Monthly Archives: August 2023

chatGPT4, chatGPT4 - Wikipedia, chatGPT4 empirical science, chatGPT4 philosophy of science, chatGPT4 science, chatGPT4 scientific

CONTINUE EXPERIMENT WITH CHATGPT4: Science, Empirical Science, Philosophy of Science

Author: Gerd Doeben-Henisch

Email: info@uffmm.org

Time: Aug 31, 2023 – Aug 31, 2023 (10:03h CET)

CONTEXT

This text belongs to a series of experiments with chatGPT4. While there exist meanwhile some experiments demonstrating the low quality of chatGPT4 in many qualitative tests [1], the author of this texts wants to check the ability of the chatGPT4 software in reproducing man-like behavior associated with the production and reception of texts on a higher level. I started this series with a first post here[2] and a second post here.[3]

SUMMARY SO FAR, APPROVED BY chatGPT4

Author

In our yesterday dialogue you gave me many answers. Here a small selection of these: (1) You cannot read a book like a human person, (2) Your database is based on a subset of documents until the year 2021, (3) You don’t “learn” in the same way humans do, (4) You don’t directly cite individual sources in your responses. Instead, your answers are generated based on patterns in the data you have been trained on, (5) Individual responses from you aren’t precisely replicable, (6) You can’t directly attribute your statements to specific sources like a scholarly article or a book. This is indeed a limitation if you’re considering the output as a “scientific description”, (7) The specifics of the training data or exact processes that lead to a particular response from you aren’t transparently available in each interaction. Is this correct?

ChatGPT

Yes, your summary of our previous dialogue is accurate based on the points you’ve listed:

  1. I cannot read a book in the same way a human does, meaning I don’t interpret or comprehend in the same manner.
  2. My knowledge is up to September 2021, which means that I might not be aware of events, advancements, or publications after that point.
  3. My “learning” is different from human learning. I don’t learn from new experiences or information after my last update. Instead, I generate responses based on patterns in the data I was trained on.
  4. I don’t cite individual sources in my responses. I provide information based on the patterns recognized during my training.
  5. Responses I give can vary slightly even if the same question is posed multiple times.
  6. I can’t directly attribute my statements to specific, individual sources.
  7. The specifics about my training data and the processes that determine my responses are not transparently provided in each interaction.

You’ve captured the essence of our prior conversation well. If you have further questions or need clarifications on any of these points, please let me know.

OVERVIEW OF NEW DIALOGUE: The Questions

  1. Is there a difference in the meanings of the expressions ‘Scientific Text’ and ‘Empirical Scientific Text’?
  2. What distinguishes a ‘scientific text’ from a ‘non-scientific text’?
  3. You mention that it’s important to note that the boundaries between “scientific” and “non-scientific” can sometimes blur, especially when it comes to disciplines like philosophy of science. How do you characterize ‘philosophy of science’?
  4. Considering the aim of ‘Philosophy of Science’: Which role plays the language used for the work of a philosopher of science?
  5. You are stating that ‘language’ plays a central role for science as well as for a philosopher of science. Thus, is it correct to state that ‘Philosophy of Science’ is talking ‘about’ Science?
  6. You state that “Philosophy of Science” stands in a meta-relation to science. Is this compatible with the statement, that a person A (a philosopher of science) is talking about another person B (a scientist) by looking to the behavior of the other person?
  7. You state that the relationship between the philosophy of science and science is multifaceted and cannot be entirely captured by comparing it to one person observing another’s behavior. From your statement I induce (1) that science is an activity realized by many individuals in parallel, a ‘population of scientists’. (2) This population of scientists is following certain commonly accepted ‘rules for science’. (3) The ‘written rules’ for science have some ‘meaning’ which is located ‘inside the scientists’.(4) It is this ‘shared meaning’ inside the scientists which enables a ‘behavior’ which commonly is qualified as ‘science work’. Is this correct?
  8. You are stating that philosophy of science doesn’t just observe the norms and practices of the population of scientists from a distance. It also critically examines, interrogates, and sometimes influences them. Would you agree with the following induced statements: (1) All members of the population of scientists are sharing a commonly accepted meaning associated with the written rules of science. (2) To understand the behavior of scientists one has to learn this shared meaning inside a scientist. (3) A philosopher of science talking ‘about’ the behavior of a population of scientists has to know this shared meaning inside the scientists to be able to describe the scientific behavior. (4) Before ‘reflecting about’ the scientific behavior one has to ‘understand’ it by knowing the shared meanings.

Continuing the Dialogue

Author

Is there a difference in the meanings of the expressions ‘Scientific Text’ and ‘Empirical Scientific Text’?

ChatGPT

Yes, there is a distinction between the terms “scientific text” and “empirical scientific text.”

  1. Scientific Text: This is a broad term that refers to any text discussing scientific topics, concepts, theories, and so on. It can encompass a wide variety of writings, from theoretical papers, reviews, and hypotheses to detailed experiments and observations. The main characteristic is that it pertains to or is relevant to science. It could be based on observations, mathematical models, theoretical principles, or any other scientific method.
  2. Empirical Scientific Text: This term is more specific. “Empirical” refers to knowledge derived from observation or experiment, i.e., it’s based on actual, direct observations or experiments in the real world. So, an empirical scientific text is a subset of scientific text that specifically deals with data collected from experiments or observations. It doesn’t rely solely on theoretical arguments or models but provides evidence from real-world data.

