Interesting stuff. Very interesting.
Do you buy it?
That article is arguing that it's all right to value things that aren't mental states over a net gain in mental utility.[1] If, for instance, you're given the choice between feeling like you've made lots of scientific discoveries and actually making just a few scientific discoveries, it's reasonable to prefer the latter.[2]
Well, that example doesn't sound all that ridiculous.
But the logic that Eliezer is using is exactly the same logic that drives somebody who's dying of a horrible disease to refuse antibiotics, because she wants to keep her body natural. And this choice is — well, it isn't wrong, choices can't be "wrong" — but it reflects a very fundamental sort of human bias. It's misguided.
And I think that Eliezer's argument is misguided, too. He can't stand the idea that scientific discovery is only an instrument to increase happiness, so he makes it a terminal value just because he can. This is less horrible than the hippie who thinks that maintaining her "naturalness" is more important than avoiding a painful death, but it's not much less dumb.
[1] Or a net gain in "happiness," if we don't mind using that word as a catchall for "whatever it is that makes good mental states good."
[2] In this discussion we are, of course, ignoring external effects altogether. And we're assuming that the person who gets to experience lots of scientific discoveries really is happier than the person who doesn't, otherwise there's nothing to debate. Let me note that in the real world, it is obviously possible to make yourself less happy by taking joy-inducing drugs — for instance if doing so devalues the rest of your life. This fact makes Eliezer's stance seem a lot more reasonable than it actually is.
Choices can be wrong, and that one is. The hippy is simply mistaken about the kinds of differences that exist between "natural" and "non-natural" things, and about how much she would care about those differences if she knew more chemistry and physics. And presumably if she was less mistaken in expectations of what happens "after you die".
As for relating this to Eliezer's argument, a few examples of wrong non-subjective-happiness values is no demonstration that subjective happiness is the only human terminal value. Especially given the introspective and experimental evidence that people care about certain things that aren't subjective happiness.
(This is a semi-serious introduction to the metaethics sequence. You may find it useful, but don't take it too seriously.)
Meditate on this: A wizard has turned you into a whale. Is this awesome?
"Maybe? I guess it would be pretty cool to be a whale for a day. But only if I can turn back, and if I stay human inside and so on. Also, that's not a whale.
"Actually, a whale seems kind of specific, and I'd be suprised if that was the best thing the wizard can do. Can I have something else? Eternal happiness maybe?"
Meditate on this: A wizard has turned you into orgasmium, doomed to spend the rest of eternity experiencing pure happiness. Is this awesome?
...
"Kindof... That's pretty lame actually. On second thought I'd rather be the whale; at least that way I could explore the ocean for a while.
"Let's try again. Wizard: maximize awesomeness."
Meditate on this: A wizard has turned himself into a superintelligent god, and is squeezing as much awesomeness out of the universe as it could possibly support. This may include whales and starships and parties and jupiter brains and friendship, but only if they are awesome enough. Is this awesome?
...
"Well, yes, that is awesome."
What we just did there is called Applied Ethics. Applied ethics is about what is awesome and what is not. Parties with all your friends inside superintelligent starship-whales are awesome. ~666 children dying of hunger every hour is not.
(There is also normative ethics, which is about how to decide if something is awesome, and metaethics, which is about something or other that I can't quite figure out. I'll tell you right now that those terms are not on the exam.)
"Wait a minute!" you cry, "What is this awesomeness stuff? I thought ethics was about what is good and right."
I'm glad you asked. I think "awesomeness" is what we should be talking about when we talk about morality. Why do I think this?
"Awesome" is not a philosophical landmine. If someone encounters the word "right", all sorts of bad philosophy and connotations send them spinning off into the void. "Awesome", on the other hand, has no philosophical respectability, hence no philosophical baggage.
"Awesome" is vague enough to capture all your moral intuition by the well-known mechanisms behind fake utility functions, and meaningless enough that this is no problem. If you think "happiness" is the stuff, you might get confused and try to maximize actual happiness. If you think awesomeness is the stuff, it is much harder to screw it up.
If you do manage to actually implement "awesomeness" as a maximization criteria, the results will be actually good. That is, "awesome" already refers to the same things "good" is supposed to refer to.
"Awesome" does not refer to anything else. You think you can just redefine words, but you can't, and this causes all sorts of trouble for people who overload "happiness", "utility", etc.
You already know that you know how to compute "Awesomeness", and it doesn't feel like it has a mysterious essence that you need to study to discover. Instead it brings to mind concrete things like starship-whale math-parties and not-starving children, which is what we want anyways. You are already enabled to take joy in the merely awesome.
"Awesome" is implicitly consequentialist. "Is this awesome?" engages you to think of the value of a possible world, as opposed to "Is this right?" which engages to to think of virtues and rules. (Those things can be awesome sometimes, though.)
I find that the above is true about me, and is nearly all I need to know about morality. It handily inoculates against the usual confusions, and sets me in the right direction to make my life and the world more awesome. It may work for you too.
I would append the additional facts that if you wrote it out, the dynamic procedure to compute awesomeness would be hellishly complex, and that right now, it is only implicitly encoded in human brains, and no where else. Also, if the great procedure to compute awesomeness is not preserved, the future will not be awesome. Period.
Also, it's important to note that what you think of as awesome can be changed by considering things from different angles and being exposed to different arguments. That is, the procedure to compute awesomeness is dynamic and created already in motion.
If we still insist on being confused, or if we're just curious, or if we need to actually build a wizard to turn the universe into an awesome place (though we can leave that to the experts), then we can see the metaethics sequence for the full argument, details, and finer points. I think the best post (and the one to read if only one) is joy in the merely good.