<html><head><meta http-equiv="content-type" content="text/html; charset=utf-8"></head><body dir="auto"><div dir="ltr"></div><div dir="ltr"></div><blockquote type="cite"><div dir="ltr">“How can you tell a pioneer from a follower? “</div><div dir="ltr">“ The pioneers are the ones with the arrows in their backs. ” </div></blockquote><div dir="ltr">…said so many proponents of jetpacks, dirigibles, expert systems, over 3000 failed cryptocurrencies etc. (I think Elizabeth Holmes also expressed similar sentiments?)</div><div dir="ltr"><br></div><div dir="ltr">More seriously, I too expect that AI will make major advances in the next decade, but that part of that advance will come from accepting that pure LLMs are not the answer, but rather must be used in conjunction with other tools, both for freshness (eg in search) and factuality.</div><div dir="ltr"><br></div><div dir="ltr">Pure LLMs themselves are rapidly growing in some ways—but not all. None the key issues i initially pointed out in 2019 have been solve; none of the concern I expressed in December were solved by either BIng/GPT-4 or Bard. <a href="https://garymarcus.substack.com/p/what-to-expect-when-youre-expecting?utm_source=%2Finbox&utm_medium=reader2">https://garymarcus.substack.com/p/what-to-expect-when-youre-expecting?utm_source=%2Finbox&utm_medium=reader2</a> </div><div dir="ltr"><br><blockquote type="cite">On Mar 22, 2023, at 10:18, Terry Sejnowski <terry@snl.salk.edu> wrote:<br><br></blockquote></div><blockquote type="cite"><div dir="ltr">
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
LLMs are rapidly evolving.<br>
<br>
We are at an early stage, similar to that of the Wright brothers,<br>
not very far off the ground but with proof of principle.<br>
And they had many crashes along the way.<br>
<br>
How can you tell a pioneer from a follower? <br>
The pioneers are the ones with the arrows in their backs.<br>
<br>
Ten years from now this discussion will be quite different.<br>
<br>
Terry<br>
<br>
-----<br>
<br>
<div><Qrb0uSufquydipex.png></div><br>
<br>
<div class="moz-cite-prefix">On 3/21/2023 5:22 AM, Stephen José
Hanson wrote:<br>
</div>
<blockquote type="cite" cite="mid:562ab84e-2e73-616b-87a7-c3c62cef6eb3@rubic.rutgers.edu">
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<p><font size="4"><font face="monospace">Very funny!</font></font></p>
<p><font size="4"><font face="monospace">However, my GTP4, seems
somehow a bit smarter..</font></font></p>
<p style="line-height: 100%; margin-bottom: 0.2in"><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">ME: Ok pick a number between 1 and 10 and I
will guess it.</font></font></span></p>
<p style="border: 1px solid #d9d9e3; padding: 0.02in"><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">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.</font></font></span></p>
<p><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">ME: 5?</font></font></span></p>
<p style="border: 1px solid #d9d9e3; padding: 0.02in"><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">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!</font></font></span></p>
<p style="line-height: 100%; margin-bottom: 0in"><br>
</p>
<p>Hmm, ok how about jokes?</p>
<p><br>
</p>
<p style="line-height: 100%; margin-bottom: 0in"><font face="Ubuntu"><font style="font-size: 11pt" size="2">ME: Ok,
Knock, knock?</font></font></p>
<p style="border: 1px solid #d9d9e3; padding: 0.02in"><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">GTP4: Who's there?</font></font></span></p>
<p><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">ME: orange</font></font></span></p>
<p style="border: 1px solid #d9d9e3; padding: 0.02in"><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">GTP4: Orange who?</font></font></span></p>
<p><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">ME: Orange you glad to see me?</font></font></span></p>
<p style="border: 1px solid #d9d9e3; padding: 0.02in"><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">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!</font></font></span></p>
<p style="margin-bottom: 0in"><br>
</p>
<p style="margin-bottom: 0in">Self-awarness?</p>
<p style="margin-bottom: 0in"><br>
</p>
<p><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">ME: how many Chatbots do you need to change
a lightbulb?</font></font></span></p>
<p style="border: 1px solid #d9d9e3; padding: 0.02in"><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">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!</font></font></span></p>
<p style="border: 1px solid #d9d9e3; padding: 0.02in"><span style="display: inline-block; border: 1px solid #d9d9e3;
padding: 0.02in"><font style="font-size: 11pt" size="2"><font face="Ubuntu">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!</font></font></span></p>
<p style="margin-bottom: 0in"><br>
</p>
<p style="line-height: 100%; orphans: 2; widows: 2; margin-bottom:
0in">Then the lobotomized (what did they do to it?) shows up.</p>
<p style="line-height: 100%; orphans: 2; widows: 2; margin-bottom:
0in">It sounds like a lawyer and a marketing expert...</p>
<p style="line-height: 100%; orphans: 2; widows: 2; margin-bottom:
0in">Steve<br>
</p>
<p style="margin-bottom: 0in"><br>
</p>
<p><br>
<br>
</p>
<p style="margin-bottom: 0in"><br>
</p>
<p style="font-variant: normal; letter-spacing: normal;
font-style: normal; font-weight: normal; line-height: 100%;
orphans: 2; widows: 2; margin-bottom: 0in">
<br>
</p>
