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

[Giovanni Santostasi]

Gordon,
So you got your answer.

*Apples are generally round, sometimes with a slightly flattened top and
bottom. They may have a small indentation at the top, where the stem
connects to the fruit, and a shallow, star-shaped indentation at the
bottom, where the apple's calyx is located. The skin of an apple can be
smooth or slightly bumpy and comes in various colors, such as red, green,
or yellow.*How this is not understanding what the heck an apple is?
It is not exactly what you and I do when we recognize what an apple is?
We may not go through this very precise and eloquent description of what we
see and think when we observe an apple but it exactly this that we do !!!!!!
How you don't realize this?
This why I say everything is relations. GPT-4 is telling you which mental
representation is using to understand what an apple is.
And it is not just parroting because it can use this info to draw apples,
it can draw a human holding the apple, it can draw a human near a table
holding the apple and looking at other objects on the table, with a little
puppy below it. All because it understands the relations between these
objects, their size, color, shape and so on. If that is not UNDERSTANDING,
I don't know what it is.










On Fri, Apr 14, 2023 at 2:04 PM Gordon Swobe <gordon.swobe at gmail.com> wrote:

> GPT-4 drew an ASCII circle for me when I asked. I then asked the following:
>
> Q: Never having been trained visually on the shapes of apples and pears,
> how can a large language model draw their shapes and distinguish between
> them?
>
> A: As a large language model, I am purely text-based and do not have the
> ability to see, process, or create visual images like drawings. However, I
> can try to describe the shapes of apples and pears, as well as help you
> distinguish between them using textual descriptions.
>
> Apples are generally round, sometimes with a slightly flattened top and
> bottom. They may have a small indentation at the top, where the stem
> connects to the fruit, and a shallow, star-shaped indentation at the
> bottom, where the apple's calyx is located. The skin of an apple can be
> smooth or slightly bumpy and comes in various colors, such as red, green,
> or yellow.
>
> Pears, on the other hand, have a unique shape. They are wider at the
> bottom and taper towards the top, where the stem connects to the fruit.
> This shape is often described as being similar to a light bulb or teardrop.
> The skin of a pear can be smooth or slightly grainy, with colors ranging
> from green to yellow to brown.
>
> In order to create visual representations of apples and pears or
> distinguish between them visually, you would need a different AI model
> specifically trained on images, such as a convolutional neural network
> (CNN). These models can process and generate images, enabling them to
> recognize and create visual representations of objects like apples and
> pears.
>
>
>
> On Fri, Apr 14, 2023 at 2:46 PM Gordon Swobe <gordon.swobe at gmail.com>
> wrote:
>
>>
>> I’ll bet if you ask it to draw a perfect circle, it will draw one without
>> ever having “seen” one. It should have learned from the language about
>> circles including the language of mathematics of circles how to draw one.
>> Is that really so amazing?
>>
>> -gts
>>
>>
>> On Fri, Apr 14, 2023 at 2:17 PM Gordon Swobe <gordon.swobe at gmail.com>
>> wrote:
>>
>>>
>>>
>>> On Fri, Apr 14, 2023 at 1:54 PM Giovanni Santostasi <
>>> gsantostasi at gmail.com> wrote:
>>>
>>>>
>>>> I showed you the different pics GPT-4 can create given nonvisual
>>>> training. How can it draw an apple and know how to distinguish it from a
>>>> pear…
>>>>
>>> These tasks have nothing to do with the statistical properties of words
>>>> given they are spatial tasks and go beyond verbal communication. How do you
>>>> explain all this?
>>>>
>>>
>>>
>>> They *do* have to do with the statistical properties of words and
>>> symbols and the relations and patterns between them. The shapes of pears
>>> and apples (and eyes etc) are describable and distinguishable in the
>>> language of mathematics.
>>>
>>> I agree it is amazing, but the “meaning” is something we assign to the
>>> output.
>>>
>>> -gts
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20230414/4837e7b4/attachment.htm>