[ExI] GPT-4 on its inability to solve the symbol grounding problem

Fri Apr 14 10:10:47 UTC 2023

[image: image.png]

A man holding an apple and a pear, in front of a table with a bowl and a
plate. I also asked to add eyes and a mouth and blond hair.
Pretty good job for a blind AI.
Giovanni

On Thu, Apr 13, 2023 at 9:33 PM Giovanni Santostasi <gsantostasi at gmail.com>
wrote:

>
>
> *So are you claiming that you can communicate to someone, (say a
> congenitally blind person that has never experienced your redness) what a
> colorness property like redness is like, with only abstract text?  What do
> you think the term "ineffable" means?*Giovanni: Try to describe the
> experience of seeing red to a person that is congenitally blind.
> GPT-4:
> Describing the experience of seeing red to a person who is congenitally
> blind can be challenging, as they have never had the ability to perceive
> colors. However, we can attempt to convey the concept of red by relating it
> to other senses and emotions.
>
> Red is a warm color, often associated with strong emotions and sensations.
> Imagine the feeling of warmth you experience when you step out into the sun
> on a hot day, or the heat you feel when you hold a warm mug of tea or
> coffee. Red can be related to that sensation of warmth.
>
> In terms of emotions, red is often associated with passion, love, and
> intensity. Think about the feeling of excitement when you receive a gift or
> a surprise, the quickened heartbeat when you are in a thrilling situation,
> or the rush of emotions when you are with someone you love. Red can evoke
> these strong feelings and emotions.
>
> Additionally, red is also connected to the sense of taste. Consider the
> taste of a ripe, juicy strawberry or a spicy chili pepper. The flavors can
> range from sweet to hot and can evoke a sense of energy and stimulation.
> This connection to taste can help provide a sensory association with the
> color red.
>
> While it is impossible to fully convey the visual experience of seeing red
> to a congenitally blind person, relating the color to sensations, emotions,
> and tastes can help provide a contextual understanding of what red
> represents in our experiences.
>
>
>
>
> On Thu, Apr 13, 2023 at 7:24 PM Brent Allsop <brent.allsop at gmail.com>
> wrote:
>
>>
>> Hi Giovanni,
>> So are you claiming that you can communicate to someone, (say a
>> congenitally blind person that has never experienced your redness) what a
>> colorness property like redness is like, with only abstract text?  What do
>> you think the term "ineffable" means?
>>
>>
>> On Wed, Apr 12, 2023 at 9:45 PM Giovanni Santostasi <
>> gsantostasi at gmail.com> wrote:
>>
>>> Brent,
>>> What is your evidence for such statements? Is there an experiment, not a
>>> thought experiment that follows your made-up rules (like the color
>>> converter that has serious problems from a logical and scientific point of
>>> view that I don't want to discuss here). Can you find a paper, a real
>>> experiment in neuroscience that supports this statement:
>>>
>>>
>>> *But there is no way you can communicate to someone what redness is
>>> like, with text alone.*
>>> What do you mean here by communicate? Is it my analogy about touching a
>>> blue line on a map and saying the blue line is not wet?
>>> Is this what you really mean?
>>> In other words, do you mean if I describe to you what happens in my
>>> brain or any other brain what sequences of events, what relationships
>>> between neurons, what neural code represents my perception of red, you are
>>> not going to see red in your head?
>>>
>>> If that is what you mean, do you realize how absurd of an idea this is?
>>>  1) It is not what science is about, it is not supposed to make you feel
>>> red, it is supposed to make you understand what is fundamental about this
>>> phenomenon of red, science's job is to provide simplification,
>>> abstractions, maps, and models. This simplification is not a BUG but a
>>> FEATURE. It is what gives power to science.
>>> 2) The usefulness of making a model is that you can carry the map in
>>> your pocket, sort of speak, and bring it with you in another location and
>>> communicate everything essential (for whatever purpose) to somebody else
>>> that has never been in that place. Yes, they are not to experience the
>>> landscape as if they were there but that is not the point at all.
>>> If we use the analogy of the blueprint instead of a map I can recreate a
>>> car or a building using the blueprint and if somebody comes by and points
>>> to the blueprint and says "but this engine doesn't move" you will think
>>> that person is crazy and mentally impaired. If you want to ride the car,
