I don’t think those are the only two ways to refute the argument. I can think of at least two more:
(3) Deny the third step of the argument’s structure — the “so we should doubt Eliezer’s conclusions” part. Analogical reasoning applied to surface features of arguments is not reliable. There’s really no substitute for actually examining an argument.
(4) Disagree that construing the hippie’s position as constituting any sort of “reasoning” that may or may not be “suspect” is a meaningful description of what’s going on in your hypothetical (or at least, the interesting aspect of what’s going on, the part we’re concerned with). The point I was making is this: what’s relevant in that scenario is that the hippie has “keeping her body natural” as a terminal value. If that’s a coherent value, then the rest of the reasoning (“and therefore I shouldn’t take this pill”) is trivial and of no interest to us. Now it may not be a coherent value, as I said; but if it is — well, arguing with terminal values is not a matter of poking holes in someone’s logic. Terminal values are given.
As for your other points:
It’s true, you didn’t say “mistake” on its own. What I am wondering is this: ok, refusing to become orgasmium fails to satisfy the mathematical requirements of hedonistic utilitarianism.
But why should anyone care about that?
I don’t mean this as a general, out-of-hand dismissal; I am asking, specifically, why such a requirement would override a person’s desires:
Person A: If you become orgasmium, you would feel more pleasure than you otherwise would. Person B: But I don’t want to become orgasmium. Person A: But if you want to feel as much pleasure as possible, then you should become orgasmium! Person B: But… I don’t want to become orgasmium.
I see Person B’s position as being the final word on the matter (especially if, as you say, we’re ignoring external consequences). Person A may be entirely right — but so what? Why should that affect Person B’s judgments? Why should the mathematical requirements behind Person A’s framework have any relevance to Person B’s decisions? In other words, why should we be hedonistic utilitarians, if we don’t want to be?
(If we imagine the above argument continuing, it would develop that Person B doesn’t want to feel as much pleasure as possible; or, at the least, wants other things too, and even the pleasure thing he wants only given certain conditions; in other words, we’d arrive at conclusions along the lines outlined in the “Complexity of value” wiki entry.)
(As an aside, I’m still not sure why you’re ignoring external effects in your arguments.)
Person A: If you become orgasmium, you would feel more pleasure than you otherwise would.
Person B: But I don’t want to become orgasmium.
If I become orgasmium, then I would cease to exist, and the orgasmium, which is not me in any meaningful sense, will have more pleasure than I otherwise would have. But I don’t care about the pleasure of this orgasmium, and certainly would not pay my existence for it.
Person A: If you become orgasmium, you would feel more pleasure than you otherwise would.
Person B: But I don’t want to become orgasmium.
Person A: But if you want to feel as much pleasure as possible, then you should become orgasmium! Person B: But… I don’t want to become orgasmium.
I see Person B’s position as being the final word on the matter (especially if, as you say, we’re ignoring external consequences). Person A may be entirely right — but so what? Why should that affect Person B’s judgments? Why should the mathematical requirements behind Person A’s framework have any relevance to Person B’s decisions? In other words, why should we be hedonistic utilitarians, if we don’t want to be?
The difficulty here, of course, is that Person B is using a cached heuristic that outputs “no” for “become orgasmium”; and we cannot be certain that this heuristic is correct in this case. Just as Person A is using the (almost certainly flawed) heuristic “feel as much pleasure as possible”, which outputs “yes” for “become orgasmium”.
The difficulty here, of course, is that Person B is using a cached heuristic that outputs “no” for “become orgasmium”
Why do you think so?
we cannot be certain that this heuristic is correct in this case.
What do you mean by “correct”?
Edit: I think it would be useful for any participants in discussions like this to read Eliezer’s Three Worlds Collide. Not as fictional evidence, but as an examination of the issues, which I think it does quite well. A relevant quote, from chapter 4, “Interlude with the Confessor”:
A sigh came from that hood. “Well… would you prefer a life entirely free of pain and sorrow, having sex all day long?”
“Not… really,” Akon said.
The shoulders of the robe shrugged. “You have judged. What else is there?”
I give a decent probability to the optimal order of things containing absolutely zero pleasure. I assign a lower, but still significant, probability to it containing an infinite amount of pain in any given subjective interval.
