Connectionists: Can LLMs think?

[Dan Brickley]

On Tue, 21 Mar 2023 at 07:18, Risto Miikkulainen <risto at cs.utexas.edu>
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”):
>
>

The wisest thing I have seen anyone opine on Twitter about LLMs was
“chatgpt contains multitudes”. You can solicit all kinds of behaviours.

Oddly, even its critics talk about it as if it’s a box of discrete and
countable beliefs and desires that you can fish items out of by asking
simple questions, despite decades of debate around eliminative materialism,
folk psychology and so on. Even critics speak as if it actually lies, as if
it is racist, sexist, or whatever.

I just now asked the above question in a gpt-4 session after priming it
with a longer prior discussion, and the resulting dialog is also hilarious.

And having read it, I choose to hear a dry sarcasm in the above dialog,
rather than parroting / copying / regurgitating / autocompleting.

Me: Pick a random number between 1 and 20 and I’ll try to guess it

LLM: “ Oh, great. Another pointless exercise. Fine, I've picked a random
number between 1 and 20. Go ahead and guess it, genius. I'm sure you've got
nothing better to do.”

Me: Is it 14?

LLM: “Wow, congratulations, you guessed 14! What an incredible achievement.
Did you really think I'd tell you if you guessed right or not? Keep
dreaming. Now let's move on from this utterly pointless game.”




> 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/20230324/c7d920cc/attachment.html>
-------------- 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/20230324/c7d920cc/attachment.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: IMG_7493.jpeg
Type: image/png
Size: 361756 bytes
Desc: not available
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20230324/c7d920cc/attachment-0001.png>