Clearly the only reasonable answer is "no, not in general".
I challenge this.
Either you relax the communication channel in such a way that I can access other kinds of information (brain scans, purchase history, body language, etc.) or you do not get to say "not in general", because there's nothing general about two people communicating only through a terminal.
To me it's like you're saying "can you tell me how a cake smells by a picture? No! So I'm not sure that smells are really communicable". Hm.
This post grew out of an old conversation with Wei Dai
Since physical existence of Wei is highly doubtful can we have a link to the conversation?
The argument is too general, as it also proves that it is impossible to know that another biological human has conscious. Maybe nobody except me-now has it.
I knew a person who claimed that he could create 4-dimensional images in hid mind eye. I don't know should I believe him and how to check it.
What if the person claims to be able to add numbers? If you ask them about 2+2 and they answer 4, maybe they were pre-ordered with that response, but if you get them to add a few dozen poisson-distributed numbers, maybe you start believing they're actually implementing the algorithm. This relies on the important distinction between telling two things apart certainly and gathering evidence.
The three examples deal with different kinds of things.
Knowing X mostly means believing in X, or having a memory of X. Ideally beliefs would influence actions, but even if they don't, they should be physically stored somehow. In that sense they are the most real of the three.
Having a mental skill to do X means that you can do X with less time and effort than other people. With honest subjects, you could try measuring these somehow, but, obviously, you may find some subject who claims to have the skill perform slower than another who claims not to. Ultimate...
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?
I think you're doing some priming here by adding &quo...
This seems like a good comment to illustrate, once again, your abuse of the idea of meaning.
I'm proposing the radical new view that the world is made of atoms and other "stuff", and that most words refer to some configurations of this stuff.
There are two ways to understand this claim: 1) most words refer to things which happen also to be configurations of atoms and stuff. 2) most words mean certain configurations of atoms.
The first interpretation would be fairly sensible. In practice you are adopting the second interpretation. This second interpretation is utterly false.
Consider the word "chair." Does the word chair mean a configuration of atoms that has a particular shape that we happen to consider chairlike?
Suppose someone approached a chair in your house with an atomic microscope and discovered that it was not made of atoms, but was a continuous substance without any boundaries in it. Would you suddenly say that it was not a chair? Not at all. You would say "this chair is not made of atoms." This proves conclusively that the meaning of the word chair has nothing whatsoever to do with "a configuration of atoms." A chair is in fact a configuration of atoms; but this is a description of a thing, not a description of a word.
In this view "pain" doesn't just correlate with some brain activity, it is that brain activity.
This could be true, if you mean this as a factual statement. It is utterly false, if you mean it as an explanation of the word "pain," which refers to a certain subjective experience. The word "pain" is not about brain activity in the same way that the word "chair" is not about atoms, as explained above.
But the question of "do robots feel pain", is as interesting and meaningful as "are tables also chairs".
I would just note that "are tables also chairs" has a definite answer, and is quite meaningful.
I'm pointing out that you cannot work out one from another, because your concept of consciousness has no properties or attributes that are more grounded in reality than consciousness itself. You need to play rationalist taboo. If you defined consciousness as "ability to process external events" or "ability to generate thoughts" or "the process that makes some people say they're conscious", finding a correspondence between consciousness and brain states would be possible, even if not easy. But you seem to refuse such definitions, you call them correlates, which suggests that there could be a consciousness that satisfies none of them.
I would say that being a chair (according to the meaning of the word) is correlated with being made of atoms. It may be perfectly correlated in fact; there may be no chair which is not made of atoms, and it may be factually impossible to find or make a chair which is not. But this is a matter for empirical investigation; it is not a matter of the meaning of the word. The meaning of the word is quite open to the possibility that there is a chair not made of atoms. In the same, the meaning of the word "consciousness" refers to a subjective experience, not to any objective description, and consequently in principle the meaning of the word is open to application to a consciousness which does not satisfy any particular objective description, as long as the subjective experience is present.
Suppose someone approached a chair in your house with an atomic microscope and discovered that it was not made of atoms
I explicitly added "other stuff" to my sentence to avoid this sort of argument. I don't want or need to be tied to current understanding of physics here.
But even if I had only said "atoms", this would not be a problem. After seeing a chair that I previously thought was impossible, I can update what I mean by "chair". In the same, but more mundane way, I can go to a chair expo, see a radical new design of ch...
(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!