Signer

Posts

Sorted by New

Wiki Contributions

Comments

The problem is that there is more than one (“I remain myself after sleep”) statement and if you consider all of them together, there is no longer another way.

Well, yes, there are other statements - “I am my body” and “I remain myself after sleep” are among them. If your way allows contradicting “I am my body” then it's not the only contradiction-free way, and other ways (that contradict other initial statements) are on the same footing. At least as far as logic goes.

The contradiction is in your brain in the form of the data encoded there. It’s not an incorrect belief about where atoms are.

Then patternist identity encodes contradiction to “I am my body” in the same way. And if your choice of statements to contradict is not determined by either logic or beliefs about atoms, then it is determined by your preferences. There is just not much other kinds of stuff in the universe.

That would require some extremely convoluted theory of consciousness that nobody could believe.

So like I said, requirement for a theory of consciousness to not be convoluted is just your preference. Just like any definition of what it means for someone to actually believe something - it's not logic that forces you, because as long as you have a contradiction anyway, you can say that someone was wrong about themselves not believing in convoluted theory of consciousness - and not knowledge about reality. That's why it's about ethics. Or why do you thing someone should prefer non-convoluted theory of consciousness?

For example, it would contradict one of the things you said previously, where a consciousness belongs to a macroscopic, spatially extended object (like a human body), and that’s what makes the object experience that consciousness.

Nah, you can just always make it more convoluted^^. For example I could say that usually microscopic changes are safe, but changing neurons into silicon is too much and destroys consciousness.

By a logical error, I had in mind committing a contradiction, an invalid implication, etc.

Implication from what? There is no chain of implications that starts with "I think I value me" and "everything is atoms" and ends with “transplanting a brain to another body preserves me”. Unless you already have laws for how you reduce things.

In other words, if you consider the explicit properties you believe the concept of yourself to have, and then you compare them against other beliefs you already hold, you’ll discover a contradiction which can be only remedied by accepting the reduction of “you” into a substanceless pattern. There is no other way.

Your beliefs and explicit properties are in different ontologies - there is no law for comparing them. If your current reduction of yourself contradicts your beliefs, you can change your reduction. Yes, a substanceless pattern is a valid change of reduction. But a vast space of other reductions is also contradiction-free (physically possible, in other words) - "I am my body" doesn't require atoms to be in wrong places. You didn't present an example of where it does, so you agree, right?

If by "beliefs" you mean high-level approximations, like in addition to "I am my body", you have "I remain myself after sleep" and then you figure out atoms and start to use "the body after sleep is not really the same", then obviously there are many other ways to resolve this instead of "I am substanceless pattern". There is nothing preventing you from saying that "body" should mean different things in "I am my body" and "the body after sleep", you can conclude that you are not you after sleep - why is one explicit property is better than another if excluding either solves the contradiction? Like I said, is it about consciousness specifically, where you think people can't be wrong about what way point to when they think about blacking out? Because it's totally possible to be wrong about your consciousness.

Then there would be subsequent steps

"To be sure, Fading Qualia may be logically possible. Arguably, there is no contradiction in the notion of a system that is so wrong about its experiences." So, by "correct" you mean "doesn't feel implausible"? Or what else makes imagining slowly replacing your neurons "correct"?

I mean, where did you even got the idea that it is possible to derive anything ethical using only correctness? That's is/ought distinction, isn't it?

Wait, "logical" error? Like, you believe that "transplanting a brain to another body preserves you" is a theorem of QFT + ZFC or something? That... doesn't make sense - there is no symbol for "brain" in QFT + ZFC.

No, it’s not, you just think it is. If you could reflect on all your beliefs, you’d come to the conclusion you were wrong.

How does it make that conclusion correct?

If you mean not talking about them in the sense of not referring to them, I’d want to know how they reduced consciousness (or their personal survival) if they couldn’t refer to those concepts in the first place.

I mean after they stopped believing in (and valuing) soul they switched to valuing physically correct description of their body without thinking whether it was correct reduction of a soul. And not being a computer they are not perfectly correct in their description, but the point is why not help them correct their description and make them more like a computer valuing the body? Where is mistake in that?

Or even, can you give an example of just one correct step in the reasoning about what are the real properties of a concept (of a chair or consciousness or whatever)?

"Different bodies have different consciousness" is an implicit property of the concept. The whole problem of changing ontology is that you can't keep all the properties. And there is nothing except your current preferences that can decide which ones you keep.

They didn’t start talking about chairs (instead of consciousness) because they care about chairs.

In what parts (the reduction of) your concept of being mistaken is not isomorphic to caring? Or, if someone just didn't talk about high-level concepts at all, what are your explicit and implicit properties of correctness that are not satisfied by knowing where all the atoms are and still valuing your body?

While all definitions are arbitrary, the ontology of any given existing thing (like consciousness) is objective.

How does this work? There is only one objective ontology - true physics. That we don't know it complicates things somewhat, but on our current understanding (ethically significant) consciousness is not an ontological primitive. Everything is just quantum amplitude. Nothing really changes whether you call some part of universe "consciousness" or "chair" or whatever. Your reduction can't say things that contradict real ontology, of course - you can't say "chair is literally these atoms and also it teleports faster than light". But there is nothing that contradict real ontology in "I am my body".

