The idea that maximally-coherent agents look like squiggle-maximizers raises the question: what would it look like for humans to become maximally coherent?
One answer, which Yudkowsky gives here, is that conscious experiences are just a “weird and more abstract and complicated pattern that matter can be squiggled into”.
But that seems to be in tension with another claim he makes, that there’s no way for one agent’s conscious experiences to become “more real” except at the expense of other conscious agents—a claim which, according to him, motivates average utilitarianism across the multiverse.
Clearly a squiggle-maximizer would not be an average squigglean. So what’s the disanalogy here? It seems like @Eliezer Yudkowsky is basically using SSA, but comparing between possible multiverses—i.e. when facing the choice between creating agent A or not, you look at the set of As in the multiverse where you decided yes, and compare it to the set of As in the multiverse where you decided no, and (if you’re deciding for the good of A) you pick whichever one gives A a better time on average.
Yudkowsky has written before (can’t find the link) that he takes this approach because alternatives would entail giving up on predictions about his future experiences—e.g. constantly predicting he’s a Boltzmann brain and will dissolve in the next second. But this argument by Wei Dai shows that agents which reason in this way can be money-pumped by creating arbitrarily short-lived copies of them. Based on this I claim that Yudkowsky’s preferences are incoherent, and that the only coherent thing to do here is to “expect to be” a given copy in proportion to the resources it will have available, as anthropic decision theory claims. (Incidentally, this also explains why we’re at the hinge of history.)
But this is just an answer, it doesn’t dissolve the problem. What could? Some wild guesses:
You are allowed to have preferences about the external world, and you are allowed to have preferences about your “thread of experience”—you’re just not allowed to have both. The incoherence comes from trying to combine the two; the coherent thing to do would be to put them into different agents, who will then end up in very different parts of the multiverse.
Another way of framing this: you are allowed to be a decision-maker, and you are allowed to be a repository of welfare, but you’re not allowed to be both (on pain of incoherence/being dutch-booked).
Something totally different: the problem here is that we don’t have intuitive experience of being agents which can copy themselves, shut down copies, re-merge, etc. If we did, then maybe SSA would seem as silly as expecting to end up in a different universe whenever we went to sleep.
Actually, maybe the operative thing we lack experience with is not just splitting into different subagents, but rather merging together afterwards. What does it feel like to have been thousands of different parallel agents, and now be a single agent with their unified experiences? What sort of identity would one construct in that situation? Maybe this is an important part of dissolving the problem.
what would it look like for humans to become maximally coherent [agents]?
In your comments, you focus on issues of identity—who are “you”, given the possibility of copies, inexact counterparts in other worlds, and so on. But I would have thought that the fundamental problem here is, how to make a coherent agent out of an agent with preferences that are inconsistent over time, an agent with competing desires and no definite procedure for deciding which desire has priority, and so on, i.e. problems that exist even when there is no additional problem of identity.
Clearly a squiggle-maximizer would not be an average squigglean
Why??? Being expected squiggle maximizer literally means that you implement policy that produces maximum average number of squiggles across the multiverse.
The “average” is interpreted with respect to quality. Imagine that your only option is to create low-quality squiggles, or not to do so. In isolation, you’d prefer to produce them than not to produce them. But then you find out that the rest of the multiverse is full of high-quality squiggles. Do you still produce the low-quality squiggles? A total squigglean would; an average squigglean wouldn’t.
It depends upon whether the maximizer considers its corner of the multiverse to be currently measurable by squiggle quality, or to be omitted from squiggle calculations at all. In principle these are far from the only options as utility functions can be arbitrarily complex, but exploring just two may be okay so long as we remember that we’re only talking about 2 out of infinity, not 2 out of 2.
An average multiversal squigglean that considers the current universe to be at zero or negative squiggle quality will make the low quality squiggles in order to reduce how much its corner of the multiverse is pulling down the average. An average multiversal squigglean that considers the current universe to be outside the domain of squiggle quality, and will remain so for the remainder of its existence may refrain from making squiggles. If there is some chance that it will become eligible for squiggle evaluation in the future though, it may be better to tile it with low-quality squiggles now in order to prevent a worse outcome of being tiled with worse-quality future squiggles.
In practice the options aren’t going to be just “make squiggles” or “not make squiggles” either. In the context of entities relevant to these sorts of discussion, other options may include “learn how to make better squiggles”.
By “squiggle maximizer” I mean exactly “maximizer of number of physical objects such that function is_squiggle returns True on CIF-file of their structure”.
We can have different objects of value. Like, you can value “probability that if object in multiverse is a squiggle, it’s high-quality”. Here yes, you shouldn’t create additional low-quality squiggles. But I don’t see anything incoherent here, it’s just different utility function?
