Connectionists: Chomsky's apple

Thu Mar 9 10:36:49 EST 2023

The problem with thought experiments, and particularly the famous ones in theory of mind (Searle's Chinese Room, Mary's Room, etc.) is that they contain a subtle appeal to intuition. You get out what you bring to it. Put another way, they help expose and clarify your own intuitions, but they don't actually prove anything.

Stefan asked the right question: Is there a difference between simulating something and actually doing it?

My answer: If your simulation gets real work done, then no. Is there a difference between simulating the addition of 2+2 and actually adding 2+2? As long as you get the answer 4, then no. Is there a difference between co-writing a science-fiction story about a user interacting with a sentient AI and actually being a sentient AI? Probably yes.

This goes back to the classic question that Turing raised. If the machine's behavior is indistinguishable from a human thinking, maybe we should grant that it actually thinks. Things we used to imagine were solely in the human domain, which required some special sauce that machines lack, have successively fallen to the onslaught of the AI project. Chess, fine art, Python code ...

Perhaps the real problem is our intuition that humans are somehow special, rather than just machines ourselves. We have this "yeah, but..." response each time one of these capabilities gets overtaken. That's an existential question, and we need some time to mourn.

Then we should utterly ignore our feelings of Human Exceptionalism and focus on how stuff works. How does the brain actually get thinking done? A proper theory should address the full breadth of evidence from neuroscience (not just a few cherry-picked general features) and all the results of ANN work.

________________________________
From: Connectionists <connectionists-bounces at mailman.srv.cs.cmu.edu> on behalf of Stefan C Kremer <skremer at uoguelph.ca>
Sent: Wednesday, March 8, 2023 6:43 PM
To: Terry Sejnowski <terry at salk.edu>
Cc: Connectionists List <connectionists at cs.cmu.edu>
Subject: [EXTERNAL] Re: Connectionists: Chomsky's apple

You don't often get email from skremer at uoguelph.ca. Learn why this is important<https://aka.ms/LearnAboutSenderIdentification>
One of the criticisms against John Searle’s argument (https://en.wikipedia.org/wiki/Chinese_room<https://gcc02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fen.wikipedia.org%2Fwiki%2FChinese_room&data=05%7C01%7Cfrothga%40sandia.gov%7C094d520e8de347cc173408db2075be4d%7C7ccb5a20a303498cb0c129007381b574%7C1%7C0%7C638139462313512288%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=3TKOH61khVrsTyuFHJvjeMHNfkEyA4PrpZea3StuePw%3D&reserved=0>) 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/e0bac91b/attachment.html>