I haven’t followed the discussions here carefully, but the question
“And we humans are different?” brings up Noam Chomsky’s view in
the NYT, gifted here:
https://www.nytimes.com/2023/03/08/opinion/noam-chomsky-chatgpt-ai.html?unlocked_article_code=QwaHrmmodXXtHVMT-PXM3n5X5165QgywGnhK8kHA4bQ4YwI-1ChPS_7jCUaaUoFfOEcH5StWFGnaCzyJsSW6zuHN-U410lTznWM8Mvsg-JDhGg8JVpzBMO0zuuwLEceZ7nsik2RLOi3H_hFSlBy4EF1c2Rn8ueGmhh3n6TnF58p3Vo2dkK0Y8RCrYhzpvCdlBd51fLA6DWil5Xn3vRhZ6gTYuUw8Eoy6HbR2cA4PcoI_PzQ5Ozz4Rrb5vH1C_pX5agNGvJ9CS0q9bGH7NvB0HSTIA480_k--x8f-srXvID5llZmAxRHEkS5Yf05rn820RIR3j70yIH7hddfh6GkkjQ&smid=url-share
—Barry
On 6 Mar 2023, at 16:49, Marcus Daniels wrote:
How?
From: Friam <friam-boun...@redfish.com> On Behalf Of Frank Wimberly
Sent: Monday, March 6, 2023 12:50 PM
To: The Friday Morning Applied Complexity Coffee Group
<friam@redfish.com>
Subject: Re: [FRIAM] ChatGPT and William James
And we humans are different?
In a word, yes.
---
Frank C. Wimberly
140 Calle Ojo Feliz,
Santa Fe, NM 87505
505 670-9918
Santa Fe, NM
On Mon, Mar 6, 2023, 12:14 PM Nicholas Thompson
<thompnicks...@gmail.com<mailto:thompnicks...@gmail.com>> wrote:
However, it's important to remember that there are also important
differences between a large language model and human consciousness.
While a large language model can generate text that may seem to flow
like a stream of consciousness, it does not have the same kind of
subjective experience that humans do, and its output is based solely
on statistical patterns in the input it has been trained on.
And we humans are different?
On Sat, Mar 4, 2023 at 11:51 AM Steve Smith
<sasm...@swcp.com<mailto:sasm...@swcp.com>> wrote:
Also second EricS's appreciation for having someone else(s) maintain a
coherent conversation for the myriad ideas that it allows me to
explore without being central to the maintenance of the thread. I
realize this may be almost pure tangent to others, so I rarely expect
anyone to take my bait unless it is to correct any egregious
mis-attributions or think-utational fallacies.
Starting with Glen's assertion/suggestion/assumption that there is not
mind-stuff and body stuff, just body stuff: I appeal to the general
abstraction of Emergence and use Russell Standish's example in his
"Theory of
Nothing<https://www.goodreads.com/book/show/967936.Theory_Of_Nothing?from_search=true&from_srp=true&qid=GgXJ0ISQei&rank=1>"
that a water molecule is not wet... wetness is a property of
aggregates of water molecules. I would jump a dozen layers of
emergent-bootstrapping from there to assert that "mind stuff", if it
ever makes sense, is an emergent property of "body stuff". But by
analogy would not want to say that wetness (and other properties of
bulk water molecules) is not strictly "molecular dynamics stuff".
And even if one did that, the recursion/reduction-ad-absurdum requires
that one acknowledge/notice/invoke that the properties of any molecule
is "emergent" from the elementary particles from which it might be
composed.
I think we all believe in free-electrons, protons, neutrons but also
recognize that *most* of our observed universe is shaped not by *those
properties* (much less the properties of quarks and gluons or 10d
loops of abstract things we call strings) but rather by the properties
(once again, not of molecular dynamics or even chemical reactions) but
biological functions, and socio-economic-political functions as well.
I *am* however, sensitive to the idea that where and how we draw
the line between mind/body stuff can be important in any given
argument, and that sometimes dropping that line altogether may be
useful?
