(This post grew out of an old conversation with Wei Dai.)
Imagine a person sitting in a room, communicating with the outside world through a terminal. Further imagine that the person knows some secret fact (e.g. that the Moon landings were a hoax), but is absolutely committed to never revealing their knowledge of it in any way.
Can you, by observing the input-output behavior of the system, distinguish it from a person who doesn't know the secret, or knows some other secret instead?
Clearly the only reasonable answer is "no, not in general".
Now imagine a person in the same situation, claiming to possess some mental skill that's hard for you to verify (e.g. visualizing four-dimensional objects in their mind's eye). Can you, by observing the input-output behavior, distinguish it from someone who is lying about having the skill, but has a good grasp of four-dimensional math otherwise?
Again, clearly, the only reasonable answer is "not in general".
Now imagine a sealed box that behaves exactly like a human, dutifully saying things like "I'm conscious", "I experience red" and so on. Moreover, you know from trustworthy sources that the box was built by scanning a human brain, and then optimizing the resulting program to use less CPU and memory (preserving the same input-output behavior). Would you be willing to trust that the box is in fact conscious, and has the same internal experiences as the human brain it was created from?
A philosopher believing in computationalism would emphatically say yes. But considering the examples above, I would say I'm not sure! Not at all!
I know that the experience of stubbing my toe is called pain, and I know that what I'm sitting on is called a chair. But I don't know the "precise descriptions of the full gamut of atomic configurations which implement" them in either case. This is very normal.
You seem to be under impression that I advocate certain methods of examining brains over others. I don't know where you got that? I do believe that everything that could be learned about a brain could be learned by zapping one set of neurons and seeing if another set fires. But if it's more practical for you to show the brain something purple, and ask it to rate how bitter that felt, from 1 to 5, I have no problems with it. This method, while less direct, can be more useful (especially depending on the exact questions you want to answer). The problem, as I understand, is that you believe these two methods to be radically different, when they are not. It's as if you assume something is real, just because it comes out of people's mouths.
I'm not assigning any different meanings to those words, at least not in this context. Are you? Interestingly, both words are pretty awkward to use here. And maybe I can agree that "realization" is a little better.
Parts of my text are referring to the arguments I saw in wikipedia under "multiple realizaility". But the idea that Pain definitely is a thing that exists, rather than just a label for a set of things that your brain sometimes does, that are in some ways similar, is something I do find in your posts. In particular, you have to believe this to even ask whether robots feel pain.
I'm still waiting for your empirical reasons why "purple is not bitter", or better yet, "purple is not a chair", if you feel the concept of bitterness is too subjective.
The chair you are sitting on is a realisation; Van Gogh's painting of his chair at Arles is a representation. You can't sit on it.
... (read more)