This is a linkpost for https://matiroy.substack.com/p/p-zombies-waking-themselves-up
New Comment
As @William_Mayner says, what we are discussing isn't p zombies , but computational zombues, it c-zombies. P zombies are not incoherent, as @derelict5432 ssays, but inconsistent with physicalism.
You don’t have to be a substance dualist to believe a sim (something computationally or functionally isomorphic to a person) could be a zombie. It’s a common error , that because dualism is a reason to reject something as being genuinely conscious, it is the only reason—there is also an argument based on physicalism.
There are three things that can defeat the multiple realisability of consciousness:-
-
Computationalism is true, and the physical basis makes a difference to the kinds of computations that are possible.
-
Physicalism is true, but computationalism isn't. Having the right computation without the right physics -- without running on the metal --only gives a semblance of consciousness.
-
Dualism is true. Consciousness depends on something that is neither physics nor computation.
So there are two issues: what explains claims of consciousness? What explains absence of consciousness?
Computationalism is a theory of multiple realisability: the hardware on which the computation runs doesn't matter, so long as it is adequate to run the computation, so grey matter and silicon can run the same computations...and a lot of physical details are therefore irrelevant to conscious.
Computationalism, even very fine grained computationalism, isn't a direct consequence of physicalism.
Physicalism has it that an exact atom-by-atom duplicate of a person will be a person and not a zombie, because there is no nonphysical element to go missing. That's the argument against p-zombies. But if actually takes an atom-by-atom duplication to achieve human functioning, then the computational theory of mind will be false, because CTM implies that the same algorithm running on different hardware will be sufficient. Physicalism doesn't imply computationalism, and arguments against p-zombies don't imply the non existence of c-zombies -- unconscious duplicates that are identical computationally, but not physically.
So it is possible,given physicalism , for qualia to depend on the real physics , the physical level of granularity, not on the higher level of granularity that is computation.
Effects can have multiple causes. One possible cause of a claim to be conscious is actually being conscious. Another is being a functional duplicate of an entity that claims to be conscious. Another is some kind of delusion. Under normal circumstances, reports of consciousness are strong evidence of consciousness , but robotic duplicates and neuronal replacement scenarios aren't normal circumstances
A computational duplicate of a believer in consciousness and qualia -- a c-zombie -- will continue to state that it has them , whether it does or not, because its a computational duplicate , so it produces the same output in response to the same input. Likewise, a duplicate of a non believer will deny them. (This point is clearer if you think in terms of duplicates of specific individuals with consistent views, like Dennett and Chalmers, rather than a generic human ).
Do C Zombies imply Epiphenomenalism?
No, not necessarily. Functions and algorithms don't cause anything, substrates do. If a conscious state in a normal physical brain is identical to some physical state, then it shares in its causal powers. Robo Chalmers has a different substrate based on silicon , or whatever .Robo Chalmers' substrate is causally effective, but that doesn' necessarily mean Robo Chalmers has a causally effective consciousness, because it might not have (hard problem, phenomenal) consciousness at all. Or an entirely different phenomenology.
If an entirely zombie like computational duplicate is possbile, that undermine the Absent,Dancing and Fading argument If the end point, complete absence of Qualia is possible, the mid point of faded Qualia is not impossible
Is there a post or wiki page laying out the differences between P- and C-zombies in an operational sense? Not how they internally work or feel, but what would an outside observer be able to detect to distinguish a person from a C-Zombie (already established that P-Zombies are indistinguishable).
Ah! Shoot. Yeah, I didn't use the correct terminology, P-zombies =/= C-zombies! Thanks for pointing that out and for the explanation.
Do C Zombies imply Epiphenomenalism? --> I'm not sure I follow the argument for why it doesn't.
I think I was one of those people :)
I was describing some of the implications of integrated information theory (IIT) for uploaded minds (see our paper that spells out the argument).
To be clear, IIT is not compatible with true p-zombies, in the sense of the zombie being physically identical—its predictions about the consciousness of two physically identical systems are necessarily the same. The casual structure of the physical substrate is what matters for consciousness according to IIT, so physical identity implies phenomenal identity.
Rather, IIT implies the possibility of functional or computational p-zombies, i.e. a simulation that's indistinguishable from you once you abstract away the physical differences at the lower layer that's running the simulation, but which does not reproduce your qualia (the simulation would be distinguishable if you're allowed to look at the physical implementation). So IIT is compatible with digital minds because it says that consciousness is substrate-independent, but the substrate has to have the right kind of causal structure at the physical level.
Your argument is a clear articulation of why I think it's rational to upload, and would choose to do it despite being an IIT author (modulo any concerns about loss of agency, possibility of being eternally tortured, etc.).
Any nonzero chance of continuing to be conscious is preferable no chance! (And I don't think value is destroyed by the temporary p-zombie).
Not so elegantly! I'd considered the question of whether I'd upload, but only gotten as far as a general "What do I have to lose" (though there are serious practical worries about agency & control).
