I know this conversation has drifted quite a bit.... but I wanted to point out that if I was a weary lecturer teaching 6 classes a semester, who was thrilled to get anything with complete sentences and a vague semblance of thought, the chat bot gets an A on its responses.
If it is in one of the advanced seminars I used to teach, where there were a manageable number of students, and I'm was really reading the papers to grade them.... well... the chat bot's responses might still garner a passing grade, but not much better than that. This is clearly a "I quickly scanned the internet" level of response. Odds are that if I was in a cranky mood, and fed those responses into a plagiarism catcher, large chunks of it would be flagged. I wish I still had access to one, so I could check. And that assumes I asked the types of questions used as prompts here (which I typically wouldn't), instead of questions that required demonstration of deeper analysis/engagement with the text. The big problem with these bots, from the perspective of a professor, is that they provide poor students access to the same type of help that was always available to rich students via their peers, and which have been available to the upper-middle class for a while now via various websites (namely, having someone else improvise a passable essay for you to turn in). Because the profession has long discounted making students do real intellectual work, and then grading that work seriously, the chat bots pose a serious problem. <echar...@american.edu> On Tue, Feb 28, 2023 at 5:23 PM Jochen Fromm <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://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/
