I understand that, but I’m still asking why subliminal stimuli are not morally relevant for you? They may still create disposition to act in aversive way, so there is still mechanism in some part the brain/neural network that causes this behaviour and has access to the stimulus—what’s the morally significant difference between a stimulus being in some neurons and being in others, such that you call only one location “awareness”?
Signer
Why does it matter that Gilbert infers something from the behavior of his neural network and not from the behavior of his body? Both are just subjective models of reality. Why does it matter whether he knows something about his pain? Why it doesn’t count, if Gilbert avoids pain defined as the state of neural network that causes him to avoid it, even when he doesn’t know something about it? Maybe you can model it as Gilbert himself not feeling pain, but why the neural network is not a moral patient?
The reference classes you should use work as a heuristic because there is some underlying mechanism that makes them work. So you should use reference classes in situations where their underlying mechanism is expected to work.
Maybe the underlying mechanism of doomsday predictions not working is that people predicting doom don’t make their predictions based on valid reasoning. So if someone uses that reference class to doubt AI risk, this should be judged as them making a claim about reasoning of people predicting AI doom being similar to people in cults predicting Armageddon.
The fact that these physicalists feel it would be in some way necessary to instantiate colour, but not other things, like photosynthesis or fusion, means they subscribe to the idea that there is something epistemically unique about qualia/experience, even if they resist the idea that qualia are metaphysically unique.
No, it means they subscribe to the idea that there is something ethically different about qualia/experience. It’s not unique, it’s like riding a bike. Human sometimes call physical interactions, utility of which is not obtainable by just thinking, “knowledge”, when these interactions are with human body. And “they feel” is not an argument about knowledge, it’s an argument about feelings. The difference between instantiating fusion in brain or red is not epistemical, it’s ethical—qualia are useful for humans, so they don’t properly transfer intuitions into Mary’s case, and even if they do, humans care more about their brain instantiating red, than their brain fusing. Fundamentally, they all can be viewed as different representations of knowledge. It’s just some representations are valuable by themselves.
What? Are you saying that if it is necessary for something for her than completer knowledge, it isn’t necessary for complete knowledge?
I’m saying that if differences in feelings of necessity are explainable by preferences, then what need there is to introduce problematic definitions of knowledge?
The intended point is that she gains knowledge from personal experience that isn’t predictable from a perfect understanding of physics. I don’t know what you mean by “physicalism predicts gaining knowledge”. Physicalism doesn’t predict that you should gain additional knowledge by instantiating a state yourself , because physicalism is the idea that all facts are physical facts, which implies all facts are objective facts, which implies personal instantiation can’t add anything (so king sc you, like Mary, dint have any resource limitationd)
Yes, and the consequence of this point is that you shouldn’t use such definition of knowledge, because it implies that knowing how to ride a bike is unphysical.
Physicalism in a strict sense means that objective knowledge is the only knowledge.
I don’t see how there can be any objective knowledge—encodings are subjective. By the way, why is ok for Physicalism to mean different things in context of different arguments? Physicalism in the Hard Problem doesn’t mean that knowing how to ride a bike is unphysical.
But if you insist on defining Physicalism in such a way, then yes, Mary doesn’t gain additional knowledge. Which proves that such definition contradicts some people’s intuition about experience and bikes. It doesn’t prove anything about real epistemology without additional assumptions.
Mary’s Room, AKA the Knowledge Argument is about knowledge. It’s epistemological. No explicit claims about ontology are made. No nonphysical ontology is implied by talking about qualia, either, for the usual reason that qualia aren’t defined as nonphysical.
I’m saying it doesn’t work as argument without ontological assumptions.
Without predicting what they are.
No qualia are predicted by phytsicalism.
That’s not a fact. Physicalism doesn’t predict that anything feels like anything.
You can’t conclude this without additional assumptions from Mary alone! I’m not arguing “physicalism is true” here, only that Mary is useless in disproving it. The only thing you can get from Mary, is that there is prediction-instantiation gap with experiences. But it’s the same gap as between knowing about a state and being in a state, like with knowing how to ride a bike.
One of such possible assumptions is that there is some difference between relations of knowledge and state in cases of experience and bikes. That in some sense knowledge without acquaintance about bikes is still about bikes, but knowledge about experience is not actually about experience. That knowledge without acquaintance about experience is incomplete in some additional way, not related to the ordinary difference between knowing and being. But it is an additional assumption, not something you can derive from Mary’s Room, because, again, Mary gaining something after leaving the room is predicted both in case of experience and in case of bikes.
