That seems a little bit ad hoc to me. Either you care about dogs (and then even the tiniest non-zero amount of caring should be enough for the argument) or you don’t. People often come up with lexical constructs when they feel uncomfortable with the anticipation of having to change their behaviour. As a consequentialist, I figured out that I care a bit about dog welfare, and being aware of my scope insensitivity, I can see why some people dislike biting the bullet which results from simple additive reasoning. An option would be, though, to say that one’s brain (and anyhow therefore one‘s moral framework) is only capable of a certain amount of caring for dogs and that this variable is independent of the number of dogs. For me that wouldn’t work out though for I care about the content of sentient experience in a additive way. But for the sake of the argument : if a hyperintelligent alien came to the Earth (eg. an AI), what would you propose how the alien should figure out which mechanisms in the universe should be of moral concern? What would you think of the agent’s morality if it discounted your welfare lexically?
That seems a little bit ad hoc to me. Either you care about dogs (and then even the tiniest non-zero amount of caring should be enough for the argument) or you don’t.
You can’t tell me, first, that above all I must conform to a particular ritual of cognition, and then that, if I conform to that ritual, I must change my morality to avoid being Dutch-booked. Toss out the losing ritual; don’t change the definition of winning.
What you are doing here is insisting that I conform to your ritual of cognition (i.e. total utilitarianism with real-number valuation and additive aggregation). I see no reason to accede to such a demand.
The following are facts about what I do and don’t care about:
1) All else being equal, I prefer that a dog not be tortured. 2) All else being equal, I prefer that my grandmother not be tortured. 3) I prefer any number of dogs being tortured to my grandmother being tortured. 4 through ∞) Some other stuff about my preferences, skipped for brevity.
#s 2 and 3 are very strong preferences. #1 is less so.
Now I want to find a moral calculus that captures those facts. You, on the other hand, are telling me that, first, I must accept your moral calculus, and then, that if I do so, I must toss out one of the aforementioned preferences.
I decline to do either of those things. (As Eliezer says in the above link: The utility function is not up for grabs.)
But for the sake of the argument : if a hyperintelligent alien came to the Earth (eg. an AI), what would you propose how the alien should figure out which mechanisms in the universe should be of moral concern?
I don’t know. This is the kind of thing that demonstrates why we need FAI theory and CEV.
What would you think of the agent’s morality if it discounted your welfare lexically?
I would think that its morality is different from mine. Also, I would be sad, because presumably such a morality on the AI’s part would result in bad things for me. Your point?
Ok, let’s do some basic friendly AI theory: Would a friendly AI discount the welfare of “weaker” beings as you and me (compared to this hyper-agent) lexically? Could that possibly be a fAI? If not, then I think we should also rethink our moral behaviour towards weaker beings in our game here for our decisions can result in bad things for them correspondingly.
My bad about the ritual. Thanks. Out of interest about your preferences: Imagine the grandmother and the dog next to each other. A perfect scientist starts to exchange pairs of atoms (let’s assume here that both individuals contain the same amount of atoms) so that the grandmother more and more transforms into the dog (of course there will be several weird intermediary stages). For the scientist knows his experiment very well, none of the objects will die; in the end it’ll look like the two objects changed their places.
At which point does the mother stop counting lexically more than the dog?
Sometimes continuity arguments can be defeated by saying: “No I don’t draw an arbitrary line; I adjust gradually whereas in the beginning I care a lot about the grandmother and in the end just very little about the remaining dog.” But I think that this argument doesn’t work here for we deal with a lexical prioritization. How would you act in such a scenario?
A perfect scientist starts to exchange pairs of atoms (let’s assume here that both individuals contain the same amount of atoms) so that the grandmother more and more transforms into the dog (of course there will be several weird intermediary stages).
Identity isn’t in specific atoms. The effect of swapping a carbon atom in the grandma with a carbon atom in the dog is none at all.
Jiro’s response shows one good reason why I don’t find that thought experiment very interesting. Another obvious reason is its extreme implausibility and, I strongly suspect, actual incoherence (given what we know about physics and biology). I think I can safely say “I have no idea what I would prefer”, much like Eliezer finds no reason to answer how he would explain his arm being turned into a blue tentacle, and not have that be counted against me.
On to FAI theory:
Would a friendly AI discount the welfare of “weaker” beings as you and me (compared to this hyper-agent) lexically? Could that possibly be a fAI?