No, concepts are value-neutral. Caring about a concept is distinct from whether a given reduction of a concept is correct, incorrect or arbitrary.

There is no objective justification for a concept of a chair. AIXI doesn't need to think about chairs. Like, really, try to specify correctness of a reduction of chair without appeal to usefulness.

we’ll end up mistakenly believing incorrect things about reality

Wait, but we already assumed that we are using "I am my body" definition that is correct about reality. Well, I assumed. Being incorrect means there must be some atoms in your model that are not in there real place. But "I am my body" doesn't mean you forget that there will be another body with the same pattern at the destination of a teleporter. Or any other physical consequence. You still haven't specified what incorrect things about atoms "I am my body" entails.

Is it about you thinking that consciousness specifically is ontologically primitive or that "blacking out" can't be reduced to whatever you want or something and you would agree if we only talked about chairs? Otherwise I really want to see your specification of what does "correct reduction" means.

I pretty much agree with your restatement of my position, but you didn't present arguments for yours. Yes, I'm saying that all high-level concepts are value-laden. You didn't specify what do you mean by "correct", but for "corresponds to reality" it just doesn't make sense for the definition of death to be incorrect. What do you even mean that it is incorrect, when it describes the same reality?

That’s potentially a good objection, but a high-level concept already has a set of properties, explanatorily prior to it being reduced.

Yeah, they are called "preferences" and the problem is that they are in different language.

I mean, it's not exactly inconsistent to have a system of preferences about how you resolve ontological shifts and to call that subset of preferences "correct" and nothing is really low-level anyway, but... you do realize that mistakes in reduction are not the same things as mistakes about reality?

This isn’t purely a matter of who wins in a philosophy paper.

So is killing someone by separating them from their bus.

The laws declared among other Stepan Bandera, the Organisation of Ukrainian Nationalists, and the Ukrainian Insurgent Army to be national heroes who aren’t allowed to be insulted.

Was skeptical about "aren’t allowed to be insulted" part, so here is the law if someone also wants to check.

Otherwise, you could survive your death by defining yourself to be a black hole (those are extremely long-lived).

That's the point? There are no physical laws that force you to care about your pattern instead of caring about black hole. And there are no laws that force you to define death one way or another. And no unique value-free way to infer low-level description from high-level concept - that's ontological shift problem. You can't "know", that death means your pattern is not instantiated anywhere, ones you know about atoms or whatever. You can only know that there are atoms and that you can model yourself as using "death" concept in some situations. You still need to define death afterwards. You can motivate high-level concepts by epistemic values - "modeling these atoms as a chair allows me to cheaply predict it". But there is no fundamental reason why your epistemic values must dictate what high-level concepts you use for your other values.

If your consciousness survives but you don’t black out forever, that would be a contradiction

It's only contradiction if you define "you blacking out" as your destruction of consciousness. Like I said, it's begging the question. Nothing is forcing you to equate ethically significant blacking out with "there are no instantiations of your pattern" instead of "current instantiation is destroyed.

That it’s a mental illness, I suppose.

So it is a matter of semantics.

it would mean, for example, that if someone shoots you in the head, it’s just a matter of semantics whether you black out forever or not

Yes, it is just a matter of semantics, unless you already specified what "you black out forever" means in low-level terms. There are no additional facts about reality that force you to describe your head in a shot state as blacking out forever or even talk about "you" at all.

Since you actually black out forever iff your consciousness is destroyed

And that's an inference from what law? Defining "destroyed" as "there are no other instantiations of a pattern of your consciousness" is just begging the question.

Saying that you will black out forever after the teleportation is as much of a decent approximation of the truth as saying that you will black out forever after going to sleep

I mean, there are detectable physical differences, but sure, what's your objection to "sleep is death" preference?

There is only one universe. Everything else, including singling out consciousness, is already definitional (and I don't see how physical locality, for example, is more definitional than "not blacking out forever"). Thinking overwise is either smuggling epistemic methods to ethics ("but it's simpler if we model you and house as separate entities!" or something) which is unjustified personal meta-preference and certainly bad without explicitly marking it as such. Or just plain forgetting about subjectivity of high-level concepts such as consciousness. Calling something "consciousness" also doesn't change underling reality of your brain continuing to exist after a car accident.

What they believe is that they actually black out forever, like after a car accident, and a copy of them who falsely feels like them will actually take their place.

In the case of teleportation, for example, how "this body will no longer instantiate my pattern of consciousness" is not correct description of reality and how "I will black out forever" is not a decent approximation of it? There will be instantiation of blacking out forever - decision to model it as continuing somewhere else is, like you say, definitional.

If I told you one day that I terminally cared about never leaving my house because I defined myself as my body + my house, and if my body leaves my house, I cease to exist, would you think that I’m holding a terminal belief, or would you consider some deep confusion, possibly caused by schizophrenia?

Wait, why do you think schizophrenia doesn't change terminal values? I would hope it's just confusion, but if t's your values then it's your values.

I don’t admire the self-determination of people who choose to define themselves as their body—instead, I can see they’re making an error of judgment as to what actually destroys/doesn’t destroy their consciousness

You didn't demonstrate what fact about reality in low-level terms they get wrong.

Load More