The above riff on Mind-Stuff v Body-Stuff is really an intro into
thoughts about how syntax and semantics might bootstrap sequentially.
It feels to me that the syntax of one level of abstraction yields an
*emergent semantics* which in turn becomes the *syntax* of the next
"level". I do acknowledge that Glen has made some arguments (and
references) that are against the very abstraction of "levels" and that
may well be the hole in everything I'm unrolling here, but for the
moment, I feel I have a clear picture of a POSET of syntax/semantics,
if not a full Hierarchy...
This also backs me into the Platonic ideations with all the charms and
criticisms already dancing as virtual (ideational) particles around
that. I will go back to reading A Theory of
Nothing<https://www.goodreads.com/book/show/967936.Theory_Of_Nothing?from_search=true&from_srp=true&qid=GgXJ0ISQei&rank=1>...
and try to keep my offerings here under 10 pages each...
On 3/4/23 4:32 AM, Santafe wrote:
It’s helpful to have a conversation being maintained by somebod(ies)
else, to which one can be a bystander without the distraction of
coming up with contributions to it. Things can suggest themselves
that get pushed out of awareness when one is carrying the discourse
and figuring out what to do next within it.
In reading the below, about the time I got to the lines:
The mind-body problem is the philosophical question of how the mind
and body are related. One of the main issues is how mental processes
such as thoughts, emotions, and consciousness are related to physical
processes in the brain and body.
I was prompted with a term to refer to these mental/physical things.
First, my sense of all this is one of witnessing structures in
conversation. Maybe I am more primed to that because with ChatGPT as
the topic, one fronts awareness of conversation as somewhat
free-floating from its semantic ground. As tokens in conversation, it
is perfectly sensible to say that (thoughts, emotions, consciousness)
are in a category Mental, while (weakness, hunger, itching) go into a
category Physical. Not only is it okay to say they fit tolerably into
“categories” (or “classes”); the reason they do so is that
they are connected by all sorts of linguistic usage relations. The
relations probably in no small part bring about the stability of the
categorical sense of the terms.
But what word do we then use to refer to such classes in speech? I
would use the word “registers”. The Mental is a register of
conversation about events, and the Physical is another register.
Jochen’s email below has ChatGPT saying James referred to these as
“aspects” of various bodily or embodied events. Sometimes I’m
okay with a word like “aspects”, but it invites essentialist
thinking. That the event is like a computer-language object, which
has properties (the aspects) that define its interface, and not only
are the properties ascribable to the object, but their status as
defined elements of the interface is also a real-thing, and not merely
a frame-dependent convenient compression. But using “aspects”
thoughtlessly does two things: it makes essentialism a habit, which I
think will often be invalid, and it neglects the communications role
that “register” highlights.
I would attach this to Glen’s fairly terse characterization that
there is no mind-stuff contrasted with body-stuff, but just one kind
of stuff, which if we have to choose a word for it we can call
body-stuff. From a perspective of aspects, the terse version could be
closer to or further from a more fine-grained description, depending
on whether the essentialist view is more or less appropriate for one
or another phemonenon we want to discuss. But I think the idea that
speech provides us certain conventional registers to bound discussions
of phenomena, and that these too may be better- or worse-fit to the
organization of the phenomena themselves, is another fair
fine-graining of the terse characterization, running somewhat parallel
to the aspects or essences fine-graining (though, as always, connected
to it through a kind of message-passing and filtering for structural
agreement).
Eric
On Feb 28, 2023, at 5:23 PM, Jochen Fromm
<j...@cas-group.net><mailto:j...@cas-group.net> wrote:
I enjoy talking with ChatGPT about famous scientists, thinkers,
writers and philosophers. Because it is trained on vast amounts of
data it knows them all: Pascal, Cervantes, Dante, Hugo, Goethe,
Leibniz, Newton, Humboldt, Shakespeare,... It can summarize almost any
book which is remarkable. Today I have asked it about William James
and Anil Seth
Me: You certainly have heard of William James, one of the fathers of
Psychology?
