C-Zombie Uploads Downloading Themselves & Believing You're A C-Zombie
Uploaded minds would change their substrate (or "download themselves") to become conscious again. And a conscious upload who's a C-Zombie believer wouldn't believe they're conscious.
x-post: LessWrong
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,
Their probability that they’re conscious should be the same as the probability that they’re not in a simulation (or otherwise digital).
If they realized that they were actually an uploaded mind all along (by our civilization rather than a simulation), they should believe that they aren’t conscious. They should claim that observing that they’re conscious wouldn’t change their stated belief that they’re not conscious if they’re digital.
Their probability that they’re in a simulation shouldn’t be updated from their introspection that they’re conscious.
More generally, none of their beliefs should change from introspecting on their consciousness. They should never say “because (I observe introspectively that) I’m conscious”. C-zombie would process the information in exactly the same way, and a belief is only as good as its capacity to differentiate true worlds from false worlds. They must come to the conclusion that they’re conscious by a process that never requires first knowing that they’re conscious (from introspection). If their (introspection of their) consciousness causes them knowing they’re conscious equally well as it would cause a non-conscious being to “know” that, then the belief has zero correlation with the fact, and so it’s not a rational belief and should be discarded.
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.
Is there a standard relaxation of the p-zombies hypothetical you can point to where this is coherent? Because by my understanding, in the original formulation, p-zombies would behave identically in all externally observable respects to conscious equivalents, including by all appearances believing themselves to already be conscious. And agents that thought themselves already conscious would not try to download themselves back into bodies in order to restore consciousness.