In simpler terms, while all empirical scientific texts are scientific texts, not all scientific texts are empirical. Some might be theoretical, for example.

Author

What distinguishes a ‘scientific text’ from a ‘non-scientific text’?

ChatGPT

The distinction between a “scientific text” and a “non-scientific text” lies in the content, purpose, methodology, and structure of the writing. Here are some distinguishing features:

  1. Content:
    • Scientific Text: Deals with topics related to natural or social sciences such as biology, chemistry, physics, psychology, sociology, etc.
    • Non-scientific Text: Can deal with any subject, from literature and history to personal opinions or fictional narratives.
  2. Purpose:
    • Scientific Text: Primarily to communicate research findings, theories, methodologies, or review existing literature. It seeks to expand knowledge in a field, challenge existing notions, or validate/invalidate hypotheses.
    • Non-scientific Text: Can have various purposes including entertaining, informing, expressing opinions, narrating stories, etc., without adhering to the scientific method.
  3. Methodology:
    • Scientific Text: Adheres to the scientific method, which involves formulating hypotheses, conducting experiments or observations, analyzing data, and drawing conclusions.
    • Non-scientific Text: Does not necessarily follow any specific methodology, especially not the scientific method.
  4. Structure and Style:
    • Scientific Text: Typically has a structured format, often including sections like introduction, methodology, results, discussion, and conclusion. It uses precise and objective language.
    • Non-scientific Text: Can have a variety of structures and styles depending on the type of writing (e.g., essay, poem, opinion piece, novel). The language can be subjective, emotive, or descriptive.
  5. Evidence and Verification:
    • Scientific Text: Relies on empirical evidence, reproducibility, and peer review to validate claims.
    • Non-scientific Text: May not rely on empirical evidence and is often not subjected to peer review or validation in the same rigorous manner as scientific texts.
  6. Audience:
    • Scientific Text: Often written for other scientists, researchers, or professionals in the field, although there are also scientific texts intended for broader audiences.
    • Non-scientific Text: Can be aimed at the general public, specific interest groups, or any other audience.

That being said, it’s important to note that the boundaries between “scientific” and “non-scientific” can sometimes blur, especially when it comes to disciplines like philosophy of science or when scientific concepts are discussed in popular literature. Moreover, some non-scientific texts, like historical analyses, may incorporate rigorous methodologies and provide evidence for their claims even if they don’t adhere strictly to the scientific method.

Author

You mention that it’s important to note that the boundaries between “scientific” and “non-scientific” can sometimes blur, especially when it comes to disciplines like philosophy of science. How do you characterize ‘philosophy of science’?

ChatGPT

Certainly, the philosophy of science is a fascinating discipline that delves into the foundational, methodological, and epistemological questions surrounding science. Here’s a more detailed characterization:

  1. Nature and Purpose:
    • Philosophy of science aims to understand the nature and purpose of scientific activity. It raises questions about what science is, what its objectives are, and what makes scientific activity distinctive from other human pursuits.
  2. Foundational Issues:
    • Philosophers of science explore the basic concepts and principles underlying scientific theories and practices. For example, they might investigate the nature of causation, the concept of a scientific law, or the interpretation of probability in statistical mechanics.
  3. Methodological Examination:
    • It studies the methods used in science, asking questions like: What is the scientific method? Are there universal methods that apply to all scientific disciplines, or do methods differ across fields? How do scientists confirm or falsify theories?
  4. Theory and Observation:
    • One central concern in the philosophy of science is the relationship between theory and observation. Philosophers examine how theories are tested, how they relate to observational data, and the problem of underdetermination (the idea that data can be explained by multiple, sometimes incompatible, theories).
  5. Scientific Explanation:
    • What does it mean to explain a phenomenon scientifically? Philosophers of science analyze different models of explanation, like deductive-nomological, probabilistic, or causal-mechanistic explanations.
  6. Scientific Change and Progress:
    • Philosophers investigate how scientific theories evolve over time, what constitutes scientific progress, and how paradigm shifts (a term popularized by Thomas Kuhn) occur in scientific disciplines.
  7. Realism and Anti-realism:
    • This debate concerns the nature of scientific theories and their relationship to the world. Realists believe that scientific theories aim to describe the world as it truly is, while anti-realists believe that theories are just tools for prediction and may not necessarily reveal the true nature of reality.
  8. Values in Science:
    • Philosophy of science also studies the role of values, both epistemic (related to knowledge) and ethical, in scientific practice. For instance, it may question how societal values influence scientific research or how objective science can truly be.
  9. Interdisciplinary Concerns:
    • The philosophy of science often intersects with other disciplines, such as the history of science, sociology of science, and cognitive science, to provide a holistic understanding of scientific practices.

Philosophy of science doesn’t just deal with abstract or purely theoretical concerns. Many of its insights have practical implications for how science is conducted, taught, funded, and communicated. By scrutinizing the foundational aspects of scientific activity, the philosophy of science enriches our understanding and appreciation of the scientific endeavor.

Author

Considering the aim of ‘Philosophy of Science’: Which role plays the language used for the work of a philosopher of science?