… why? Humans definitely appear to want to avoid pain and enjoy pleasure. i suppose I can see pleasure being replaced with “better” emotions, but I’m really baffled regarding the pain. Is it to do with punishment? Challenge? Something I haven’t thought of?
Agreed, pretty much. I said significant probability, not big. I’m not good at translating anticipations into numbers, but no more than 5%. Mostly based on extreme outside view, as in “something I haven’t thought of”.
I don’t think those are the only two ways to refute the argument. I can think of at least two more:
(3) Deny the third step of the argument’s structure — the “so we should doubt Eliezer’s conclusions” part. Analogical reasoning applied to surface features of arguments is not reliable. There’s really no substitute for actually examining an argument.
(4) Disagree that construing the hippie’s position as constituting any sort of “reasoning” that may or may not be “suspect” is a meaningful description of what’s going on in your hypothetical (or at least, the interesting aspect of what’s going on, the part we’re concerned with). The point I was making is this: what’s relevant in that scenario is that the hippie has “keeping her body natural” as a terminal value. If that’s a coherent value, then the rest of the reasoning (“and therefore I shouldn’t take this pill”) is trivial and of no interest to us. Now it may not be a coherent value, as I said; but if it is — well, arguing with terminal values is not a matter of poking holes in someone’s logic. Terminal values are given.
As for your other points:
It’s true, you didn’t say “mistake” on its own. What I am wondering is this: ok, refusing to become orgasmium fails to satisfy the mathematical requirements of hedonistic utilitarianism.
But why should anyone care about that?
I don’t mean this as a general, out-of-hand dismissal; I am asking, specifically, why such a requirement would override a person’s desires:
Person A: If you become orgasmium, you would feel more pleasure than you otherwise would.
Person B: But I don’t want to become orgasmium.
Person A: But if you want to feel as much pleasure as possible, then you should become orgasmium!
Person B: But… I don’t want to become orgasmium.
I see Person B’s position as being the final word on the matter (especially if, as you say, we’re ignoring external consequences). Person A may be entirely right — but so what? Why should that affect Person B’s judgments? Why should the mathematical requirements behind Person A’s framework have any relevance to Person B’s decisions? In other words, why should we be hedonistic utilitarians, if we don’t want to be?
(If we imagine the above argument continuing, it would develop that Person B doesn’t want to feel as much pleasure as possible; or, at the least, wants other things too, and even the pleasure thing he wants only given certain conditions; in other words, we’d arrive at conclusions along the lines outlined in the “Complexity of value” wiki entry.)
(As an aside, I’m still not sure why you’re ignoring external effects in your arguments.)
If I become orgasmium, then I would cease to exist, and the orgasmium, which is not me in any meaningful sense, will have more pleasure than I otherwise would have. But I don’t care about the pleasure of this orgasmium, and certainly would not pay my existence for it.
The difficulty here, of course, is that Person B is using a cached heuristic that outputs “no” for “become orgasmium”; and we cannot be certain that this heuristic is correct in this case. Just as Person A is using the (almost certainly flawed) heuristic “feel as much pleasure as possible”, which outputs “yes” for “become orgasmium”.
Why do you think so?
What do you mean by “correct”?
Edit: I think it would be useful for any participants in discussions like this to read Eliezer’s Three Worlds Collide. Not as fictional evidence, but as an examination of the issues, which I think it does quite well. A relevant quote, from chapter 4, “Interlude with the Confessor”:
Humans are not perfect reasoners.
[Edited for clarity.]
I give a decent probability to the optimal order of things containing absolutely zero pleasure. I assign a lower, but still significant, probability to it containing an infinite amount of pain in any given subjective interval.
Is this intended as a reply to my comment?
reply to the entire thread really.
Fair enough.
Is this intended as a reply to my comment?
… why? Humans definitely appear to want to avoid pain and enjoy pleasure. i suppose I can see pleasure being replaced with “better” emotions, but I’m really baffled regarding the pain. Is it to do with punishment? Challenge? Something I haven’t thought of?
Agreed, pretty much. I said significant probability, not big. I’m not good at translating anticipations into numbers, but no more than 5%. Mostly based on extreme outside view, as in “something I haven’t thought of”.
Oh, right. “Significance” is subjective, I guess. I assumed it meant, I don’t know, >10% or whatever.