How does EU resolve a toy problem like Jews vs Nazis? Or, in a more realistic example, hiring an African-American/a woman/a gay person to work in a racist/misogynistic/homophobic work environment? Presumably it would fight the hypothetical and state that “if the Nazis were objectively rational they would not hate Jews”?
It is not necessary for Nazis hating Jews to be rational that there are reasons for hating Jews, only that the reasons for not hating Jews do not outweigh the reasons for hating Jews. But their reasons for hating Jews are either self-contradictory or in fact support not hating Jews when properly worked out.
I can see the idea of fighting the hypothetical and arguing that the Nazis hate of the Jews isn’t rational, and in a state of perfect information they would think differently. At the very least they would need some kind of rational reason to hate the Jews. The scenario seems slightly different if the Jews are responsible for harming the goals of the Nazis in some way. For instance, if the Jews, I dunno, consumed disproportionate amounts of food in relation to their size and thus posed a threat to the Nazis in terms of causing worldwide famine. Even then, maximizing EU would probably involve some weird solution like limiting the food intake of the Jews, rather than outright killing them or putting them in concentration camps.
Another way of going at it would be to argue that killing the Jews would have a disproportionate negative effect on their Eudaimonia that cannot realistically be offset by the Nazis feeling better about a world without Jews. Though this may not hold if the number of Jews is sufficiently small, and the number of Nazis sufficiently large. For instance, 1 Jew vs. 1 billion Nazis.
To be honest this is something of a problem for all forms of Utilitarianism, and I don’t think EU actually solves it. EU fixes some issues people have about Classical and Preference Utilitarianism, but it doesn’t actually solve big ones like the various Repugnant Conclusions. Alas, that seems to be a problem with any form of Utilitarianism that accepts the “Greatest Number” maximization principle.
I’m not sure what exactly you’re asking about the “hiring an African-American/a woman/a gay person to work in a racist/misogynistic/homophobic work environment”. Can you clarify this example?
Another way of going at it would be to argue that killing the Jews would have a disproportionate negative effect on their Eudaimonia that cannot realistically be offset by the Nazis feeling better about a world without Jews.
Would it be OK to make 1000 Nazis feel better by making 1 Jew feel worse?
I’m not sure what exactly you’re asking about the “hiring an African-American/a woman/a gay person to work in a racist/misogynistic/homophobic work environment”. Can you clarify this example?
Same as the original example: e.g. 1000 (bigoted) men get pissed off every day seeing a woman doing a man’s job.
it doesn’t actually solve big ones like the various Repugnant Conclusions
Right, that’s the main issue. If you cannot solve it, an AGI implementing the algorithm will inevitably run into one.
I suppose an interesting way of attacking this problem would be to argue that while the magnitude of 1 million Jews is significant. The magnitude of 1 Jew is not. What I mean by this is that the degree to which the 1 million Nazis will benefit from the extermination of the Jews is actually proportional to the number of Jews that exist. This amount of Eudaimonic benefit then, will never exceed the loss of Eudaimonia that occurs when the Jews are exterminated or interned.
Making 1 Jew feel worse is a much smaller effect than making 1000 Jews feel worse. Thus, making 1 Jew feel worse has a much smaller effect on each of the 1000 Nazis than the effect of making 1000 Jews feel worse. The net effect of making 1 Jew feel worse and 1000 Nazis feel better is actually the same as making 1 Jew feel worse to make 1 Nazis feel better, or 1 million Jews feel worse to make 1 million Nazis feel better. This assumes that the Nazis’ hatred and pleasure from seeing their enemy suffer is not simply additive, but proportional to the size and scope of their “enemy”.
Thus the question really boils down to, is it alright to make one person feel bad in order to make one person feel good? If one takes the stance that equivalent pain is worse than equivalent pleasure, then the answer is no. To reach this stance, one needs only assert the validity of this thought experiment:
Would you endure one day of torture in exchange for one day of bliss? Most humans, are biased to say no. Humans in general are more pain averse than they are pleasure seeking. Therefore, making the Jews feel bad to make the Nazis feel good is not justifiable.
I’m honestly not sure if this argument makes much sense, but I present it to you as something to consider.
The problem here is that your math doesn’t seem to take into account that humans are deeply scope insensitive and our emotional involvement is largely a function of ‘distance’ (space, time, appearance, etc).
(Note: I am not a utilitarian and do not condone any illegal actions. This is a hypothetical to better express my point.)
A public execution on national TV of a hated individual, or even just a member of a hated group, could potentially give tens or hundreds of millions of observers a half hour of high-quality entertainment. Even discounting the value of the positive memories and added social cohesion from the shared experience, the kind of money advertisers will pay for even a poorly rated cable show should prove that the execution is a net benefit.
A newspaper article or TV news report, even with grizzly pictures and video, describing the deaths of hundreds of members of a hated group is less personal and thus less intense an experience. The same viewers might feel better in an abstract sense, maybe even enough to break even, but it’s probably not a particularly useful expenditure. Even if the number of viewers increased by a hundred-fold to match the victims it’s still going to be a worse deal in $$$ per utilons.