ChatGPT

The role of language in the philosophy of science is crucial and multifaceted. Philosophers of science, like philosophers in other areas, are deeply concerned with the nuances, implications, and limitations of language. Here’s why language plays a central role:

  1. Precision in Definition: The clarity of philosophical arguments often hinges on the precise definition of terms. Philosophers of science seek to define terms like “causation,” “law,” “theory,” “model,” “proof,” and “evidence” in ways that capture their use in scientific practice and distinguish them from other, sometimes colloquial, meanings.
  2. Analysis of Theoretical Constructs: Many concepts in science, like “atom,” “gene,” or “black hole,” are theoretical constructs. Philosophers of science investigate the language that scientists use to describe these constructs and how that language relates to observable phenomena.
  3. Interpretation of Models and Theories: Philosophers analyze the language of scientific models and theories to understand their structure, implications, and limitations. For instance, they might scrutinize how particular terms are used metaphorically or analogically.
  4. Examining Paradigms and Frameworks: As mentioned with Thomas Kuhn’s concept of paradigms, the language and conceptual framework of one scientific paradigm might differ radically from another. Philosophers of science explore these differences and their implications.
  5. Exploring Linguistic Structures: Some philosophers, influenced by linguistic philosophy or semiotics, delve into the deeper structures of scientific language. They might ask how the language of a scientific discipline shapes and is shaped by its practices.
  6. Addressing Ambiguities: Philosophers of science highlight and address ambiguities in scientific language, clarifying potential misunderstandings or misinterpretations.
  7. Role of Metaphor and Analogy: Science frequently uses metaphors and analogies to describe complex phenomena (e.g., the “solar system model” of the atom or “genetic code”). Philosophers of science examine the strengths, limitations, and potential pitfalls of these linguistic tools.
  8. Ethical and Societal Implications: Language doesn’t just describe the world; it also shapes how we perceive and interact with it. Philosophers of science may critique the language of science for its ethical or societal implications, such as whether it inadvertently reinforces certain biases or worldviews.
  9. Communication and Pedagogy: Language is the primary medium through which scientific knowledge is communicated, both within the scientific community and to the public. Philosophers might investigate how language can facilitate or hinder scientific understanding, especially in educational contexts.

In summary, for philosophers of science, language is not just a neutral tool but a complex system that influences, and is influenced by, scientific thought and practice. Analyzing and critiquing the language of science helps illuminate the foundational assumptions, methodologies, and implications of scientific activity.

Author

You are stating that ‘language’ plays a central role for science as well as for a philosopher of science. Thus, is it correct to state that ‘Philosophy of Science’ is talking ‘about’ Science?

ChatGPT

Yes, that’s a concise and accurate way to put it. The “Philosophy of Science” talks ‘about’ science. It reflects on, analyzes, and critiques the foundational, methodological, epistemological, and sometimes ethical aspects of scientific activity. Philosophers of science are interested in understanding what scientists do, how they do it, why they do it in that way, and what it means to produce scientific knowledge.

In other words, while scientists are primarily concerned with investigating and understanding the natural world (or human societies, in the case of social sciences), philosophers of science are more concerned with investigating and understanding the processes, methodologies, and frameworks that scientists use in their investigations.

So, “Philosophy of Science” stands in a meta-relation to science. Just as meta-ethics in philosophy is concerned with the nature of ethical statements rather than the ethical statements themselves, the philosophy of science is concerned with the nature, methodology, and implications of science rather than the specific scientific facts or theories.

Author

You state that “Philosophy of Science” stands in a meta-relation to science. Is this compatible with the statement, that a person A (a philosopher of science) is talking about another person B (a scientist) by looking to the behavior of the other person?

ChatGPT

The analogy of a person A (a philosopher of science) talking about another person B (a scientist) by observing B’s behavior can capture some aspects of the meta-relation between philosophy of science and science, but with certain caveats.

In this analogy:

  • Observation of Behavior: The philosopher of science (Person A) observes, reflects upon, and tries to understand the methodologies, assumptions, and structures that underpin the work of the scientist (Person B). This can be likened to observing the “behavior” of the scientist.
  • Interpretation and Analysis: Just as someone might analyze and interpret a person’s behavior to understand underlying motivations, thoughts, or cultural influences, the philosopher of science analyzes the “behavior” of science to uncover its foundational assumptions, methodologies, and epistemological commitments.

However, the analogy has its limitations:

  1. Beyond Individual Behavior: While the analogy implies observing the actions of an individual (Person B), the philosophy of science often deals with broader structures, paradigms, and historical shifts in scientific thinking, not just the practices of individual scientists.
  2. Engagement with Content: Philosophers of science don’t just observe the “behavior” of scientists. They often engage deeply with the actual content of scientific theories and models, trying to understand and interpret them. It’s not merely an external observation.
  3. Reciprocal Influence: In some cases, the philosophy of science has influenced the way scientists think about their own work. For instance, philosophical discussions about the nature of time, space, or causality might impact theoretical physics. This reciprocal influence doesn’t fit neatly into the analogy.

In summary, while the analogy can serve as a starting point to grasp the meta-relation, the relationship between the philosophy of science and science is multifaceted and cannot be entirely captured by comparing it to one person observing another’s behavior.

Author

You state that the relationship between the philosophy of science and science is multifaceted and cannot be entirely captured by comparing it to one person observing another’s behavior. From your statement I induce (1) that science is an activity realized by many individuals in parallel, a ‘population of scientists’. (2) This population of scientists is following certain commonly accepted ‘rules for science’. (3) The ‘written rules’ for science have some ‘meaning’ which is located ‘inside the scientists’.(4) It is this ‘shared meaning’ inside the scientists which enables a ‘behavior’ which commonly is qualified as ‘science work’. Is this correct?