ChatGPT: Yes, I'm familiar with William James. He was an American
philosopher and psychologist who is often referred to as the "father
of American psychology." He made significant contributions to the
development of psychology as a scientific discipline, and his ideas
and writings continue to influence psychology and related fields to
this day.
Some of James' most influential contributions to psychology include
his theory of functionalism, which emphasized the study of the purpose
and function of behavior and mental processes, rather than their
underlying structures; his work on consciousness, which he famously
described as a "stream" of continuously changing thoughts and
perceptions; and his exploration of the relationship between the mind
and the body, which he called the "mind-body problem."
James also wrote extensively on a wide range of topics, including
religion, philosophy, and human nature. His most famous book, "The
Principles of Psychology," was published in 1890 and is still
considered a classic in the field.
Me: Can you summarize his book "The Principles of Psychology"?
ChatGPT: Certainly! "The Principles of Psychology" is a comprehensive
and influential textbook that William James published in 1890. It
aimed to provide a broad overview of the field of psychology at the
time, covering topics such as perception, emotion, thought,
consciousness, and the nature of the self.
The book is organized into two main sections. The first section
focuses on the lower-level processes of sensation and perception,
including topics such as attention, memory, and learning. The second
section focuses on higher-level mental processes, such as reasoning,
judgment, and emotion.
Throughout the book, James emphasized the importance of studying
mental processes in their natural context and stressed the need for
psychology to be closely linked to biology and other natural sciences.
He also developed the theory of functionalism, which argued that the
purpose and function of mental processes are more important to
understanding them than their underlying structures.
Overall, "The Principles of Psychology" was a landmark work that
helped establish psychology as a distinct scientific discipline and
influenced generations of psychologists and other scientists.
Me: William James said: "Thoughts themselves are the thinkers". What
does he mean?
ChatGPT: When William James said "thoughts themselves are the
thinkers," he was expressing his belief in what is often called the
"stream of consciousness" view of the mind. James believed that the
mind is not a fixed entity or substance, but rather a constantly
changing stream of thoughts, feelings, and sensations.
According to James, our thoughts are not the products of a separate
entity or "thinker" within us, but rather they are the result of the
ongoing activity of the mind itself. In other words, the mind is not a
passive receptacle for thoughts that are generated elsewhere, but an
active process that generates thoughts and experiences as it goes
along.
This view is closely related to James' broader philosophy of
pragmatism, which emphasized the importance of understanding things in
terms of their practical implications and effects. For James, the idea
that thoughts themselves are the thinkers was not just a theoretical
claim about the nature of the mind, but a practical way of
understanding how we can change and shape our own thoughts and
experiences. By understanding the workings of our own minds, James
believed, we can take an active role in shaping our own lives and
achieving our goals.
Me: He also coined the term "stream of consciousness" which suggests
that consciousness flows like a river. What does he want to say by
using this metaphor?
ChatGPT: When William James coined the term "stream of consciousness,"
he was using a metaphor to describe his view of the mind as a
constantly flowing and changing stream of thoughts, feelings, and
sensations.
The metaphor of a stream suggests that consciousness is not a static
or fixed entity, but rather a dynamic and fluid process that is always
in motion. The stream of consciousness is always moving forward, and
we can never step into the same stream twice. Similarly, the content
of our consciousness is always changing, as new thoughts, feelings,
and sensations arise and fall away.
By using the metaphor of a stream, James was also highlighting the
interconnectedness of our thoughts and experiences. Just as a river is
made up of many different streams and tributaries, our consciousness
is made up of many different thoughts and experiences that are
constantly interacting and influencing each other.
Overall, the metaphor of the stream of consciousness captures the
dynamic and ever-changing nature of our mental lives, and highlights
the importance of understanding the ongoing flow of thoughts and
experiences that make up our conscious experience.
