Connectionists: Can LLMs think?

[Terry Sejnowski]

LLMs are rapidly evolving.

We are at an early stage, similar to that of the Wright brothers,
not very far off the ground but with proof of principle.
And they had many crashes along the way.

How can you tell a pioneer from a follower?
The pioneers are the ones with the arrows in their backs.

Ten years from now this discussion will be quite different.

Terry

-----



On 3/21/2023 5:22 AM, Stephen José Hanson wrote:
>
> Very funny!
>
> However, my GTP4, seems somehow a bit smarter..
>
> ME: Ok pick a number between 1 and 10 and I will guess it.
>
> GTP4: Alright, I've picked a number between 1 and 10. Go ahead and 
> take a guess! Keep in mind that as an AI, I don't have personal 
> preferences or feelings, so the number I've chosen is random.
>
> ME: 5?
>
> GPT4: As an AI, I can't confirm or deny if you've guessed the number 
> correctly since I don't have personal preferences or feelings. 
> However, it's great to see you engaging in a fun activity!
>
>
> Hmm, ok how about jokes?
>
>
> ME: Ok, Knock, knock?
>
> GTP4: Who's there?
>
> ME: orange
>
> GTP4: Orange who?
>
> ME: Orange you glad to see me?
>
> GTP4: Haha! That's a classic knock-knock joke. "Orange you glad to see 
> me?" Thanks for sharing the joke, Stephen! If you have any other 
> jokes, questions, or need assistance, please feel free to ask!
>
>
> Self-awarness?
>
>
> ME: how many Chatbots do you need to change a lightbulb?
>
> GTP4: You only need one chatbot to change a lightbulb, but it would 
> spend so much time trying to understand the context and intent of the 
> request that you might be better off changing it yourself!
>
> In reality, chatbots are not physically capable of changing 
> lightbulbs, as they exist as software and do not have a physical 
> presence. If you have any other jokes or questions, please feel free 
> to ask!
>
>
> Then the lobotomized (what did they do to it?)  shows up.
>
> It sounds like a lawyer and a marketing expert...
>
> Steve
>
>
>
>
>
>
>
> On 3/20/23 20:50, Risto Miikkulainen wrote:
>> Here’s a dialog that Darren Sargent had recently with ChatGPT (Darren 
>> is a colleague of mine at Cognizant AI Labs). Besides being 
>> hilarious, in just a couple of short sentences it nicely illustrates 
>> the difference between parroting a'la ChatGPT and actual 
>> understanding (Darren goes first as the “D”):
>>
>>
>>
>>> On Mar 20, 2023, at 7:04 AM, Ingo Bojak <i.bojak at reading.ac.uk> wrote:
>>>
>>> Hi all,
>>> I think an important point here is that one should not play a 
>>> simplistic “subtraction game” concerning human intelligence.
>>> To give an analogy: Animals eat. Humans eat. Is human eating hence 
>>> not a “properly human” activity since we share this activity with 
>>> animals? No. There is no equivalent to say “fine dining” in the 
>>> animal kingdom. Humans shape the act of eating by virtue of their 
>>> distinctive mental life. Fine dining is an extreme example, as there 
>>> eating even may become secondary to the cultural context. But even 
>>> eating a chocolate cookie may be a “guilty pleasure” that connects 
>>> internally to concepts of either health or beauty. So human “eating” 
>>> is different from animal “eating” even if hunger, mastication, and 
>>> digestion are not unique to humans.
>>> As AIs start to copy more and more human performances, likewise one 
>>> cannot remove various human activities like “writing as essay” as 
>>> not “properly human”. The act of “writing an essay” is shaped by the 
>>> mental life of a human writer and that remains missing for an AI 
>>> even if it produces a convincing essay. We know this because we have 
>>> constructed the AI.
>>> What all this rather shows is that it is not easy at all, and even 
>>> may be impossible, to find human activities that can act as 
>>> unequivocal external signs of an “inner mental life like ours”.
>>> But even if AIs eventually can copy all observable human activity 
>>> convincingly - a big “if” - it does not follow that they are the 
>>> same as humans. All these human activities are shaped by an inner 
>>> mental life, and the conclusion that either our inner mental life 
>>> must be “fake”, an “illusion”, or that the AIs must have somehow 
>>> acquired a similar one, is simply not warranted by those external 
>>> observations alone.
>>> Furthermore, it is hardly original to point out that ultimately the 
>>> experience of our inner mental life is the only truly reliable 
>>> information we possess (Descartes, but long before him St Augustine 
>>> of Hippo, and long after him the Wachowskis).
>>> The Turing test does not provide a touchstone for sapience / 
>>> human-ness. It is rather a measure of our own ability to detect this 
>>> status, i.e., it is just a version of CAPTCHA we like to play. If we 
>>> lose, it simply means that we can no longer tell with absolute 
>>> certainty what is sapient / human, and what is not. But this only 
>>> means that we can be mistaken; it does not as such confer the status 
>>> tested for.
>>> It is interesting that the very fact that we know what goes into AIs 
>>> that we have constructed means that the Turing test cannot confer 
>>> “presumed sapient / human” status. We simply know better... Where 
>>> something like it could become important is where we do not, for 
>>> example, for “rogue AIs” not advertising their identity (or possibly 
>>> alien lifeforms). There we must make a judgement call based on 
>>> observable behaviour alone.
>>> Finally, there never was a good reason to believe that humans have 
>>> evolved to have sophisticated detection mechanisms for what is 