Atoms undergoing exothermic reactions involving oxygen is exactly what is fire. If you use a sufficiently detailed reductive explanation,nl it does lead to identity. Heat is disorganised molecular activity.
I don’t see how you can get identity if you can just can have an ontology that doesn’t contain fire, only atoms. You can get some atoms to be numerically close to a reencoding of atoms of your brain that perceives fire. Or numerically close to some other previous model of fire. You can then check some limits for divergence and declare that atomic model matches empirical results precise-enough. But no one expects previous model to be precisely equivalent to new one? And reasoning about different specific fires definitely involves probabilistic induction.
Conversely, if by “necessary” you just mean ordinary way science does reductions, then Mary’s situation with experience fully qualifies: she correctly concludes that red qualia are activity of neurons, have as complete knowledge about bats on LSD as of bikes and fires, can say that the red of roses will feel similar to the red of blood, can predict her entire field of view with pixels marked “red” with more precision, than she will be able to track in the moment, and will get new experience after leaving the room as predicted. No part of it contradicts qualia being reducible to physics. You can only argue it by bringing zombies. Or show on which step Mary fails to reduce red qualia, that doesn’t work the same way with bikes or fires.
I guess the more substantial disagreement may be in the part, where a description of a bat-on-LSD experience in the language of physics or neural activity is somehow doesn’t count, as opposed to… I’m not sure what people expect, a description in the terms usually used to describe human experience starting with “it feels like...”? But that’s just the question of precision—why should describing nuclear reactor in terms of fire would be required to claim success in reduction? There is of course the difference between you knowing about bats-on-LSD and you having such experience—but that is also true about riding a bike or any other physical state.
It all looks to me like people are confusing knowing about qualia and being in a state of having qualia—that’s why they assume perfect certain knowledge of qualia they have, talk about qualia being impossible to communicate and so on.
?? She isn’t defined as knowing everything plausible, she is defined as knowing everything physical/objective.
Sorry, typo—“plausibly includes”.
Endurist thinking treats reproduction as always acceptable or even virtuous, regardless of circumstances. The potential for suffering rarely factors into this calculation—new life is seen as inherently good.
Not necessary—you can treat creating new people differently from already existing and avoid creating bad (in Endurist sense—not enough positive experiences, regardless of suffering) lives without accepting death for existing people. I, for example, don’t get why would you bring more death to the world by creating low-lifespan people, if you don’t like death.
clearly the system is a lot less contextual than base models, and it seems like you are predicting a reversal of that trend?
The trend may be bounded, the trend may not go far by the time AI can invent nanotechnology—would be great if someone actually measured such things.
And there being a trend at all is not predicted by utility-maximization frame, right?
People are confused about the basics because the basics are insufficiently justified.
It is learning helpfulness now, while the best way to hit the specified ‘helpful’ target is to do straightforward things in straightforward ways that directly get you to that target. Doing the kinds of shenanigans or other more complex strategies won’t work.
Best by what metric? And I don’t think it was shown, that complex strategies won’t work—learning to change behaviour from training to deployment is not even that complex.
But it is important, and this post just isn’t going to get done any other way.
Speaking about streetlighting...
What makes it rational is that there is an actual underlying hypothesis about how weather works, instead of vague “LLMs are a lot like human uploads”. And weather prediction outputs numbers connected to reality we actually care about. And there is no alternative credible hypothesis that implies weather prediction not working.
I don’t want to totally dismiss empirical extrapolations, but given the stakes, I would personally prefer for all sides to actually state their model of reality and how they think evidence changed it’s plausibility, as formally as possible.
There is no such disagreement, you just can’t test all inputs. And without knowledge of how internals work, you may me wrong about extrapolating alignment to future systems.
Yes, except I would object to phrasing this anthropic stuff as “we should expect ourselves to be agents that exist in a universe that abstracts well” instead of “we should value universe that abstracts well (or other universes that contain many instances of us)”—there is no coherence theorems that force summation of your copies, right? And so it becomes apparent that we can value some other thing.
Also even if you consider some memories a part of your identity, you can value yourself slightly less after forgetting them, instead of only having threshold for death.