>>> let me build it from the blueprint and then you can do that.
>>>
>>> So your statement above is both crazy and obvious at the same time.
>>> Science is not in the business of making you feel the original thing
>>> that is described. It is in the opposite business, it tries to abstract the
>>> essential parts, which are mostly relational parts, and how things are
>>> related to each other. This is also how science can abstract away even from
>>> the original form of something. Think about how we abstracted away the
>>> meaning of flight from birds. It is not about the feathers, and the
>>> flapping wings but the principle of aerodynamics. You can create a flying
>>> machine by using these principles that are related but not a 1 to 1
>>> relationship with how birds solved the problem of aerodynamics.
>>> By the way, this is also a natural way. Think about how many living
>>> beings rediscovered in evolution sight, camouflage, hydrodynamics,
>>> photosynthesis. Think about DNA.
>>> Yes, think about DNA. Does DNA make you see my redness? No, but my
>>> redness was somehow contained in the DNA as code. You can build the DNA to
>>> build a Giovanni that then will experience red. But if you understand where
>>> in the DNA the redness is represented, then you can use that information to
>>> understand everything there is to understand about Giovanni's redness from
>>> a scientific point of view.
>>>
>>> I think maybe in writing this down I may understand an issue that could
>>> rise to some of your thinking. That is the idea of computational
>>> irreducibility that is an idea that Wolfram developed. All the phenomena,
>>> in reality, are a sort of code but you cannot predict what the result of
>>> the code is in advance in some instances. You need to run the code to know
>>> what the results are. Maybe this is something that you have in mind when
>>> you talk about this business of redness, I have the suspicions that you are
>>> thinking something like that but you are expressing it in a way that is not
>>> easy to understand or causes a lot of confusion. So it is still code if you
>>> do but you raise an important and relevant issue about computation that
>>> some of them are so complex that they are irreducible. I'm ok with qualia
>>> being irreducible computation. Maybe is the only scientific meaningful way
>>> to think about them.
>>> Here a summary of this issue by Wolfram himself:
>>>
>>>
>>> https://writings.stephenwolfram.com/2021/09/charting-a-course-for-complexity-metamodeling-ruliology-and-more/
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>>
>>> On Wed, Apr 12, 2023 at 6:37 PM Brent Allsop via extropy-chat <
>>> extropy-chat at lists.extropy.org> wrote:
>>>
>>>>
>>>> Hi Jason,
>>>>
>>>> On Wed, Apr 12, 2023 at 8:07 AM Jason Resch via extropy-chat <
>>>> extropy-chat at lists.extropy.org> wrote:
>>>>
>>>>> Thus the simulation, like the isomorphic graph, by preserving all the
>>>>> same relationships recovers all the same properties. If the glutamate
>>>>> molecule possesses redness, then the perfect simulation of glutamate will
>>>>> possess redness too.
>>>>>
>>>>
>>>> ALL of our objective observations of physics can be fully described
>>>> with abstract text.
>>>> All of that which you could simulate, can also be described with
>>>> abstract text.
>>>>
>>>> But there is no way you can communicate to someone what redness is
>>>> like, with text alone.
>>>> You MUST have pictures, to produce the subjective experience, before
>>>> someone can know what redness is like.
>>>>
>>>> There must be certain stuff in the brain which can be computationally
>>>> bound, which produces something beyond, what can be described via abstract
>>>> text.
>>>> You can abstractly describe all of it, you can objectively observe all
>>>> of it with our senses, and you can abstractly simulate all of that.
>>>> But until it is physically computationally bound with the rest of our
>>>> consciousness, you can't know the true quality you are only abstractly
>>>> describing and simulating.
>>>>
>>>> In other words, like abstract text can't communicate the nature of
>>>> qualities.
>>>> An abstract simulation also, can't produce anything more than abstract
>>>> text can describe.
>>>> At least, that is what I predict.
>>>>
>>>>
>>>>
>>>> _______________________________________________
>>>> extropy-chat mailing list
>>>> extropy-chat at lists.extropy.org
>>>> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat
>>>>
>>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20230414/80a5819a/attachment.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 21913 bytes
Desc: not available
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20230414/80a5819a/attachment.png>