The idea that maximally-coherent agents look like squiggle-maximizers raises the question: what would it look like for humans to become maximally coherent?
One answer, which Yudkowsky gives here, is that conscious experiences are just a “weird and more abstract and complicated pattern that matter can be squiggled into”.
But that seems to be in tension with another claim he makes, that there’s no way for one agent’s conscious experiences to become “more real” except at the expense of other conscious agents—a claim which, according to him, motivates average utilitarianism across the multiverse.
Clearly a squiggle-maximizer would not be an average squigglean. So what’s the disanalogy here? It seems like @Eliezer Yudkowsky is basically using SSA, but comparing between possible multiverses—i.e. when facing the choice between creating agent A or not, you look at the set of As in the multiverse where you decided yes, and compare it to the set of As in the multiverse where you decided no, and (if you’re deciding for the good of A) you pick whichever one gives A a better time on average.
Yudkowsky has written before (can’t find the link) that he takes this approach because alternatives would entail giving up on predictions about his future experiences—e.g. constantly predicting he’s a Boltzmann brain and will dissolve in the next second. But this argument by Wei Dai shows that agents which reason in this way can be money-pumped by creating arbitrarily short-lived copies of them. Based on this I claim that Yudkowsky’s preferences are incoherent, and that the only coherent thing to do here is to “expect to be” a given copy in proportion to the resources it will have available, as anthropic decision theory claims. (Incidentally, this also explains why we’re at the hinge of history.)
But this is just an answer, it doesn’t dissolve the problem. What could? Some wild guesses:
You are allowed to have preferences about the external world, and you are allowed to have preferences about your “thread of experience”—you’re just not allowed to have both. The incoherence comes from trying to combine the two; the coherent thing to do would be to put them into different agents, who will then end up in very different parts of the multiverse.
Another way of framing this: you are allowed to be a decision-maker, and you are allowed to be a repository of welfare, but you’re not allowed to be both (on pain of incoherence/being dutch-booked).
Something totally different: the problem here is that we don’t have intuitive experience of being agents which can copy themselves, shut down copies, re-merge, etc. If we did, then maybe SSA would seem as silly as expecting to end up in a different universe whenever we went to sleep.
Actually, maybe the operative thing we lack experience with is not just splitting into different subagents, but rather merging together afterwards. What does it feel like to have been thousands of different parallel agents, and now be a single agent with their unified experiences? What sort of identity would one construct in that situation? Maybe this is an important part of dissolving the problem.
In your comments, you focus on issues of identity—who are “you”, given the possibility of copies, inexact counterparts in other worlds, and so on. But I would have thought that the fundamental problem here is, how to make a coherent agent out of an agent with preferences that are inconsistent over time, an agent with competing desires and no definite procedure for deciding which desire has priority, and so on, i.e. problems that exist even when there is no additional problem of identity.
Why??? Being expected squiggle maximizer literally means that you implement policy that produces maximum average number of squiggles across the multiverse.
The “average” is interpreted with respect to quality. Imagine that your only option is to create low-quality squiggles, or not to do so. In isolation, you’d prefer to produce them than not to produce them. But then you find out that the rest of the multiverse is full of high-quality squiggles. Do you still produce the low-quality squiggles? A total squigglean would; an average squigglean wouldn’t.
It depends upon whether the maximizer considers its corner of the multiverse to be currently measurable by squiggle quality, or to be omitted from squiggle calculations at all. In principle these are far from the only options as utility functions can be arbitrarily complex, but exploring just two may be okay so long as we remember that we’re only talking about 2 out of infinity, not 2 out of 2.
An average multiversal squigglean that considers the current universe to be at zero or negative squiggle quality will make the low quality squiggles in order to reduce how much its corner of the multiverse is pulling down the average. An average multiversal squigglean that considers the current universe to be outside the domain of squiggle quality, and will remain so for the remainder of its existence may refrain from making squiggles. If there is some chance that it will become eligible for squiggle evaluation in the future though, it may be better to tile it with low-quality squiggles now in order to prevent a worse outcome of being tiled with worse-quality future squiggles.
In practice the options aren’t going to be just “make squiggles” or “not make squiggles” either. In the context of entities relevant to these sorts of discussion, other options may include “learn how to make better squiggles”.
By “squiggle maximizer” I mean exactly “maximizer of number of physical objects such that function is_squiggle returns True on CIF-file of their structure”.
We can have different objects of value. Like, you can value “probability that if object in multiverse is a squiggle, it’s high-quality”. Here yes, you shouldn’t create additional low-quality squiggles. But I don’t see anything incoherent here, it’s just different utility function?