Killing millions in a short time-frame for entertainment value is just realistically not going to be an efficient use of time and energy, even if trillions or quadrillions of human viewers were watching. A million really is a statistic, and it’s unreasonable to expect anyone to care more about a million deaths than a half dozen.
How does EU resolve a toy problem like Jews vs Nazis? Or, in a more realistic example, hiring an African-American/a woman/a gay person to work in a racist/misogynistic/homophobic work environment? Presumably it would fight the hypothetical and state that “if the Nazis were objectively rational they would not hate Jews”?
It is not necessary for Nazis hating Jews to be rational that there are reasons for hating Jews, only that the reasons for not hating Jews do not outweigh the reasons for hating Jews. But their reasons for hating Jews are either self-contradictory or in fact support not hating Jews when properly worked out.
I can see the idea of fighting the hypothetical and arguing that the Nazis hate of the Jews isn’t rational, and in a state of perfect information they would think differently. At the very least they would need some kind of rational reason to hate the Jews. The scenario seems slightly different if the Jews are responsible for harming the goals of the Nazis in some way. For instance, if the Jews, I dunno, consumed disproportionate amounts of food in relation to their size and thus posed a threat to the Nazis in terms of causing worldwide famine. Even then, maximizing EU would probably involve some weird solution like limiting the food intake of the Jews, rather than outright killing them or putting them in concentration camps.
Another way of going at it would be to argue that killing the Jews would have a disproportionate negative effect on their Eudaimonia that cannot realistically be offset by the Nazis feeling better about a world without Jews. Though this may not hold if the number of Jews is sufficiently small, and the number of Nazis sufficiently large. For instance, 1 Jew vs. 1 billion Nazis.
To be honest this is something of a problem for all forms of Utilitarianism, and I don’t think EU actually solves it. EU fixes some issues people have about Classical and Preference Utilitarianism, but it doesn’t actually solve big ones like the various Repugnant Conclusions. Alas, that seems to be a problem with any form of Utilitarianism that accepts the “Greatest Number” maximization principle.
I’m not sure what exactly you’re asking about the “hiring an African-American/a woman/a gay person to work in a racist/misogynistic/homophobic work environment”. Can you clarify this example?
Would it be OK to make 1000 Nazis feel better by making 1 Jew feel worse?
Same as the original example: e.g. 1000 (bigoted) men get pissed off every day seeing a woman doing a man’s job.
Right, that’s the main issue. If you cannot solve it, an AGI implementing the algorithm will inevitably run into one.
I suppose an interesting way of attacking this problem would be to argue that while the magnitude of 1 million Jews is significant. The magnitude of 1 Jew is not. What I mean by this is that the degree to which the 1 million Nazis will benefit from the extermination of the Jews is actually proportional to the number of Jews that exist. This amount of Eudaimonic benefit then, will never exceed the loss of Eudaimonia that occurs when the Jews are exterminated or interned.
Making 1 Jew feel worse is a much smaller effect than making 1000 Jews feel worse. Thus, making 1 Jew feel worse has a much smaller effect on each of the 1000 Nazis than the effect of making 1000 Jews feel worse. The net effect of making 1 Jew feel worse and 1000 Nazis feel better is actually the same as making 1 Jew feel worse to make 1 Nazis feel better, or 1 million Jews feel worse to make 1 million Nazis feel better. This assumes that the Nazis’ hatred and pleasure from seeing their enemy suffer is not simply additive, but proportional to the size and scope of their “enemy”.
Thus the question really boils down to, is it alright to make one person feel bad in order to make one person feel good? If one takes the stance that equivalent pain is worse than equivalent pleasure, then the answer is no. To reach this stance, one needs only assert the validity of this thought experiment:
Would you endure one day of torture in exchange for one day of bliss? Most humans, are biased to say no. Humans in general are more pain averse than they are pleasure seeking. Therefore, making the Jews feel bad to make the Nazis feel good is not justifiable.
I’m honestly not sure if this argument makes much sense, but I present it to you as something to consider.
The problem here is that your math doesn’t seem to take into account that humans are deeply scope insensitive and our emotional involvement is largely a function of ‘distance’ (space, time, appearance, etc).
(Note: I am not a utilitarian and do not condone any illegal actions. This is a hypothetical to better express my point.)
A public execution on national TV of a hated individual, or even just a member of a hated group, could potentially give tens or hundreds of millions of observers a half hour of high-quality entertainment. Even discounting the value of the positive memories and added social cohesion from the shared experience, the kind of money advertisers will pay for even a poorly rated cable show should prove that the execution is a net benefit.
A newspaper article or TV news report, even with grizzly pictures and video, describing the deaths of hundreds of members of a hated group is less personal and thus less intense an experience. The same viewers might feel better in an abstract sense, maybe even enough to break even, but it’s probably not a particularly useful expenditure. Even if the number of viewers increased by a hundred-fold to match the victims it’s still going to be a worse deal in $$$ per utilons.
Killing millions in a short time-frame for entertainment value is just realistically not going to be an efficient use of time and energy, even if trillions or quadrillions of human viewers were watching. A million really is a statistic, and it’s unreasonable to expect anyone to care more about a million deaths than a half dozen.