[ExI] LLM's cannot be concious

[Giovanni Santostasi]

 What about math, it is a language but it has no referent.

Mathematics can be thought of as a language, but it is fundamentally
different from natural languages like English or Spanish. While natural
languages primarily rely on referents to convey meaning, mathematics is an
abstract and formal system used to represent relationships, quantities, and
patterns.

However, it's not accurate to say that mathematics has no referents at all.
In mathematics, symbols and expressions serve as a means of representing
abstract concepts and relationships, and these symbols can be seen as
having referents, albeit abstract ones. For example, the number "2" is a
symbol that represents the abstract concept of "two of something."
Similarly, variables like "x" or "y" serve as placeholders for unknown or
varying quantities, and they can also be thought of as having referents
within the context of a specific problem or equation.

In this sense, the referents in mathematics are more abstract and
generalized compared to those in natural languages, which are often tied to
concrete objects, experiences, or ideas. The power of mathematics comes
from its ability to represent and manipulate these abstract concepts and
relationships in a precise and logical way, allowing us to model and solve
problems across a wide range of disciplines.
[image: Giovanni Santostasi]
But then a NLM doesn't need to have a direct experience of 2 of something,
that concept can be totally abstract, right?

Yes, you are correct. A neural language model (NLM), like ChatGPT, does not
need direct experience of "two of something" to understand or use the
concept. NLMs learn from vast amounts of text data, and through this
process, they develop an understanding of the abstract concept of numbers,
including "2," based on the patterns and relationships observed in the data.

NLMs can learn about the properties and usage of numbers in language
without having any real-world experience or direct interaction with
objects. They can generate appropriate responses involving numbers or
mathematical concepts because they have been exposed to numerous examples
of how these concepts are used in various contexts during their training.

On Thu, Mar 23, 2023 at 6:35 PM Adrian Tymes via extropy-chat <
extropy-chat at lists.extropy.org> wrote:

> On Thu, Mar 23, 2023 at 6:18 PM Gordon Swobe via extropy-chat <
> extropy-chat at lists.extropy.org> wrote:
>
>> I think it was Adrian who asked you that question. A referent as I use
>> the term is something that exists outside of language to which a word
>> refers. You have an apple in your hand and you say "this is an apple." The
>> apple in your hand is the referent that corresponds to your word "apple."
>>
>> As for whether referents are data, it is unclear to me how referents
>> could be data. I am inclined to say no but I am not sure what Adrain is
>> getting at here.
>>
>
> Ah, I thought you meant that the referent was the *fact that* that was an
> apple, rather than the referent being the apple itself.  Facts are data;
> objects (such as apples) are not.
> _______________________________________________
> 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/20230323/4110b85c/attachment.htm>