Connectionists: Chomsky's apple

Stefan C Kremer skremer at uoguelph.ca
Wed Mar 8 20:43:59 EST 2023


One of the criticisms against John Searle’s argument (https://en.wikipedia.org/wiki/Chinese_room) has always been that it wouldn’t be possible to construct a book comprehensive enough to answer all the queries, or that it would take too long to produce an output.  Chat GPT shows that we have at least approached that limitation (perhaps not truly overcome it…yet).

The question posed by Searle (and answered with a “yes” by Chomsky in his thinking about counterfactuals, causal explanation, and thinking) is: is there a difference between understanding and simulated understanding?

I don’t know how we could ever answer this question (an to me that’s the important point), but it seems that Searle’s thought experiment becomes more relevant, now that a feasible implementation can be constructed, than when it was originally proposed.

Stefan


On Mar 8, 2023, at 12:25 PM, Terry Sejnowski <terry at salk.edu> wrote:

CAUTION: This email originated from outside of the University of Guelph. Do not click links or open attachments unless you recognize the sender and know the content is safe. If in doubt, forward suspicious emails to IThelp at uoguelph.ca


I have always been impressed with Chomsky's ability to use plausible
arguments to make his case even when they were fallacious.

https://www.nytimes.com/2023/03/08/opinion/noam-chomsky-chatgpt-ai.html#commentsContainer

"Here’s an example. Suppose you are holding an apple in your hand. Now you let the apple go. You observe the result and say, “The apple falls.” That is a description. A prediction might have been the statement “The apple will fall if I open my hand.” Both are valuable, and both can be correct. But an explanation is something more: It includes not only descriptions and predictions but also counterfactual conjectures like “Any such object would fall,” plus the additional clause “because of the force of gravity” or “because of the curvature of space-time” or whatever. That is a causal explanation: “The apple would not have fallen but for the force of gravity.” That is thinking."

His apple example sounded convincing, so I tested GPT on it:

Me:  If I hold an apple in my hand and let it go what will happen?

GPT:  The apple will fall to the ground due to the force of gravity.

Me: What about any such object?

GPT: Any object released from a person's hand will fall to the ground due to the force of gravity.

Me:  What would happen if there wasn't a force of gravity?

GPT:  If there were no force of gravity, objects would not be able to stay on the ground and would float away in all directions

Chomsky defined thinking by the correct answers to these questions.

Alas, the tide has turned.

Terry

-----

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20230309/5284bcde/attachment.html>


More information about the Connectionists mailing list