ChatGPT

Your inferences capture important aspects of the relationship between science, scientists, and the philosophy of science, with some qualifications. Let’s review your points:

  1. Population of Scientists: Yes, science is indeed an activity carried out by many individuals, often collaboratively. These individuals collectively form the scientific community or a “population of scientists.”
  2. Rules for Science: Scientists, especially within specific disciplines, generally adhere to a set of methodologies, standards, and norms—often referred to as the “scientific method” or the ethos of science. These can include practices such as peer review, empirical testing, reproducibility, and falsifiability, among others. These “rules” may vary across disciplines but serve to maintain the rigor and credibility of scientific research.
  3. Meaning Inside Scientists: It’s a nuanced point. While there are “written rules” or guidelines for conducting science, the internalization of these rules goes beyond just written directives. Scientists undergo extensive training and socialization, learning not just the overt rules but also the tacit knowledge, values, and norms of their discipline. This internalized understanding guides their scientific practice.
  4. Shared Meaning & Behavior: The shared understanding and internalization of the ethos of science by the scientific community do indeed result in behaviors characteristic of scientific inquiry. This shared foundation helps in ensuring consistency, rigor, and mutual intelligibility in scientific work.

However, it’s also important to note:

  • The evolution of scientific norms and practices: The “rules” and norms of science aren’t static; they evolve over time as science itself progresses and as the broader societal context changes.
  • Diversity within science: Different scientific disciplines might have variations in their methodologies, standards, and practices. For instance, methods in particle physics can differ considerably from ethnographic methods in cultural anthropology, though both are scientific.
  • Role of philosophy of science: The philosophy of science doesn’t just observe these norms and practices from a distance. It critically examines, interrogates, and sometimes influences them. Philosophers of science may raise questions about the nature of evidence, the interpretation of statistical methods, the structure of scientific theories, or the ethical implications of certain scientific practices.

In summary, your inferences offer a structured way of understanding the practice of science and its underlying shared ethos, with the aforementioned nuances and complexities taken into account.

Author

You are stating that philosophy of science doesn’t just observe the norms and practices of the population of scientists from a distance. It also critically examines, interrogates, and sometimes influences them. Would you agree with the following induced statements: (1) All members of the population of scientists are sharing a commonly accepted meaning associated with the written rules of science. (2) To understand the behavior of scientists one has to learn this shared meaning inside a scientist. (3) A philosopher of science talking ‘about’ the behavior of a population of scientists has to know this shared meaning inside the scientists to be able to describe the scientific behavior. (4) Before ‘reflecting about’ the scientific behavior one has to ‘understand’ it by knowing the shared meanings.

ChatGPT

Your inferences touch on core ideas related to the nature of scientific practices and the approach of philosophy of science. Let’s review each of your points:

  1. Shared Meaning Among Scientists: While it’s generally true that there’s a commonly accepted ethos or set of standards within scientific disciplines, it’s essential to remember that “shared meaning” isn’t necessarily uniform. Different scientists, based on their training, specific subfields, cultural backgrounds, and individual experiences, might have variations in their interpretations and applications of these rules. However, there’s indeed a foundational consensus that allows for mutual intelligibility and collaboration within the scientific community.
  2. Understanding the Shared Meaning: To understand the behavior of scientists fully, one would benefit from understanding this shared ethos and the underlying tacit knowledge. This includes both formal methodologies and the more subtle, unwritten norms and values of scientific practice.
  3. Philosopher’s Knowledge of Shared Meaning: Yes, for a philosopher of science to offer a meaningful critique, analysis, or description of scientific practices, they need to be familiar with the shared meanings, methods, and values of scientists. However, philosophers also bring an external perspective that can question assumptions and probe deeper into the foundations of these shared meanings.
  4. Understanding Before Reflecting: In general, understanding is a prerequisite for meaningful reflection. To critically analyze or reflect upon scientific practices, one first needs a foundational understanding of those practices. This is akin to the idea that one must understand a game’s rules and objectives before commenting on strategies or critiquing its design.

However, a few considerations:

  • Dynamism of Science: It’s important to recognize that the shared meanings and practices of science aren’t static. They evolve with new discoveries, technological advancements, and shifts in the broader societal context. Philosophers of science not only reflect on current practices but also on these evolutionary changes.
  • Interdisciplinary Nature: The philosophy of science often interacts with other disciplines, such as sociology of science, history of science, or cognitive science. These interdisciplinary engagements enrich the understanding and reflection on scientific practices.
  • Role of Outsider’s Perspective: While understanding from within is crucial, sometimes an outsider or a more distanced perspective can provide insights that might be less obvious to those deeply embedded within a discipline. Philosophers of science can provide this vantage point, revealing biases, assumptions, or unexplored avenues.

In summary, your inferences capture significant aspects of how philosophy of science engages with the practices and underlying meanings of science. The relationship is one of understanding, reflection, critique, and, sometimes, influence.

COMMENTS

[1] There was a conference at the Technical University of Darmstadt with the title “KI – Text und Geltung. Wie verändern KI-Textgeneratoren wissenschaftliche Diskurse?” (Translated: AI – Text and Validity. How do AI text generators change scientific discourses? )., https://zevedi.de/en/topics/ki-text-2/ . One lecturer Thomas Arnold, gave a speech entitled “Herausforderungen in der Forschung: Mangelnde Reproduzierbarkeit und Erklärbarkeit” (Translated: Challenges in research: lack of reproducibility and explainability), which will be published by de Gruyter at the end of 2023/ or the beginning of 2024.

