Researcher at the Center on Long-Term Risk. All opinions my own.
Anthony DiGiovanni
Karma: 986
does that require you to either have the ability to commit to a plan or the inclination to consistently pick your plan from some prior epistemic perspective
You aren’t required to take an action (/start acting on a plan) that is worse from your current perspective than some alternative. Let maximality-dominated mean “w.r.t. each distribution in my representor, worse in expectation than some alternative.” (As opposed to “dominated” in the sense of “worse than an alternative with certainty”.) Then, in general you would need[1] to ask, “Among the actions/plans that are not maximality-dominated from my current perspective, which of these are dominated from my prior perspective?” And rule those out.
- ^
If you care about diachronic norms of rationality, that is.
- ^
mostly problems with logical omnisicence not being satisfied
I’m not sure, given the “Indeterminate priors” section. But assuming that’s true, what implication are you drawing from that? (The indeterminacy for us doesn’t go away just because we think logically omniscient agents wouldn’t have this indeterminacy.)
the arbitrariness of the prior is just a fact of life
The arbitrariness of a precise prior is a fact of life. This doesn’t imply we shouldn’t reduce this arbitrariness by having indeterminate priors.
The obvious answer is only when there is enough indeterminacy to matter; I’m not sure if anyone would disagree. Because the question isn’t whether there is indeterminacy, it’s how much, and whether it’s worth the costs of using a more complex model instead of doing it the Bayesian way.
Based on this I think you probably mean something different by “indeterminacy” than I do (and I’m not sure what you mean). Many people in this community explicitly disagree with the claim that our beliefs should be indeterminate at all, as exemplified by the objections I respond to in the post.
When you say “whether it’s worth the costs of using a more complex model instead of doing it the Bayesian way”, I don’t know what “costs” you mean, or what non-question-begging standard you’re using to judge whether “doing it the Bayesian way” would be better. As I write in the “Background” section: “And it’s question-begging to claim that certain beliefs “outperform” others, if we define performance as leading to behavior that maximizes expected utility under those beliefs. For example, it’s often claimed that we make “better decisions” with determinate beliefs. But on any way of making this claim precise (in context) that I’m aware of, “better decisions” presupposes determinate beliefs!”
You also didn’t quite endorse suspending judgement in that case—“If someone forced you to give a best guess one way or the other, you suppose you’d say “decrease”.
The quoted sentence is consistent with endorsing suspending judgment, epistemically speaking. As the key takeaways list says, “If you’d prefer to go with a given estimate as your “best guess” when forced to give a determinate answer, that doesn’t imply this estimate should be your actual belief.”
But if it is decision relevant, and there is only a binary choice available, your best guess matters
I address this in the “Practical hallmarks” section — what part of my argument there do you disagree with?
You seem to be underestimating how pervasive / universal this critique is—essentially every environment is more complex than we are
I agree it’s pretty pervasive, but the impression I’ve gotten from my (admittedly limited) sense of how infra-Bayesianism works is:
The “more complex than we are” condition for indeterminacy doesn’t tell us much about when, if ever, our credences ought to capture indeterminacy in how we weigh up considerations/evidence — which is a problem for us independent of non-realizability. For example, I’d be surprised if many/most infra-Bayesians would endorse suspending judgment in the motivating example in this post, if they haven’t yet considered the kinds of arguments I survey. This matters for how decision-relevant indeterminacy is for altruistic prioritization.
I’m also not aware of the infra-Bayesian literature addressing the “practical hallmarks” I discuss, though I might have missed something.
(The Solomonoff induction part is a bit above my pay grade, will think more about it.)
Just a pointer, I’d strongly recommend basically anything by Alan Hajek about this topic. “The reference class problem is your problem too” is a highlight. I find him to be an exceptionally clear thinker on philosophy of probability, and expect discussions about probability and beliefs would be less confused if more people read his work.
(1) isn’t a belief (unless accompanied by (2))
Why not? Call it what you like, but it has all the properties relevant to your argument, because your concern was that the person would “act in all ways as if they’re in pain” but not actually be in pain. (Seems like you’d be begging the question in favor of functionalism if you claimed that the first-person recognition ((2)-belief) necessarily occurs whenever there’s something playing the functional role of a (1)-belief.)
That’s not possible, because the belief_2 that one isn’t in pain has nowhere to be instantiated.
I’m saying that no belief_2 exists in this scenario (where there is no pain) at all. Not that the person has a belief_2 that they aren’t in pain.
Even if the intermediate stages believed_2 they’re not in pain and only spoke and acted that way (which isn’t possible), it would introduce a desynchronization between the consciousness on one side, and the behavior and cognitive processes on the other.
