better than "minimize pain" -- are unlikely to have strong anti-torture preferences.

As for the other two points: you might have already argued for them somewhere else, but if not, feel free to say more here. It's at least obvious that anti-em-torture is harder to enforce, but are you thinking it's also probably too hard to even know whether a computation creates a person being tortured? Or that our notion of torture is probably confused with respect to ems (and possibly with respect to us animals too)?

Has anyone attempted to prove the statement "Consciousness of a Turing machine is undecideable"? The proof (if it's true) might look a lot like the proof that the halting problem is undecideable.

Your conjecture seems to follow from Rice's theorem, assuming the personhood of a running computation is a property of the partial function its algorithm computes. Also, I think you can prove your conjecture by taking a certain proof that the Halting Problem is undecidable and replacing 'halts' with 'is conscious'. I can track this down if you're still interested.

But this doesn't mess up Eliezer's plans at all: you can have "nonhalting predicates" that output "doesn't halt" or "I don't know", analogous to the nonperson predicates proposed here.

I think you're right that many of the relevant empirical facts will be about your preferences. At risk of repeating myself, though, there are other facts that matter, like whether ems are conscious, how much it costs to prevent torture, and what better things we could be directing our efforts towards.

To partially answer your question ("how much effort is it worth to prevent the torture of ems?"): I sure do want torture to not happen, unless I'm hugely wrong about my preferences. So if preventing em torture turns out to not be worth a lot of effort, I predict it's because there are other bad things that can be more efficiently prevented with our efforts.

But I'm still not sure how you wanted your question interpreted. Are you, for example, wondering whether you care about ems as much as non-em people? Or whether you care about torture at all? Or whether the best strategy requires putting our efforts somewhere else, given that you care about torture and ems?

Are you unsure about whether em torture is as bad as non-em torture? Or do you just mean to express that we take em torture too seriously? Or is this a question about how much we should pay to prevent torture (of ems or not), given that there are other worthy causes that need our efforts?

Or, to ask all those questions at once: do you know which empirical facts you need to know in order to answer this?

Oh, we agree, I was just unclear about my objection. Fixed.