[2] Gerd Doeben-Henisch, Aug 28, 2023 : STATE CHANGE FROM NON-WRITING TO WRITING. WORKING WITH CHATGPT4 IN PARALLEL. AN EXPLORATION, https://www.uffmm.org/2023/08/28/state-change-from-non-writing-to-writing-working-with-chatgpt4-in-parallel/

[3] Gerd Doeben-Henisch, Aug 30, 2023: READING A BOOK, LEARNING, BEING SCIENTIFIC, WIKIPEDIA. A dialogue with chatGPT4 bringing you ‘back to earth’ : https://www.uffmm.org/2023/08/30/reading-a-book-learning-being-scientific-wikipedia-a-dialogue-with-chatgpt4-bringing-you-back-to-earth/

Knowledge

READING A BOOK, LEARNING, BEING SCIENTIFIC, WIKIPEDIA. A dialogue with chatGPT4 bringing you ‘back to earth’

Autor: Gerd Doeben-Henisch

Aug 30, 2023 – Aug 30, 2023

Email: info@uffmm.org

CONTEXT

This text belongs to a series of experiments with chatGPT4. While there exist meanwhile some experiments demonstrating the low quality of chatGPT4 in many qualitative tests [1], the author of this texts wants to check the ability of the chatGPT4 software in reproducing man-like behavior associated with the production and reception of texts on a higher level. I started this series with a first post here.[2]

SUMMARY

In the following series of dialogues with chatGPT4 the software stated in the beginning that it cannot read a book like a human person. Asking for a special book with the title “Das Experiment sind wir” by the author Christian Stöcker? the software answered, that it doesn’t know the book. Then I tried to ask the software, whether it can nevertheless ‘learn’ something based on the documents given to the software until the year 2021. The answer was quite revealing: “No, I don’t “learn” in the same way humans do. I don’t actively process new information, form new connections, or change my understanding over time. Instead, my responses are based on patterns in the data I was trained on. My knowledge is static and doesn’t update with new information unless a new version of me is trained by OpenAI with more recent data.” I didn’t give up to understand what the software is able to do if not ‘reading a book’ or to ‘learn’. I asked: “What can you extract from your text base related to the question what can happen in the head of people if they read a book?” I got a list of general properties summarized from different source (without mentioning these sources). I continued asking the software not about the leaning inside itself but what the software knows about the learning inside humans persons reading a book: “How do you describe the process of learning in human persons while reading a book?” The software did mention some aspects which have to be considered while a human person reads a book. But this gives only some ‘static view’ of the structure being active in the process of reading. More interesting is perhaps a ‘dynamic aspect’ of reading a book which can be circumscribed as ‘learning’: which kinds of changing are typical for human persons while reading a book? The software gives a detailed breakdown of the learning process in human persons while reading, but again these are statements without any ‘backing up’, no sources,no contexts, but in the everyday world — especially in science –, it is necessary that a reader can get the knowledge about the sources of statements claiming to be serious: are the presented facts only ‘fakes’, purely wrong, or are there serious people with serious methods of measurement which can provide some certainty that these facts are really ‘true’? Then the author did ask the software “Your answer consist of many interesting facts. Is it possible to clarify the sources you are using for these statements?” The answer again was very simple: “I’m glad you found the information interesting. My design is based on information from a wide range of books, articles, and other educational resources up to my last update in September 2021. However, I don’t directly cite individual sources in my responses. Instead, my answers are generated based on patterns in the data I was trained on.” Because it is known that wikipedia encyclopedia provides always explicit sources for the texts the author asked directly: Do you know the textbase wikipedia? Clearly, the chatGPT4 knows Wikipedia; besides many positive remarks it answered: “The structure of Wikipedia articles, with their citations, can serve as a good starting point for research on a topic. One can follow the cited sources at the bottom of each article to get more detailed or primary information on a subject.” This sounds quite good for Wikipedia. Thus it is interesting how chatGPT4 compares itself to Wikipedia: Question: “Wikipedia has cited sources at the bottom of each article. Does this mean that wikipedia is more trustful as you?” chatGPT4 doesn’t give a clear answer; it summarizes points for Wikipedia and itself, but leaves the question open. Thus the author continues asking for a more ‘general criterion’, which should be valid for both Wikipedia and chatGPT4: “Which criteria do you know for a good scientific description? ” As usual chatGPT4 gives a long list of criteria . the author asks back “Your overview about criteria for a scientific description includes terms like ‘Replicability’, ‘Citing Sources’, and ‘Transparency’. From the preceding self-description of you it is not easily to see, whether these criteria can also applied to the output of chatGPT4.” The answer chatGPT4 gives makes itself nearly unusable for any serious scientific work. Yes, you can use chatGPT4 for some first general information, but without knowing more by yourself, you are really lost. It is surely quite more fruitful to check Wikipedia directly and using the the sources there for further investigations.

Reading a book

I started spontaneously to talk with chatGPT4 about a book from Christian Ströcker with the title “Das Experiment sind wir”, published 2020.

Here is the dialogue:

Author:

Can you read a book?

ChatGPT

I don’t “read” books in the same way humans do. Instead, I was trained on vast amounts of text data, which includes information from books, articles, websites, and other written sources up to my last update in September 2021.

You can ask me about the content, summaries, themes, and other information from many books, especially those that are well-known or that were published before my last training cut-off. If the book was published after September 2021 or is particularly obscure, I might not have information about it.

If you have a particular book or topic in mind, feel free to ask, and I’ll do my best to provide relevant information!