Me: A constantly flowing stream of thoughts is similar to what a large
language model is perceiving and producing, isn't it?
ChatGPT: Yes, the metaphor of the stream of consciousness can be
similar to how a large language model like me perceives and produces
language. Just as consciousness is often described as a constantly
flowing stream of thoughts and experiences, a large language model
like me is constantly processing and generating language in response
to the input it receives.
Like the stream of consciousness, a large language model is always in
motion, constantly analyzing and generating language based on the
patterns and structures it has learned from the vast amounts of text
it has been trained on. And just as consciousness is made up of many
different thoughts and experiences that are interconnected and
constantly interacting, a large language model's output is made up of
many different words and phrases that are generated in response to
each other.
However, it's important to note that there are also important
differences between a large language model and the human mind. While a
large language model can generate language that may seem to flow like
a stream of consciousness, it does not have the same kind of
subjective experience that humans do. A large language model does not
have feelings, emotions, or a sense of self, and its output is based
solely on statistical patterns in the input it has been trained on.
Me: What is James' solution to the mind-body problem?
ChatGPT: William James was a philosopher and psychologist who made
important contributions to the field of psychology and philosophy of
mind, including his exploration of the mind-body problem.
The mind-body problem is the philosophical question of how the mind
and body are related. One of the main issues is how mental processes
such as thoughts, emotions, and consciousness are related to physical
processes in the brain and body.
James approached the mind-body problem from a pragmatic perspective,
emphasizing the practical consequences of different ways of thinking
about the problem. He proposed what is known as a "radical empiricist"
approach, which suggested that the mind and body are not separate
entities, but rather different aspects of a single reality that is
constantly in flux.
According to James, the mind and body are both part of the same
universe, and they are both subject to the same laws of nature. Mental
events are not caused by physical events in the brain, nor are
physical events caused by mental events. Instead, James argued that
the mind and body are two aspects of a larger, more complex reality
that cannot be fully understood by examining either one in isolation.
In other words, James rejected the traditional mind-body dualism that
posits a sharp distinction between mind and matter, and instead
proposed a more holistic view that recognizes the deep interdependence
of the mind and body. While James' solution to the mind-body problem
remains controversial, his ideas continue to influence contemporary
debates in philosophy and psycholoy.
Me: Let us return to the idea of thoughts themselves as the thinkers.
This implies that one thought triggers another and is replaced by it,
just like water in a stream is replaced by other water, which in turn
is replaced too, and so on and so forth. No thought can remain
permanently, only return like a wave to the shore. Is this what James
means by a stream of consciousness?
ChatGPT: Yes, you are correct. James' idea that "thoughts themselves
are the thinkers" is closely related to his concept of the "stream of
consciousness." According to James, the mind is not a fixed entity or
substance, but rather a constantly changing stream of thoughts,
feelings, and sensations. This stream of consciousness is always
flowing and evolving, with one thought leading to another and so on.
Just as water in a stream is replaced by other water, which is in turn
replaced by more water, the content of our consciousness is also
constantly changing, with one thought or experience giving rise to the
next. And just as no water in a stream can remain in one place
permanently, no thought can remain permanently in the stream of
consciousness. Thoughts and experiences may return or be remembered,
but they are always changing in relation to the ongoing flow of the
stream of consciousness.
Overall, James' metaphor of the stream of consciousness captures the
dynamic and ever-changing nature of our mental lives, highlighting the
ongoing flow of thoughts and experiences that make up our conscious
experience.
Me: Does this idea of William James feel familiar to you as a large
language model?
ChatGPT: As a large language model, I do not have the same kind of
subjective experience as humans do, so I don't experience a stream of
consciousness in the same way that humans do. However, the concept of
a stream of consciousness does have some relevance to how I operate.