Pointing out the possibility of downloading again, if a theory like IIT is eventually validated, really clinches it.
By the way, this paper from Matthew Larkum's group is quite relevant in case you haven't seen it. It's a thought experiment that I think makes IIT's contention that causal structure is relevant for consciousness (including counterfactual / dispositional properties) more plausible than it may seem at first.
1I just read the paper summary by Chat; interesting yeah, thanks for sharing! I'm not confident either way on that specific question, i.e. of whether a "perfect" replay is conscious. It reminds me of the lookup table, but just looking at a specific sequence. It might be more akin to a "telescope" looking at what happened originally rather than a new experience, but I don't know. (Under current moral/philosophical uncertainty, I'd still lean on the safer side of assuming it has moral relevance of course.)
I just added a section "On believing you're not conscious"; I'd be curious to know your thoughts on it 😊
The concept of a p-zombie is incoherent as framed. In the case you're talking about, if the digitally-uploaded mind (and body too? into a virtual environment?) is not conscious, great, now we've got a great idea what plays a causal role in consciousness and it's apparently missing in the digital version and present in the real-world one. That should help us isolate it. Otherwise, this is just ungrounded biological chauvinism.
Whether or not the uploads are non-conscious, nobody can know that they're not conscious. The biological beings can't, because the uploads acts perfect as if they are conscious. The uploads can't know either, because they have no first person experience to "know" anything at all, but instead behave as if they were conscious. This hypothetical fact about the world does not present itself to anyone inside that world.
So I think "now we've got a great idea what plays a causal role in consciousness" is false, and nothing helps the inhabitants of this hypothetical world isolate anything about it.
I was responding directly to this:
Some people were arguing that uploaded minds (or any digital minds) wouldn’t be conscious, but rather philosophical zombies—that is a mind that acts exactly as if it was conscious without actually being conscious.
How are these people who think this assessing whether or not the digital minds are conscious or not? That was my point. If they have a very strong argument (which wasn't presented) or evidence that digital minds are not conscious, out of that comes the delta, right? If there is no delta, we have as much reason and evidence for the digital mind being conscious as we do for the biological one.
I'm confused about C-Zombies. Is there or is there not something externally detectable about the condition?
For P-Zombies, there's no test for qualia, so they're truly indistinguishable from qualiawhavers. This includes indistinguishable. behavior and indistinguishable substrate (we can tell differences, but we have no clue if they affect qualia).
For C-Zombies, how is this different? They're behaviorally the same as people - they'll claim to have consciousness and experience qualia (or otherwise act in ways that make you suspect it). They're measurably different in substrate, but are you saying there's some objective test we can apply to determine consciousness?
This makes me think: To believe that an upload is a p-zombie is to believe that I'd you were uploaded and conscious, then you would still think that you're not conscious. Otherwise that would be claiming that observing your consciousness as an upload would change your behavior which is against the premise. That feels quite strange to imagine ^^
Yes, exactly as the conscious human would, if presented with the same (though faked) evidence that they are actually an upload.
It seems to me unlikely that there many, or perhaps even any, humans that would accept that they are an upload and subsequently behave as if they believe that they are actually unconscious. I wouldn't completely rule out the possibility though, as there are real humans who do behave in extremely strange ways.
So yes, an upload with such a belief would (regardless of whether or not they are actually conscious) either discard the belief, or behave very strangely by normal human norms.
I haven't had many conversations with proponents of p-zombiehood. Personally, I don't see how it works in a physicalist universe.
For this part of the model, you'd have to define where desire/goals come from - if it's from the consciousness, then p-zombies don't have it and don't care if they download to become "real".
I don't see how it works in a physicalist universe.
yep, same
if it's from the consciousness, then p-zombies don't have it and don't care if they download to become "real".
well, by definition p-zombies act the same way as their conscious counterpart; which maybe (probably) is impossible, but is a different claim from yours which seems to be "non-conscious entities can't care (/behave as if they cared) about becoming conscious"
Here's the contradiction - p-zombies will claim to be conscious. If uploads aren't actually conscious, they won't show it in their behavior it, so they won't seek it.
there are people who don't believe uploads are conscious, and also don't believe being conscious (or not conscious) causes someone to talk (or not talk) about consciousness. if they think Logical Argument X proves uploads are not conscious then an upload of them would also believe that argument, at least according to people holding that view (otherwise they would have to concede that an upload's observation of their own consciousness changes their actions)
in other words, a p-zombie can observe being an upload even though they can't observe whether or not they're conscious (according to people who believe in p-zombies in that way)
I can't pass an ITT for such people, but I'd expect that if uploaded, they'd claim to still have consciousnessness. Their current stated beliefs are about others, not themselves. I have yet to encounter anyone who claims to have experienced p-zombiehood (and indeed, the theory would make it nonsensical to do so).