Author:

What can you say about the book entitled “Das Experiment sind wir” by the author Christian Stöcker?

ChatGPT

As of my last update in September 2021, “Das Experiment sind wir” by Christian Stöcker hasn’t been one of the primary sources I was trained on. However, Christian Stöcker is known as a journalist and professor in the field of digital communication.

If “Das Experiment sind wir” was published or gained significant attention after my last update, I may not have detailed information about its content, themes, or specific insights.

For a detailed overview or analysis of the book, I would recommend reading reviews, summaries, or author interviews, or accessing the book directly. If you have other questions or need information on a related topic, I’m here to help!

RESULT

OK, chatGPT4 doesn’t know this book. This is OK, even a high performance System can not know everything.

But interesting is his confession, that chatGPT4 can not read a book as a human person would do. In this sense chatGPT4 is not a ‘typical reader’ but — as wee indeed know — a piece of software, managed by human persons, which decide, which kinds of texts chatGPT4 has to ‘store’ in his memories and which are the basis for hier ‘algorithmic processing’.

But there is left the question whether chatGBT4 at least can learn by its own starting with the text base given to him.

Author

Thus if you have a text base as a point of reference, are you able to learn in some sense by your own?

ChatGPT

No, I don’t “learn” in the same way humans do. I don’t actively process new information, form new connections, or change my understanding over time. Instead, my responses are based on patterns in the data I was trained on. My knowledge is static and doesn’t update with new information unless a new version of me is trained by OpenAI with more recent data.

Here’s an analogy: Imagine an extremely comprehensive book. This book can answer a vast array of questions based on its contents, but it can’t write new chapters or update its pages on its own. In a similar manner, I can generate answers based on the data I was trained on, but I can’t independently update that data or “learn” new things.

So, while I can generate responses based on a broad range of existing knowledge, I can’t assimilate or understand new information or events after my last training cut-off in September 2021.

RESULT

As expected, chatGBT4 can not learn as we humans can learn. To generate summaries can be of some help, but this can not replace ‘true learning’.

But let us stay with the topic of ‘reading a book’:

Author

What can you extract from your text base related to the question what can happen in the head of people if they read a book?

ChatGPT

Reading a book can have various cognitive, emotional, and psychological effects on individuals. Here are some insights based on literature, cognitive science, and psychological studies up to my last training cut-off:

  1. Cognitive Stimulation: Engaging with the written word can stimulate the brain. Studies have suggested that mental stimulation can slow the progress (or possibly even prevent) Alzheimer’s and dementia, as keeping your brain active and engaged prevents it from losing power.
  2. Mental Escape: For many, reading a book can act as an escape from the real world. Immersing oneself in a different world, whether it’s a fantasy realm or an historical setting, provides a break from everyday stressors.
  3. Increased Knowledge: Naturally, books inform and educate. This builds a knowledge base that can be applied in real-life situations.
  4. Vocabulary Expansion: Reading regularly can expand one’s vocabulary more than direct teaching or verbal communications.
  5. Improved Focus and Concentration: Unlike skimming short web articles or watching quick videos, reading a book requires a longer attention span and can help improve one’s focus and concentration.
  6. Stress Reduction: A well-written novel or non-fiction book can transport the reader to other realms, distracting them and helping them to de-stress more effectively than other methods.
  7. Improved Analytical Skills: Engaging with complex narratives and plots can help readers improve their analytical skills as they ponder plot developments and character motivations.
  8. Empathy Development: Reading fiction, in particular, allows readers to live vicariously through characters, experiencing a vast range of emotions and situations. This can help in developing a deeper understanding and empathy for others.
  9. Mental Tranquility: Reading subjects like poetry or certain religious texts can provide tranquility, help lower blood pressure, and reduce stress.
  10. Memory Improvement: Reading involves remembering various characters, their backgrounds, histories, and nuances. This can create new brain pathways and strengthen existing ones.
  11. Entertainment: Of course, one of the primary reasons people read is for entertainment. A good story can be incredibly engaging, offering hours of enjoyment.

It’s worth noting that the impact of reading can vary based on the type of book (e.g., fiction vs. non-fiction), the style of writing, the personal experiences and preferences of the reader, and the context in which they’re reading.

RESULT

chatGPT4 mentions some aspects which have to be considered while a human person reads a book. This gives some ‘static view’ of the structure being active in the process of reading.

More interesting is perhaps a ‘dynamic aspect’ of reading a book which can be circumscribed as ‘learning’: which kinds of changing are typical for human persons while reading a book?

Author

How do you describe the process of learning in human persons while reading a book?

ChatGPT

Reading a book is a complex cognitive process that involves multiple levels of mental engagement and comprehension. When a person reads, several processes related to learning occur simultaneously. Here’s a detailed breakdown of the learning process while reading:

