[ExI] The symbol grounding problem in strong AI

Stathis Papaioannou stathisp at gmail.com
Mon Jan 11 00:43:02 UTC 2010


2010/1/11 Gordon Swobe <gts_2000 at yahoo.com>:
> --- On Sat, 1/9/10, Stathis Papaioannou <stathisp at gmail.com> wrote:
>
>>> After leaving the hospital, the patient might tell you
>> he believes in Santa Claus, but he won't actually "believe"
>> in it; that is, he won't have a conscious subjective
>> understanding of the meaning of "Santa Claus".
>>
>> He has no understanding of words before the operation, but
>> he still has understanding! If he sees a dog he knows it's a dog,
>
> To think coherently about dogs or about anything else, one must understand words and this poor fellow cannot understand his own spoken or unspoken words or the words of others. At all.
>
> He completely lacks understanding of words, Stathis. Suffering from complete receptive aphasia, he has no coherent thoughts whatsoever.
>
> We can suppose less serious aphasias if you like, but to keep our experiment pure I have assumed complete receptive aphasia.
>
> With b-neurons or possibly with m-neurons we can cure him. We p-neurons we can only program him to speak and behave in a way that objective observers will find acceptable, i.e., we can program him to pass the Turing test.

The patient with complete receptive aphasia *does* have coherent, if
non-verbal thoughts. He can look at a situation, recognise what's
going on, make plans for the future. That's thinking. But this is
beside the point, as I'm sure you can see. It's easy to change the
experiment so that any anatomically localised aspect of consciousness
is taken out and replaced with zombie p-neurons. The original example
was visual perception. Cram has all the neurons responsible for visual
perception replaced and as a consequence (you have to say) he will be
completely blind. However, he will behave as if he has normal vision,
because the rest of his brain is receiving normal input from the
p-neurons. Searle thinks Cram will be blind, notice he is blind, but
be unable to do anything about it. This is only possible if Cram is
able to think with something other than his brain, as you seem to
realise, since you said that maybe Searle didn't really mean what he
wrote or it was taken out of context to make him look bad. So there
are only two remaining alternatives. One is that Cram is not blind but
has perfectly normal vision, because you were wrong about the
p-neurons lacking consciousness. The other is that Cram is blind but
doesn't notice he is blind: honestly believes that nothing has changed
and will tell you that you are crazy for saying he is blind when he
can describe everything he sees as well as you can.

Another example: we replace the neurons in Cram's pain centre with
p-neurons, leaving the rest of the brain intact, then torture him.
Cram screams and tells you to stop. You calmly inform him that he is
deluded: since he has the p-neurons he isn't in pain, he only behaves
and thinks he is in pain.

So if you believe that it is possible to make p-neurons which behave
just like b-neurons but lacking
consciousness/understanding/intentionality then you are saying
something very strange. You are saying that any conscious modality
such as perception or understanding of language can be selectively
removed from your brain (by swapping the relevant b-neurons for
p-neurons) and not only will it not affect behaviour, you also will
not be able to notice that it has been done.

Initially you said that this thought experiment was so preposterous
that you couldn't even think about it. Then you said that the
p-neurons wouldn't actually behave like b-neurons because you don't
believe consciousness is an epiphenomenon, which presents a difficulty
because you think zombies are possible and the behaviour of the brain
is computable. Later you seemed to be saying that the patient who gets
the p-neurons will behave normally but won't notice that an aspect of
his consciousness is gone because he will become a complete zombie and
therefore won't notice anything at all. What is your latest take on
what will happen?

>> But you claim that Cram will actually have no understanding of
>> "dog" despite all this. That is what seems absurd: what else could it
>> possibly mean to understand a word if not to use the word appropriately
>> and believe you know the meaning of the word?
>
> Although Cram uses the word "dog" appropriately after the operation, he won't believe he knows the meaning of the word, i.e., he will not understand the word "dog". If that seems absurd to you, remember that he did not understand it before the operation either. In this respect nothing has changed.

He will hear the word "dog" and remember that he has to take his dog
for a walk. If you ask him to draw a picture of a dog, a cat and a
giraffe he will be able to do it. If you ask him to point to the
tallest of the three animals he has drawn he will point to the
giraffe. That sounds to me like understanding! What more could you
possibly want of the poor fellow?


-- 
Stathis Papaioannou



More information about the extropy-chat mailing list