<p>
</p>
<p><br>
</p>
<div class="moz-cite-prefix">On 3/20/23 20:50, Risto Miikkulainen
wrote:<br>
</div>
<blockquote type="cite" cite="mid:AE89BC36-6456-4C11-8084-A173748EE480@cs.utexas.edu">
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”):
<div class=""><br class="">
</div>
<div class=""><div><image.png></div><br class="">
<div><br class="">
<blockquote type="cite" class="">
<div class="">On Mar 20, 2023, at 7:04 AM, Ingo Bojak <<a href="mailto:i.bojak@reading.ac.uk" class="moz-txt-link-freetext" moz-do-not-send="true">i.bojak@reading.ac.uk</a>>
wrote:</div>
<br class="Apple-interchange-newline">
<div class="">
<div class="WordSection1" style="page: WordSection1;
caret-color: rgb(0, 0, 0); font-family: Helvetica;
font-size: 12px; font-style: normal;
font-variant-caps: normal; font-weight: 400;
letter-spacing: normal; text-align: start;
text-indent: 0px; text-transform: none; white-space:
normal; word-spacing: 0px; -webkit-text-stroke-width:
0px; text-decoration: none;">
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">Hi all,<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">I think an important point
here is that one should not play a simplistic
“subtraction game” concerning human intelligence.<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">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.<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">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.<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">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”.<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">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.<span class="Apple-converted-space"> </span><o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">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).<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">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.<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">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.<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">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.<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">Best,<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">Ingo<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div class="">
<div style="border-style: solid none none;
border-top-width: 1pt; border-top-color: rgb(225,
225, 225); padding: 3pt 0cm 0cm;" class="">
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<b class=""><span style="font-size: 11pt;
font-family: Calibri, sans-serif;" class="" lang="EN-US">From:</span></b><span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="" lang="EN-US"><span class="Apple-converted-space"> </span>Connectionists
<<a href="mailto:connectionists-bounces@mailman.srv.cs.cmu.edu" class="moz-txt-link-freetext" moz-do-not-send="true">connectionists-bounces@mailman.srv.cs.cmu.edu</a>><span class="Apple-converted-space"> </span><b class="">On Behalf Of<span class="Apple-converted-space"> </span></b>Thomas
Nowotny<br class="">
<b class="">Sent:</b><span class="Apple-converted-space"> </span>20
March 2023 09:48<br class="">
<b class="">To:</b><span class="Apple-converted-space"> </span>Gary
Marcus <<a href="mailto:gary.marcus@nyu.edu" class="moz-txt-link-freetext" moz-do-not-send="true">gary.marcus@nyu.edu</a>>;
Paul Cisek <<a href="mailto:paul.cisek@umontreal.ca" class="moz-txt-link-freetext" moz-do-not-send="true">paul.cisek@umontreal.ca</a>><br class="">
<b class="">Cc:</b><span class="Apple-converted-space"> </span><a href="mailto:connectionists@mailman.srv.cs.cmu.edu" class="moz-txt-link-freetext" moz-do-not-send="true">connectionists@mailman.srv.cs.cmu.edu</a><br class="">
<b class="">Subject:</b><span class="Apple-converted-space"> </span>Re:
Connectionists: Can LLMs think?<o:p class=""></o:p></span></div>
</div>
</div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<o:p class=""> </o:p></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">Hi Paul and Gary,<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">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 “</span><span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">little strings and hidden
compartments” and “how we just redirected the
audience’s attention” that undoubtedly underlie
LLMs abilities.<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">Best,<o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="">Thomas Nowotny</span><span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class=""><o:p class=""> </o:p></span></div>
<div class="">
<div style="border-style: solid none none;
border-top-width: 1pt; border-top-color: rgb(225,
225, 225); padding: 3pt 0cm 0cm;" class="">
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<b class=""><span style="font-size: 11pt;
font-family: Calibri, sans-serif;" class="" lang="EN-US">From:</span></b><span style="font-size: 11pt; font-family: Calibri,
sans-serif;" class="" lang="EN-US"><span class="Apple-converted-space"> </span>Connectionists
<<a href="mailto:connectionists-bounces@mailman.srv.cs.cmu.edu" style="color: rgb(5, 99, 193);
text-decoration: underline;" class="moz-txt-link-freetext" moz-do-not-send="true">connectionists-bounces@mailman.srv.cs.cmu.edu</a>><span class="Apple-converted-space"> </span><b class="">On Behalf Of<span class="Apple-converted-space"> </span></b>Gary
Marcus<br class="">