It doesn’t matter whether you call your multiplier “probability” or “value” if it results in your decision to not care about low-measure branch. The only difference is that probability is supposed to be about knowledge, and Wallace’s argument involving arbitrary assumption, not only physics, means it’s not probability, but value—there is no reason to value knowledge of your low-measure instances less.
this makes decision theory and probably consequentialist ethics impossible in your framework
It doesn’t? Nothing stops you from making decisions in a world where you are constantly splitting. You can try to maximize splits of good experiences or something. It just wouldn’t be the same decisions you would make without knowledge of splits, but why new physical knowledge shouldn’t change your decisions?
Things like lions, and chairs are other examples.
And counted branches.
This is how Wallace defines it (he in turn defines macroscopically indistinguishable in terms of providing the same rewards). It’s his term in the axiomatic system he uses to get decision theory to work. There’s not much to argue about here?
His definition leads to contradiction with informal intuition that motivates consideration of macroscopical indistinguishability in the first place.
We should care about low-measure instances in proportion to the measure, just as in classical decision theory we care about low-probability instances in proportion to the probability.
Why? Wallace’s argument is just “you don’t care about some irrelevant microscopic differences, so let me write this assumption that is superficially related to that preference, and here—it implies the Born rule”. Given MWI, there is nothing wrong physically or rationally in valuing your instances equally whatever their measure is. Their thoughts and experiences don’t depend on measure the same way they don’t depend on thickness or mass of a computer implementing them. You can rationally not care about irrelevant microscopic differences and still care about number of your thin instances.
How many notions of consciousness do you think are implementable by a short Python program?
Because scale doesn’t matter—it doesn’t matter if you are implemented on thick or narrow computer.
First of all, macroscopical indistinguishability is not fundamental physical property—branching indifference is additional assumption, so I don’t see how it’s not as arbitrary as branch counting.
But more importantly, branching indifference assumption is not the same as informal “not caring about macroscopically indistinguishable differences”! As Wallace showed, branching indifference implies the Born rule implies you almost shouldn’t care about you in a branch with a measure of 0.000001 even though it may involve drastic macroscopic difference for you in that branch. You being macroscopic doesn’t imply you shouldn’t care about your low-measure instances.
But why would you want to remove this arbitrariness? Your preferences are fine-grained anyway, so why retain classical counting, but deny counting in the space of wavefunction? It’s like saying “dividing world into people and their welfare is arbitrary—let’s focus on measuring mass of a space region”. The point is you can’t remove all decision-theoretic arbitrariness from MWI—“branching indifference” is just arbitrary ethical constraint that is equivalent to valuing measure for no reason, and without it fundamental physics, that works like MWI, does not prevent you from making decisions as if quantum immortality works.
“Decoherence causes the Universe to develop an emergent branching structure. The existence of this branching is a robust (albeit emergent) feature of reality; so is the mod-squared amplitude for any macroscopically described history. But there is no non-arbitrary decomposition of macroscopically-described histories into ‘finest-grained’ histories, and no non-arbitrary way of counting those histories.”
Importantly though, on this approach it is still possible to quantify the combined weight (mod-squared amplitude) of all branches that share a certain macroscopic property, e.g. by saying:
“Tomorrow, the branches in which it is sunny will have combined weight 0.7”
There is no non-arbitrary definition of “sunny”. If you are fine with approximations, then you can also decide on decomposition of wavefunction into some number of observers—it’s the same problem as decomposing classical world that allows physical splitting of thick computers according to macroscopic property “number of people”.
Even if we can’t currently prove certain axioms, doesn’t this just reflect our epistemological limitations rather than implying all axioms are equally “true”?
It doesn’t and they are fundamentally equal. The only reality is the physical one—there is no reason to complicate your ontology with platonically existing math. Math is just a collection of useful templates that may help you predict reality and that it works is always just a physical fact. Best case is that we’ll know true laws of physics and they will work like some subset of math and then axioms of physics would be actually true. You can make a guess about what axioms are compatible with true physics.
Also there is Shoenfield’s absoluteness theorem, which I don’t understand, but which maybe prevents empirical grounding of CH?
First, you can still infer meta-representation from your behavior. Second, why does it matter that you represent aversiveness, what’s the difference? Representation of aversiveness and representation of damage are both just some states of neurons that model some other neurons (representation of damage still implies possibility of modeling neurons, not only external state, because your neurons are connected to other neurons).