I don’t find this compelling, because denying epiphenomenalism doesn’t require us to think that changing the first-person aspect of X always changes the third-person aspect of some Y that X causally influences. Only that this sometimes can happen. If we artificially intervene on the person’s brain so as to replace X with something else designed to have the same third-person effects on Y as the original, it doesn’t follow that the new X has the same first-person aspect! The whole reason why given our actual brains our beliefs reliably track our subjective experiences is, the subjective experience is naturally coupled with some third-person aspect that tends to cause such beliefs. This no longer holds when we artificially intervene on the system as hypothesized.
There is no analogue of “fluid” in the brain. There is only the pattern.
We probably disagree at a more basic level then. I reject materialism. Subjective experiences are not just patterns.
I think I’m happy to say that in this example, you’re warranted in reasoning like: “I have no information about the biases of the three coins except that they’re in the range [0.2, 0.7]. The space ‘possible biases of the coin’ seems like a privileged space with respect to which I can apply the principle of indifference, so there’s a positive motivation for having a determinate probability distribution about each of the three coins centered on 0.45.”
But many epistemic situations we face in the real world, especially when reasoning about the far future, are not like that. We don’t have a clear, privileged range of numbers to which we can apply the principle of indifference. Rather we have lots of vague guesses about a complicated web of things, and our reasons for thinking a given action could be good for the far future are qualitatively different from (hence not symmetric with) our reasons for thinking it could be bad. (Getting into the details of the case for this is better left for top-level posts I’m working on, but that’s the prima facie idea.)
I’d think this isn’t a very good forecast since the forecaster should either have combined all their analysis into a single probability (say 30%) or else given the conditions under which they give their low end (say 10%) or high end (say 40%) and then if I didn’t have any opinions on the probability of those conditions then I would weigh the low and high equally (and get 25%).
This sounds like a critique of imprecise credences themselves, not maximality as a decision rule. Do you think that, even if the credences you actually endorse are imprecise, maximality is objectionable?
Anyway, to respond to the critique itself:
The motivation for having an imprecise credence of [10%, 40%] in this case is that you might think a) there are some reasons to favor numbers closer to 40%; b) there are some reasons to favor numbers closer to 10%; and c) you don’t think these reasons have exactly equal weight, nor do you think the reasons in (a) have determinately more or less weight than those in (b). Given (c), it’s not clear what the motivation is for aggregating these numbers into 25% using equal weights.
I’m not sure why exactly you think the forecaster “should” have combined their forecast into a single probability. In what sense are we losing information by not doing this? (Prima facie, it seems like the opposite: By compressing our representation of our information into one number, we’re losing the information “the balance of reasons in (a) and (b) seems indeterminate”.)
In response to the two reactions:
Why do you say, “Besides, most people actually take the opposite approch: computation is the most “real” thing out there, and the universe—and any consciouses therein—arise from it.”
Euan McLean said at the top of his post he was assuming a materialist perspective. If you believe there exists “a map between the third-person properties of a physical system and whether or not it has phenomenal consciousness” you believe you can define consciousness with a computation. In fact, anytime you believe something can be explicitly defined and manipulated, you’ve invented a logic and computer. So, most people who take the materialist perspective believe the material world comes from a sort of “computational universe”, e.g. Tegmark IV.
I’m happy to grant that last sentence for the sake of argument, but note that you originally just said “most people,” full stop, without the massively important qualifier “who take the materialist perspective.”
The non-functionalist audience is also not obliged to trust the introspective reports at intermediate stages.
This introduces a bizarre disconnect between your beliefs about your qualia, and the qualia themselves. Imagine: It would be possible, for example, that you believe you’re in pain, and act in all ways as if you’re in pain, but actually, you’re not in pain.
I think “belief” is overloaded here. We could distinguish two kinds of “believing you’re in pain” in this context:
Patterns in some algorithm (resulting from some noxious stimulus) that, combined with other dispositions, lead to the agent’s behavior, including uttering “I’m in pain.”
A first-person response of recognition of the subjective experience of pain.
I’d agree it’s totally bizarre (if not incoherent) for someone to (2)-believe they’re in pain yet be mistaken about that. But in order to resist the fading qualia argument along the quoted lines, I think we only need someone to (1)-believe they’re in pain yet be mistaken. Which doesn’t seem bizarre to me.