<b class="">Sent:</b><span class="Apple-converted-space"> </span>20
March 2023 08:01<br class="">
<b class="">To:</b><span class="Apple-converted-space"> </span>Paul
Cisek <<a href="mailto:paul.cisek@umontreal.ca" style="color: rgb(5, 99, 193);
text-decoration: underline;" class="moz-txt-link-freetext" moz-do-not-send="true">paul.cisek@umontreal.ca</a>><br class="">
<b class="">Cc:</b><span class="Apple-converted-space"> </span><a href="mailto:connectionists@mailman.srv.cs.cmu.edu" style="color: rgb(5, 99, 193);
text-decoration: underline;" class="moz-txt-link-freetext" moz-do-not-send="true">connectionists@mailman.srv.cs.cmu.edu</a><br class="">
<b class="">Subject:</b><span class="Apple-converted-space"> </span>Re:
Connectionists: Can LLMs think?<o:p class=""></o:p></span></div>
</div>
</div>
<div style="margin: 0cm; font-size: 12pt; font-family:
"Times New Roman", serif;" class="">
<o:p class=""> </o:p></div>
<div class="">
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman", serif;" class="">
bravo!<span style="font-size: 11pt;" class=""><o:p class=""></o:p></span></div>
</div>
<div class="">
<p class="MsoNormal" style="margin: 0cm 0cm 12pt;
font-size: 12pt; font-family: "Times New
Roman", serif;">
<o:p class=""> </o:p></p>
<blockquote style="margin-top: 5pt; margin-bottom:
5pt;" class="">
<p class="MsoNormal" style="margin: 0cm 0cm 12pt;
font-size: 12pt; font-family: "Times New
Roman", serif;">
On Mar 20, 2023, at 07:55, Paul Cisek <<a href="mailto:paul.cisek@umontreal.ca" style="color: rgb(5, 99, 193);
text-decoration: underline;" class="moz-txt-link-freetext" moz-do-not-send="true">paul.cisek@umontreal.ca</a>>
wrote:<o:p class=""></o:p></p>
</blockquote>
</div>
<blockquote style="margin-top: 5pt; margin-bottom:
5pt;" class="">
<div class="">
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<span style="font-family: Tahoma, sans-serif;" class=""></span><span style="font-size: 11pt;
font-family: Calibri, sans-serif;" class=""><o:p class=""></o:p></span></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
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.<o:p class=""></o:p></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<o:p class=""></o:p></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
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?<o:p class=""></o:p></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<o:p class=""></o:p></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
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?”<o:p class=""></o:p></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<o:p class=""></o:p></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
I think it’s not that machines have passed the
Turing Test, but rather that we failed it.<o:p class=""></o:p></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<o:p class=""></o:p></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
Paul Cisek<o:p class=""></o:p></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<span style="font-size: 11pt; font-family:
Calibri, sans-serif;" class="" lang="EN-CA"> </span><o:p class=""></o:p></div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<span style="font-size: 11pt; font-family:
Calibri, sans-serif;" class="" lang="EN-CA"> </span><o:p class=""></o:p></div>
<div class="">
<div style="border-style: solid none none;
border-top-width: 1pt; border-top-color:
rgb(225, 225, 225); padding: 3pt 0cm 0cm;" class="">
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<b class=""><span style="font-size: 11pt;
font-family: Calibri, sans-serif;" class="">From:</span></b><span style="font-size: 11pt; font-family:
Calibri, sans-serif;" class=""><span class="Apple-converted-space"> </span>Rothganger,
Fredrick <<a href="mailto:frothga@sandia.gov" style="color: rgb(5, 99, 193);
text-decoration: underline;" class="moz-txt-link-freetext" moz-do-not-send="true">frothga@sandia.gov</a>><span class="Apple-converted-space"> </span><br class="">
<b class="">Sent:</b><span class="Apple-converted-space"> </span>Thursday,
March 16, 2023 11:39 AM<br class="">
<b class="">To:</b><span class="Apple-converted-space"> </span><a href="mailto:connectionists@mailman.srv.cs.cmu.edu" style="color: rgb(5,
99, 193); text-decoration: underline;" class="moz-txt-link-freetext" moz-do-not-send="true">connectionists@mailman.srv.cs.cmu.edu</a><br class="">
<b class="">Subject:</b><span class="Apple-converted-space"> </span>Connectionists:
Can LLMs think?</span><o:p class=""></o:p></div>
</div>
</div>
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif;" class="">
<o:p class=""></o:p></div>
<div class="">
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif; background-color: white;" class="">
<span style="font-family: Calibri,
sans-serif;" class="">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.</span><o:p class=""></o:p></div>
</div>
<div class="">
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif; background-color: white;" class="">
<span style="font-family: Calibri,
sans-serif;" class=""> </span><o:p class=""></o:p></div>
</div>
<div class="">
<div style="margin: 0cm; font-size: 12pt;
font-family: "Times New Roman",
serif; background-color: white;" class="">
<span style="font-family: Calibri,
sans-serif;" class="">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.</span></div>
</div>
</div>
</blockquote>
</div>
</div>
</blockquote>
</div>
<br class="">
</div>
</blockquote>
</blockquote>
<br>
</div></blockquote></body></html>