  1. Perceptual Processing: This is the basic recognition of words and letters. As your eyes scan a page, the visual cortex interprets the shapes of letters and groups of letters as words. This process becomes automatic with practice and training.
  2. Decoding: This involves understanding the phonetic value of words, which is especially crucial for unfamiliar terms or names. This skill is emphasized heavily in early reading education when children sound out words.
  3. Semantic Processing: Once the words are recognized, the brain works to understand their meaning. This involves linking the words to their associated concepts in the brain.
  4. Syntax and Grammar Processing: The brain understands the structure of sentences and how words relate to each other, determining the relationships among verbs, nouns, adjectives, etc.
  5. Working Memory: This is essential for maintaining an understanding of a sentence or paragraph. As you read, you keep the beginning of a sentence in mind as you progress to the end, allowing you to grasp the entire concept.
  6. Building Connections: Learning often involves connecting new information with prior knowledge. When reading, you constantly relate what you are consuming to what you already know, which can deepen comprehension.
  7. Critical Thinking: Beyond just understanding the content, readers often evaluate, analyze, and critique what they’re reading. They may ask themselves if they agree with the author, if the information is credible, or how it relates to other things they know.
  8. Visualization: Good readers often create mental images of what they are reading. This is especially true for narrative texts where imagining scenes, characters, or events can enhance comprehension.
  9. Emotional Engagement: The content in books can evoke emotions. Whether it’s a novel that tugs at the heartstrings or a non-fiction book that arouses anger or passion about a topic, emotional engagement can increase retention and internalization of content.
  10. Metacognition: This involves thinking about one’s own thinking. Effective readers often monitor their understanding as they read, recognizing when they’re confused and employing strategies to improve comprehension.
  11. Retention & Long-Term Memory: Once the book is done, the process of shifting information from working memory to long-term memory begins. Repetition, discussion, and application of knowledge can aid this transfer.
  12. Application: The ultimate goal of learning is often to apply knowledge. After reading, a person may take actions, make decisions, or change beliefs based on what they’ve learned.

It’s important to note that everyone’s reading process might be a bit different. Some people naturally visualize more, while others might focus on critical analysis. Additionally, background knowledge, context, and the reader’s purpose (e.g., reading for pleasure versus studying for an exam) can influence how these processes unfold.

RESULT

chatGPT4 presents some facts responding to the question which are — as such — really interesting, but in the everyday world especially in science, it is necessary that a reader can get the knowledge about the sources of statements claiming to be serious: are the presented facts only ‘fakes’, purely wrong, or are there serious people with serious methods of measurement which can provide some certainty that these facts are really ‘true’?

Let us ask chatGPT4:

Author

Your answer consist of many interesting facts. Is it possible to clarify the sources you are using for these statements?

ChatGPT

I’m glad you found the information interesting. My design is based on information from a wide range of books, articles, and other educational resources up to my last update in September 2021. However, I don’t directly cite individual sources in my responses. Instead, my answers are generated based on patterns in the data I was trained on.

The steps and processes I outlined for learning while reading a book are based on widely accepted theories and research in the fields of cognitive psychology, education, and linguistics. If you’re interested in diving deeper into these topics, you might consider exploring:

  1. Cognitive psychology textbooks: These delve into the processes of perception, working memory, long-term memory, and more.
  2. Reading and literacy research: Scholars in this field have conducted in-depth studies on the processes of decoding, comprehension, and the strategies good readers use.
  3. Educational psychology: This field explores topics related to learning, including metacognition, critical thinking, and the application of knowledge.

If you’d like specific book or article recommendations, or more in-depth explanations on any of these topics, I can certainly provide them.

Author

Do you know the textbase wikipedia?

ChatGPT

Yes, I’m familiar with Wikipedia. Wikipedia is a free online encyclopedia that is collaboratively edited by volunteers from around the world. It’s one of the most visited websites globally and provides information on a vast array of topics.

Wikipedia is known for its “wiki” nature, which means that almost any article can be edited by any user with internet access. This collaborative approach has made Wikipedia a rich and ever-evolving source of information. However, because of this open-editing system, it’s always a good idea to verify critical information from Wikipedia with other reliable sources.

The structure of Wikipedia articles, with their citations, can serve as a good starting point for research on a topic. One can follow the cited sources at the bottom of each article to get more detailed or primary information on a subject.

Would you like more information or have a specific question related to Wikipedia?

RESULT

chatGPT4 knows wikipedia and gives a quite fair description of wikipedia (probably the English version). Of interest is how chatGPT4 describes the characteristic differences with wikipedia.

Author

Wikipedia has cited sources at the bottom of each article. Does this mean that wikipedia is more trustful as you?

ChatGPT

Wikipedia and I serve different purposes, and the trustworthiness of information from either source depends on the context and specific use-case.

Advantages of Wikipedia:

  1. Citations: Wikipedia articles often have extensive lists of references, which allow readers to trace back the origin of specific pieces of information. This provides a level of transparency.
  2. Collaboration: Wikipedia is collectively edited by a vast number of individuals, which can mean many eyes reviewing and refining content.
  3. Current Events: Wikipedia is often updated rapidly in the face of current events, so for very recent information, it can sometimes be more up-to-date than my last training data.

Advantages of ChatGPT (me):

  1. Broad Training Data: I’ve been trained on diverse datasets, including books, articles, and other content. This allows me to provide a wide range of information.
  2. Consistent and Neutral: While Wikipedia aims for a neutral point of view, individual articles might sometimes reflect biases of the contributors. My design aims to minimize bias and provide consistent responses.
  3. Conversational Interface: Users can have a back-and-forth dialogue with me, making it easier to ask follow-up questions or dive deeper into topics.

Considerations:

  1. Vandalism: Wikipedia can be edited by anyone, which sometimes leads to misinformation due to vandalism. However, popular pages often have vigilant editors and protective measures in place.
  2. Knowledge Cutoff: My last training data is from September 2021, so events or advancements after that date are not within my current knowledge.

Ultimately, neither Wikipedia nor I should be seen as infallible. Both can serve as starting points for research, but critical information should be cross-referenced with primary sources or authoritative references. It’s always a good practice to be discerning and critical when interpreting information from any source.