(And no, you don’t need to be an epiphenomenalist to buy this, I think. Quoting Block: “Consider two computationally identical computers, one that works via electronic mechanisms, the other that works via hydraulic mechanisms. (Suppose that the fluid in one does the same job that the electricity does in the other.) We are not entitled to infer from the causal efficacy of the fluid in the hydraulic machine that the electrical machine also has fluid. One could not conclude that the presence or absence of the fluid makes no difference, just because there is a functional equivalent that has no fluid.”)
the copies would not only have the same algorithm, but also the same physical structure arbitrarily finely
I understand, I’m just rejecting the premise that “same physical structure” implies identity to me. (Perhaps confusingly, despite the fact that I’m defending the “physicalist ontology” in the context of this thread (in contrast to algorithmic ontology), I reject physicalism in the metaphysics sense.)
This also seems tangential, though, because the substantive appeals to the algorithmic ontology that get made in the decision theory context aren’t about physically instantiated copies. They’re about non-physically-instantiated copies of your algorithm. I unfortunately don’t know of a reference for this off the top of my head, but it has come up in some personal communications FWIW.
you’d eventually meet copies of yourself
But a copy of me =/= me. I don’t see how you establish this equivalence without assuming the algorithmic ontology in the first place.
it’s not an independent or random sample
What kind of sample do you think it is?
Sure, but isn’t the whole source of weirdness the fact that it’s metaphysically unclear (or indeterminate) what the real “sampling procedure” is?
I don’t understand. It seems that when people appeal to the algorithmic ontology to motivate interesting decision-theoretic claims — like, say, “you should choose to one-box in Transparent Newcomb” — they’re not just taking a more general perspective. They’re making a substantive claim that it’s sensible to regard yourself as an algorithm, over and above your particular instantiation in concrete reality.
This post was a blog post day project. For its purpose of general sanity waterline-raising, I’m happy with how it turned out. If I still prioritized the kinds of topics this post is about, I’d say more about things like:
“equilibrium” and how it’s a misleading and ill-motivated frame for game theory, especially acausal trade;
why the logical/algorithmic ontology for decision theory is far from obviously preferable.
But I’ve come to think there are far deeper and higher-priority mistakes in the “orthodox rationalist worldview” (scare quotes because I know individuals’ views are less monolithic than that, of course). Mostly concerning pragmatism about epistemology and uncritical acceptance of precise Bayesianism. I wrote a bit about the problems with pragmatism here, and critiques of precise Bayesianism are forthcoming, though previewed a bit here.
Linkpost: Why Evidential Cooperation in Large Worlds might not be action-guiding
A while back I wrote up why I was skeptical of ECL. I think this basically holds up, with the disclaimers at the top of the post. But I don’t consider it that important compared to other things relevant to LW that people could be thinking about, so I decided to put it on my blog instead.
(I might misunderstand you. My impression was that you’re saying it’s valid to extrapolate from “model XYZ does well at RE-Bench” to “model XYZ does well at developing new paradigms and concepts.” But maybe you’re saying that the trend of LLM success at various things suggests we don’t need new paradigms and concepts to get AGI in the first place? My reply below assumes the former:)
I’m not saying LLMs can’t develop new paradigms and concepts, though. The original claim you were responding to was that success at RE-Bench in particular doesn’t tell us much about success at developing new paradigms and concepts. “LLMs have done various things some people didn’t expect them to be able to do” doesn’t strike me as much of an argument against that.
More broadly, re: your burden of proof claim, I don’t buy that “LLMs have done various things some people didn’t expect them to be able to do” determinately pins down an extrapolation to “the current paradigm(s) will suffice for AGI, within 2-3 years.” That’s not a privileged reference class forecast, it’s a fairly specific prediction.
I don’t think this distinction between old-paradigm/old-concepts and new-paradigm/new-concepts is going to hold up very well to philosophical inspection or continued ML progress; it smells similar to ye olde “do LLMs truly understand, or are they merely stochastic parrots?” and “Can they extrapolate, or do they merely interpolate?”
I find this kind of pattern-match pretty unconvincing without more object-level explanation. Why exactly do you think this distinction isn’t important? (I’m also not sure “Can they extrapolate, or do they merely interpolate?” qualifies as “ye olde,” still seems like a good question to me at least w.r.t. sufficiently out-of-distribution extrapolation.)
That’s right.
(Not sure you’re claiming otherwise, but FWIW, I think this is fine — it’s true that there’s some computational cost to this step, but in this context we’re talking about the normative standard rather than what’s most pragmatic for bounded agents. And once we start talking about pragmatic challenges for bounded agents, I’d be pretty dubious that, e.g., “pick a very coarse-grained ‘best guess’ prior and very coarse-grained way of approximating Bayesian updating, and try to optimize given that” would be best according to the kinds of normative standards that favor indeterminate beliefs.)