I don’t think it’s false, it’s more like implicitly conditioned on what you expect. I would say it unrolls into “I don’t want to live past 100 given that I expect myself to be sick, feeble-minded, and maybe in permanent low-grade pain by that point”.
Take away the implied condition and the preference will likely change as well.
Unfortunately the implied conditional is often a alief, not a belief. So if you say “imagine that you were healthy, smart, and happy...” they’ll still often say they don’t want to live that long. But if there were a lot of healthy, smart, happy 100 year olds, people would change their minds.
It isn’t rare to come across an actually healthy, smart, and happy 80 year old who says that they feel that they have basically lived long enough. Obviously this is anecdotal but I would estimate that I have seen or heard of such incidents at least ten times in my life. So this is not only a counterfactual. People sometimes preserve these preferences even when the situation is actual.
Fair enough. Either way, it’s not a contradiction, it’s just imprecision in communication of preferences.
Note that there may be inconsistency over time—predicted preferences and actual preferences often differ. I don’t see any reason that wouldn’t be true of an AI as well.
I don’t think it’s false, it’s more like implicitly conditioned on what you expect. I would say it unrolls into “I don’t want to live past 100 given that I expect myself to be sick, feeble-minded, and maybe in permanent low-grade pain by that point”.
Take away the implied condition and the preference will likely change as well.
Unfortunately the implied conditional is often a alief, not a belief. So if you say “imagine that you were healthy, smart, and happy...” they’ll still often say they don’t want to live that long. But if there were a lot of healthy, smart, happy 100 year olds, people would change their minds.
And what makes you believe that? I doubt that you have data.
It isn’t rare to come across an actually healthy, smart, and happy 80 year old who says that they feel that they have basically lived long enough. Obviously this is anecdotal but I would estimate that I have seen or heard of such incidents at least ten times in my life. So this is not only a counterfactual. People sometimes preserve these preferences even when the situation is actual.
In fact I do. Parental data :-(
Fair enough. Either way, it’s not a contradiction, it’s just imprecision in communication of preferences.
Note that there may be inconsistency over time—predicted preferences and actual preferences often differ. I don’t see any reason that wouldn’t be true of an AI as well.