OK I read the LW comment you linked and skimmed the post, but I don’t see how they show that we should expect lots of crucial considerations to come up specifically—they seem to argue more for “we’re clueless about how much we should do ECL”? (but correct me if I’m wrong, I may have missed something). On your example, but why should I expect their attempts to do so to backfire if I don’t already expect our own attempts to backfire? That seems like it just grounds out in the original debate. (btw, I also would like to get less confused about the similarity thing)
On the simulators, it just seems like its hard to think of possible simulator-motivations where us reaching good outcomes in the simulation would be bad for the base reality, and easy to think of ones where it would be neutral or good.
In general, I think the unawareness angle is genuinely interesting, I’m just not moved by it as much as you, probably for a few different reasons that would take some time to articulate.
they seem to argue more for “we’re clueless about how much we should do ECL”?
I think they suggest that there’s just a lot of subtlety in working out the implications of acausal decision theories in practice. Which is reason to expect more crucial considerations in this domain generally / reason to doubt your “by definition” argument.
but why should I expect their attempts to do so to backfire
Why should you expect them to be positive in expectation either? (The broader point of the unawareness sequence is that there’s an ambiguous pile of positive and negative effects to weigh up.)
On the simulators, it just seems like its hard to think of possible simulator-motivations where us reaching good outcomes in the simulation would be bad for the base reality, and easy to think of ones where it would be neutral or good.
But then we’re back to the Extrapolation argument, which you claimed you weren’t committed to. I’m saying, even if the balance of effects we can think of looks good, we’re looking at a super tiny sliver of the set of effects our fully aware selves would be weighing up — and it’s a biased sample of such effects, so extrapolating from that sample is dubious.
“But then we’re back to the Extrapolation argument, which you claimed you weren’t committed to.”
No, I didn’t claim that—I said the snippet you quoted wasn’t the Extrapolation argument, and I stand by that. I’m definitely sympathetic to something like Extrapolation in general.
The original snippet was more about the acausal stuff, and wasn’t Extrapolation, and the distinct argument I subsequently mentioned about simulators was Extrapolation.
There’s no quick objection I can give to your response specifically (except to simplistically say “no, I don’t buy it, we know more than that, we can have some reasonable guesses about simulators’ intentions”) - properly laying out my disagreements would take a little bit of time and effort, as is usually the case for deep worldview differences.
OK I read the LW comment you linked and skimmed the post, but I don’t see how they show that we should expect lots of crucial considerations to come up specifically—they seem to argue more for “we’re clueless about how much we should do ECL”? (but correct me if I’m wrong, I may have missed something). On your example, but why should I expect their attempts to do so to backfire if I don’t already expect our own attempts to backfire? That seems like it just grounds out in the original debate.
(btw, I also would like to get less confused about the similarity thing)
On the simulators, it just seems like its hard to think of possible simulator-motivations where us reaching good outcomes in the simulation would be bad for the base reality, and easy to think of ones where it would be neutral or good.
In general, I think the unawareness angle is genuinely interesting, I’m just not moved by it as much as you, probably for a few different reasons that would take some time to articulate.
I think they suggest that there’s just a lot of subtlety in working out the implications of acausal decision theories in practice. Which is reason to expect more crucial considerations in this domain generally / reason to doubt your “by definition” argument.
Why should you expect them to be positive in expectation either? (The broader point of the unawareness sequence is that there’s an ambiguous pile of positive and negative effects to weigh up.)
But then we’re back to the Extrapolation argument, which you claimed you weren’t committed to. I’m saying, even if the balance of effects we can think of looks good, we’re looking at a super tiny sliver of the set of effects our fully aware selves would be weighing up — and it’s a biased sample of such effects, so extrapolating from that sample is dubious.
“But then we’re back to the Extrapolation argument, which you claimed you weren’t committed to.”
No, I didn’t claim that—I said the snippet you quoted wasn’t the Extrapolation argument, and I stand by that. I’m definitely sympathetic to something like Extrapolation in general.
(Edited for tone)
Sorry, I don’t understand. The snippet I quoted — about acausal stuff and simulations — is what’s at issue in this discussion.
Regardless, I’m still interested in where you object to my response to Extrapolation. Could you please say more on that?
The original snippet was more about the acausal stuff, and wasn’t Extrapolation, and the distinct argument I subsequently mentioned about simulators was Extrapolation.
There’s no quick objection I can give to your response specifically (except to simplistically say “no, I don’t buy it, we know more than that, we can have some reasonable guesses about simulators’ intentions”) - properly laying out my disagreements would take a little bit of time and effort, as is usually the case for deep worldview differences.