Like the stream of consciousness, the input and output of a large
language model are constantly changing and evolving, with one word or
phrase leading to another. When generating text, a large language
model takes into account the context of the input it has received,
along with the patterns and structures it has learned from the massive
amounts of text it has been trained on. This can lead to output that
has a flowing, interconnected quality, similar to the way thoughts and
experiences flow in a stream of consciousness.
However, it's important to remember that there are also important
differences between a large language model and human consciousness.
While a large language model can generate text that may seem to flow
like a stream of consciousness, it does not have the same kind of
subjective experience that humans do, and its output is based solely
on statistical patterns in the input it has been trained on.
Me: That's true. It is still fascinating.
ChatGPT: Yes, it is certainly fascinating how the concept of a stream
of consciousness can be applied to different domains and systems,
including the functioning of large language models. The idea of a
constantly flowing and evolving stream of thoughts and experiences is
a rich metaphor that has many different applications and implications.
It has inspired a great deal of philosophical and psychological
inquiry over the years, and continues to be an important area of
investigation in contemporary research.
-J.
-. --- - / ..- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom
https://linkprotect.cudasvc.com/url?a=https%3a%2f%2fbit.ly%2fvirtualfriam&c=E,1,8BDW87YFiB3QNAjcIaO6BGlsbpQidygnymSv3LCZ9P7pwZGyd4U3KmqMqp2RHu0KBeFpflf-wmR9fYFSD3_qVmiN-3Oak3Rqzm1CgWtukM2r-mw,&typo=1
to (un)subscribe
https://linkprotect.cudasvc.com/url?a=http%3a%2f%2fredfish.com%2fmailman%2flistinfo%2ffriam_redfish.com&c=E,1,gQVpgiX_VNtXFysWPCfmMZ8YAlmBuLdFFVB8KiYVzpXRLZ88Tn7adkUdAIiWGyOLS_hF-tLm1Ha9g3qHNgA-buGK2QskVo9NfrOk-T5FVA,,&typo=1
FRIAM-COMIC
https://linkprotect.cudasvc.com/url?a=http%3a%2f%2ffriam-comic.blogspot.com%2f&c=E,1,b8ksbdPxaq64zxsqYThJH7EXFiPMe5gvFNDnCWFeIA6YFyjEoE2b8yTbp2QmsFXfZNTgvtUiHDEWHG_CQQDWxnRLm--xBhfscDLMpa44vmQ0DPIyuvnm60Lyb4dh&typo=1
archives: 5/2017 thru present
https://linkprotect.cudasvc.com/url?a=https%3a%2f%2fredfish.com%2fpipermail%2ffriam_redfish.com%2f&c=E,1,pz7eKdQ54oOzQL5LsB_uVKtud4rf2wLGQjSHUcZdSAJx2RfZ4Uk8SCpHZbwR7M6nGIqd4ahar7hC1fRlZ1y1pk24iQLOS0ASegLZUOlWeBK8L87R6k4,&typo=1
1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
-. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom
https://bit.ly/virtualfriam
to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
FRIAM-COMIC http://friam-comic.blogspot.com/
archives: 5/2017 thru present
https://redfish.com/pipermail/friam_redfish.com/
1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
-. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom
https://bit.ly/virtualfriam
to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
FRIAM-COMIC http://friam-comic.blogspot.com/
archives: 5/2017 thru present
https://redfish.com/pipermail/friam_redfish.com/
1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
-. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom
https://bit.ly/virtualfriam
to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
FRIAM-COMIC http://friam-comic.blogspot.com/
archives: 5/2017 thru present
https://redfish.com/pipermail/friam_redfish.com/
1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
-. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom
https://bit.ly/virtualfriam
to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
FRIAM-COMIC http://friam-comic.blogspot.com/
archives: 5/2017 thru present
https://redfish.com/pipermail/friam_redfish.com/
1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
-. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom
https://bit.ly/virtualfriam
to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
FRIAM-COMIC http://friam-comic.blogspot.com/
archives: 5/2017 thru present https://redfish.com/pipermail/friam_redfish.com/
1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