By definition, it would not, because if it did, then it would be an Unfriendly AI.
If not, then I think we should also rethink our moral behaviour towards weaker beings in our game here for our decisions can result in bad things for them correspondingly.
How do you get from facts about the behavior of an FAI to claims about how we should act? I spy one of those pesky “is-ought” transitions that bedeviled Hume!
Corollary: why should we care that our behavior results in bad things for animals? Isn’t that the question in the first place, and doesn’t your statement beg said question?
That seems a little bit ad hoc to me. Either you care about dogs (and then even the tiniest non-zero amount of caring should be enough for the argument) or you don’t. People often come up with lexical constructs when they feel uncomfortable with the anticipation of having to change their behaviour. As a consequentialist, I figured out that I care a bit about dog welfare, and being aware of my scope insensitivity, I can see why some people dislike biting the bullet which results from simple additive reasoning. An option would be, though, to say that one’s brain (and anyhow therefore one‘s moral framework) is only capable of a certain amount of caring for dogs and that this variable is independent of the number of dogs. For me that wouldn’t work out though for I care about the content of sentient experience in a additive way. But for the sake of the argument : if a hyperintelligent alien came to the Earth (eg. an AI), what would you propose how the alien should figure out which mechanisms in the universe should be of moral concern? What would you think of the agent’s morality if it discounted your welfare lexically?
Eliezer handled this sort of objection in Newcomb’s Problem and Regret of Rationality:
What you are doing here is insisting that I conform to your ritual of cognition (i.e. total utilitarianism with real-number valuation and additive aggregation). I see no reason to accede to such a demand.
The following are facts about what I do and don’t care about:
1) All else being equal, I prefer that a dog not be tortured.
2) All else being equal, I prefer that my grandmother not be tortured.
3) I prefer any number of dogs being tortured to my grandmother being tortured.
4 through ∞) Some other stuff about my preferences, skipped for brevity.
#s 2 and 3 are very strong preferences. #1 is less so.
Now I want to find a moral calculus that captures those facts. You, on the other hand, are telling me that, first, I must accept your moral calculus, and then, that if I do so, I must toss out one of the aforementioned preferences.
I decline to do either of those things. (As Eliezer says in the above link: The utility function is not up for grabs.)
I don’t know. This is the kind of thing that demonstrates why we need FAI theory and CEV.
I would think that its morality is different from mine. Also, I would be sad, because presumably such a morality on the AI’s part would result in bad things for me. Your point?
Ok, let’s do some basic friendly AI theory: Would a friendly AI discount the welfare of “weaker” beings as you and me (compared to this hyper-agent) lexically? Could that possibly be a fAI? If not, then I think we should also rethink our moral behaviour towards weaker beings in our game here for our decisions can result in bad things for them correspondingly.
My bad about the ritual. Thanks. Out of interest about your preferences: Imagine the grandmother and the dog next to each other. A perfect scientist starts to exchange pairs of atoms (let’s assume here that both individuals contain the same amount of atoms) so that the grandmother more and more transforms into the dog (of course there will be several weird intermediary stages). For the scientist knows his experiment very well, none of the objects will die; in the end it’ll look like the two objects changed their places. At which point does the mother stop counting lexically more than the dog? Sometimes continuity arguments can be defeated by saying: “No I don’t draw an arbitrary line; I adjust gradually whereas in the beginning I care a lot about the grandmother and in the end just very little about the remaining dog.” But I think that this argument doesn’t work here for we deal with a lexical prioritization. How would you act in such a scenario?
You can ask the same question with the grandmother turning into a tree instead of into a dog.
Identity isn’t in specific atoms. The effect of swapping a carbon atom in the grandma with a carbon atom in the dog is none at all.
Jiro’s response shows one good reason why I don’t find that thought experiment very interesting. Another obvious reason is its extreme implausibility and, I strongly suspect, actual incoherence (given what we know about physics and biology). I think I can safely say “I have no idea what I would prefer”, much like Eliezer finds no reason to answer how he would explain his arm being turned into a blue tentacle, and not have that be counted against me.
On to FAI theory:
By definition, it would not, because if it did, then it would be an Unfriendly AI.
How do you get from facts about the behavior of an FAI to claims about how we should act? I spy one of those pesky “is-ought” transitions that bedeviled Hume!
Corollary: why should we care that our behavior results in bad things for animals? Isn’t that the question in the first place, and doesn’t your statement beg said question?