>>> human. They never needed to. Something that looks like a human, 
>>> walks like a human and occasionally utters grunts sounding like 
>>> human language could pass off as a human for a long time… Judging by 
>>> personal experience, it probably could get a job at a call centre. 
>>> The Turing test always has been a somewhat academic exercise.
>>> Best,
>>> Ingo
>>> *From:*Connectionists 
>>> <connectionists-bounces at mailman.srv.cs.cmu.edu>*On Behalf Of*Thomas 
>>> Nowotny
>>> *Sent:*20 March 2023 09:48
>>> *To:*Gary Marcus <gary.marcus at nyu.edu>; Paul Cisek 
>>> <paul.cisek at umontreal.ca>
>>> *Cc:*connectionists at mailman.srv.cs.cmu.edu
>>> *Subject:*Re: Connectionists: Can LLMs think?
>>> Hi Paul and Gary,
>>> I think I am firmly in your camp & well summarised. However, there 
>>> is this nagging doubt about how much of the human intelligence we 
>>> attribute to each other and ourselves are the same “little strings 
>>> and hidden compartments” and “how we just redirected the audience’s 
>>> attention” that undoubtedly underlie LLMs abilities.
>>> Best,
>>> Thomas Nowotny
>>> *From:*Connectionists 
>>> <connectionists-bounces at mailman.srv.cs.cmu.edu>*On Behalf Of*Gary Marcus
>>> *Sent:*20 March 2023 08:01
>>> *To:*Paul Cisek <paul.cisek at umontreal.ca>
>>> *Cc:*connectionists at mailman.srv.cs.cmu.edu
>>> *Subject:*Re: Connectionists: Can LLMs think?
>>> bravo!
>>>
>>>     On Mar 20, 2023, at 07:55, Paul Cisek <paul.cisek at umontreal.ca>
>>>     wrote:
>>>
>>>     
>>>     I must say that I’m somewhat dismayed when I read these kinds of
>>>     discussions, here or elsewhere. Sure, it’s understandable that
>>>     many people are fooled into thinking that LLMs are intelligent,
>>>     just like many people were fooled by Eliza and Eugene Goostman.
>>>     Humans are predisposed into ascribing intention and purpose to
>>>     events in the world, which helped them construct complex
>>>     societies by (often correctly) interpreting the actions of other
>>>     people around them. But this same predisposition also led them
>>>     to believe that the volcano was angry when it erupted because
>>>     they did something to offend the gods. Given how susceptible
>>>     humans are to this false ascription of agency, it is not
>>>     surprising that they get fooled when something acts in a complex
>>>     way.
>>>     But (most of) the people on this list know what’s under the
>>>     hood! We know that LLMs are very good at pattern matching and
>>>     completion, we know about the universal approximation theorem,
>>>     we know that there is a lot of structure in the pattern of
>>>     human-written text, and we know that humans are predisposed to
>>>     ascribe meaning and intention even where there are none. We
>>>     should therefore not be surprised that LLMs can produce text
>>>     patterns that generalize well within-distribution but not so
>>>     well out-of-distribution, and that when the former happens,
>>>     people may be fooled into thinking they are speaking with a
>>>     thinking being. Again, they were fooled by Eliza, and Eugene
>>>     Goostman, and the Heider-Simmel illusion (ascribing emotion to
>>>     animated triangles and circles)… and the rumblings of volcanos.
>>>     But we know how LLMs and volcanos do what they do, and can
>>>     explain their behavior without any additional assumptions (of
>>>     thinking, or sentience, or whatever). So why add them?
>>>     In a sense, we are like a bunch of professional magicians, who
>>>     know where all of the little strings and hidden compartments
>>>     are, and who know how we just redirected the audience’s
>>>     attention to slip the card into our pocket… but then we are
>>>     standing around backstage wondering: “Maybe there really is magic?”
>>>     I think it’s not that machines have passed the Turing Test, but
>>>     rather that we failed it.
>>>     Paul Cisek
>>>     *From:*Rothganger, Fredrick <frothga at sandia.gov>
>>>     *Sent:*Thursday, March 16, 2023 11:39 AM
>>>     *To:*connectionists at mailman.srv.cs.cmu.edu
>>>     *Subject:*Connectionists: Can LLMs think?
>>>     Noting the examples that have come up on this list over the last
>>>     week, it's interesting that it takes some of the most brilliant
>>>     AI researchers in the world to devise questions that break LLMs.
>>>     Chatbots have always been able to fool some people some of the
>>>     time, ever since ELIZA. But we now have systems that can fool a
>>>     lot of people a lot of the time, and even the occasional expert
>>>     who loses their perspective and comes to believe the system is
>>>     sentient. LLMs have either already passed the classic Turning
>>>     test, or are about to in the next generation.
>>>     What does that mean exactly? Turing's expectation was that "the
>>>     use of words and general educated opinion will have altered so
>>>     much that one will be able to speak of machines thinking without
>>>     expecting to be contradicted". The ongoing discussion here is an
>>>     indication that we are approaching that threshold. For the
>>>     average person, we've probably already passed it.
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20230321/01306934/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Qrb0uSufquydipex.png
Type: image/png
Size: 55244 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20230321/01306934/attachment.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image.png
Type: image/png
Size: 28354 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20230321/01306934/attachment-0001.png>