My body has apparently gone through something similar to p-zombiehood at least once.
I don't recall any experience of the time interval (some minutes I heard), but I was reported to have been awake and alert and conversing and able to do mental arithmetic. Then I lay down and some minutes later sat up again, from which point I do recall experiencing normally but with no memory of any of the prior activity.
Alternatively I just had some memory loss that has never been recovered but with no other identifiable long-term effects. I was recently out of anesthetic at the time, so both explanations seem reasonably viable.
Remnant effects from the anesthetic could have impaired medium-term (order of minutes) and long-term memory formation without impairing short-term memory (enough to allow me to reply to speech etc). Or equally well could have impaired whatever underlies consciousness or its connection with the body, and there was no actual experience to remember.
Yeah, you might very well be right that they would change their mind. But presumably someone with that position would claim that they wouldn't change their mind.
Right - so are we discussing what a (presumably) conscious human predicts about their upload experience, or are we predicting what they'd do/say if uploaded? I think they're two different questions, and honestly have very low confidence that either one is very useful to any decisions or actions today.
That conditions on prior beliefs about whether uploads are conscious and whether consciousness is what causes you to talk about being conscious, not on whether the uploads are conscious.
i basically agree. i think uploads are conscious, so i think the belief that uploads are not conscious has to be caused by something else than "uploads not being conscious"
Yes, I was going to comment in the same way. From the original post:
In the future, if you realized that uploads were not conscious, you might want to change their substrate in order to make them conscious again. Let’s assume you were cryopreserved, and then were uploaded as your revival method.
How would you "realize" such a thing? There is no evidence that you could find that would distinguish between being in a world in which such high-fidelity uploads were conscious and those in which they were not. Did you mean "realize" by some non-rational means, such as religious revelation or something?
Even in that case, I expect that your upload would behave as if it had either received irrefutable evidence that it was actually conscious after all, or that it actually is not an upload and someone is trying to fool it into thinking that it is an upload. If the biological human would have protested that of course I'm conscious, then so would the upload.
If it can be presented with something that does makes it behave as if it is convinced that it is an upload, without losing conviction that uploads are unconscious, then the same would happen for the biological human if you were able to somehow give them the same evidence (e.g. by means of direct sensory nerve control). That's inherent in it being a perfect behavioural replica.
So you would also have to conclude that a corresponding conscious biological human could likewise be convinced that it is not actually conscious and have them want to download into a biological body. Which is not out of the realm of possibility, but it hardly seems like a universal or even likely sort of thing.
it's not their observation of their consciousness or lack thereof that changes their mind because p-zombies act the same as if they were not conscious
the difference is that when they look at their brain they see it is made of different material than the non-uploads and think that material doesn't support consciousness (just like their non-uploads counterpart also believe)
This weekend I attended the Machine Consciousness Conference, “MC0001”.
C-Zombies definition. Some people were arguing that uploaded minds (or any digital minds) wouldn’t be conscious. That instead, they would be “C-Zombies”—that is a mind that acts exactly as if it was conscious (/as its biological conscious counterpart) without actually being conscious (ie. they compute the sensory input in the same way, and therefore produce the same behavior given the same input). I personally believe uploads are (quite likely) conscious, but let’s assume they are C-Zombies.
Addendum: Here’s the refutation for P-Zombies: https://www.lesswrong.com/s/FqgKAHZAiZn9JAjDo. Probably a better use of your time to read why P-Zombies don’t make sense rather than this post arguing about the implications if they did 😄
C-Zombies downloading themselves. In the future, if you realized that uploads were not conscious, you might want to change their substrate in order to make them conscious again. Let’s assume you were cryopreserved, and then were uploaded as your revival method. Your p-zombie would act the same way as you would, by definition, and so would also be wanting to download p-zombies / make them conscious again. Therefore your p-zombie would presumably decide to download itself back into a substrate that supports consciousness. Problem solved.
(Unless you think most of the value was already destroyed by having a temporary p-zombie between the 2 conscious states.)
Addendum
Clarification on C-Zombies observing their brain: C-Zombies act exactly the same as their biological counterpart given the same environment. However, there’s one part of their environment that has to be different, which is their own brain. So if they “open their brain” to look inside of it, then they will observe something different. However, the biological brain was in a vat, connected to the same virtual reality as the C-Zombie, and in the virtual reality you showed to both that they were biological brains, or showed to both that they were digital brains (even though that’s a deception for one of them), then in that scenario both would be acting in the same way. So it’s not quite their brain that changes how they behave, but rather the observation of their brain.
On believing you’re not conscious: (As far as I understand) According to C-Zombie believers (which I’m not), what causes them to believe they are conscious is not the introspection that they’re conscious, but rather the observation of how their brain is embeded in physics. Consequently,
Corrected error 6/2: I originally used the concept of P-Zombies instead of C-Zombies as I should have. See this comment for an explanation of the difference.