RESULT

The characterization of wikipedia is still quite fair. But in some sens does chatGPT4 ‘downplay’ it’s lack of real sources, which are the basis of any serious arguing.

Author

Which criteria do you know for a good scientific description?

ChatGPT

Scientific descriptions are meant to be precise, clear, and replicable. To ensure a high-quality scientific description, several criteria should be met:

  1. Accuracy: The description should correctly represent observations, data, or results without exaggeration or misrepresentation.
  2. Clarity: The language used should be clear and free from ambiguity. It should be easily understood by those with appropriate background knowledge in the field.
  3. Completeness: All relevant details should be included, especially those that would be necessary for replication or to understand the context of the study.
  4. Consistency: Descriptions should be consistent in terms of units of measurement, terminology, and methodology.
  5. Objectivity: The description should be free from personal bias. Instead of using subjective terms, rely on objective measurements and observations.
  6. Replicability: Enough detail should be provided so that another scientist with the same background knowledge and resources can replicate the study or experiment.
  7. Relevance: Only pertinent details should be included. While completeness is important, overloading a description with irrelevant information can detract from its usefulness.
  8. Use of Standardized Terminology: Using accepted and standardized terms in the field ensures that the description is understood universally among experts.
  9. Citing Sources: Any claim, idea, or method that isn’t original to the current study should be appropriately cited, giving credit to the original sources and allowing readers to delve deeper into the background if they wish.
  10. Avoiding Jargon (when possible): While specialized terms can be necessary, over-reliance on jargon can alienate those slightly outside the immediate field. When jargon is used, it should be defined or explained.
  11. Providing Context: A good scientific description often includes background information or a literature review to give context to the study’s significance and position within the broader field.
  12. Transparency: Limitations, potential sources of error, and uncertainties should be clearly stated. This honesty allows readers to gauge the reliability of the findings and understand any potential caveats.

A good scientific description is essentially a balance between precision and clarity. It should be detailed enough to be of value to experts in the field while still being accessible to those with a general background in the discipline.

RESULT

The overview of criteria for a scientific description includes terms like ‘Replicability’, ‘Citing Sources’, and ‘Transparency’. From the preceding self-description of chatGPT4 it is not easily to see, whether these criteria can also applied to the output of chatGPT4.

Lets transform this into a question:

Author

Your overview about criteria for a scientific description includes terms like ‘Replicability’, ‘Citing Sources’, and ‘Transparency’. From the preceding self-description of you it is not easily to see, whether these criteria can also applied to the output of chatGPT4.

ChatGPT

That’s an insightful observation. Let’s discuss the applicability of some of these criteria to ChatGPT (like me) and its outputs:

  1. Replicability: While the underlying research and development process of models like mine can be replicated in theory, the specific outputs for each query might vary slightly, even with similar inputs. Therefore, individual responses from me aren’t precisely replicable.
  2. Citing Sources: I don’t provide direct citations for specific statements in my responses. My training data comes from diverse sources, and I generate responses based on patterns in that data. Thus, I can’t directly attribute my statements to specific sources like a scholarly article or a book. This is indeed a limitation if you’re considering the output as a “scientific description.”
  3. Transparency: OpenAI, the organization behind me, has released details about the architecture, training methodology, and intentions behind models like mine. However, the specifics of the training data or exact processes that lead to a particular response aren’t transparently available in each interaction.

In light of this:

  • For scholarly or academic purposes, my responses should be considered as starting points or general overviews. Critical information should always be cross-referenced with authoritative and primary sources.
  • For general inquiries or casual information, my design is to provide accurate and coherent answers based on the vast amount of data I’ve been trained on.

It’s crucial to recognize the intended use and context when considering the applicability of scientific criteria to any tool or source, including ChatGPT.

COMMENTS

[1] There was a conference at the Technical University of Darmstadt with the title “KI – Text und Geltung. Wie verändern KI-Textgeneratoren wissenschaftliche Diskurse?” (Translated: AI – Text and Validity. How do AI text generators change scientific discourses? )., https://zevedi.de/en/topics/ki-text-2/ . One lecturer Thomas Arnold, gave a speech entitled “Herausforderungen in der Forschung: Mangelnde Reproduzierbarkeit und Erklärbarkeit” (Translated: Challenges in research: lack of reproducibility and explainability), which will be published by de Gruyter at the end of 2023/ or the beginning of 2024.

[2] Gerd Doeben-Henisch, STATE CHANGE FROM NON-WRITING TO WRITING. WORKING WITH CHATGPT4 IN PARALLEL. AN EXPLORATION, https://www.uffmm.org/2023/08/28/state-change-from-non-writing-to-writing-working-with-chatgpt4-in-parallel/

acting, authentic writing, author's brain, chatGPT4, emotional, exploration, foreshadowed, gut feeling, helplessness, intuition, meaning, non-action, non-knowing, Not being able to explain, pre-text phase, rational, rebirth, space of the inner, undefined state, worldview-emergence

State Change from Non-Writing to Writing. Working with chatGPT4 in parallel. An Exploration

Author: Gerd Doeben-Henisch

Email: info@uffmm.org

Aug 28, 2023 – Aug 28, 2023 (18:10h CET)

CONTEXT: Man and Machine. One head against Billions of documents …

The author has started an experiment writing two tracks in parallel: the first track is his own writing without chatGPT4, and the next track ist a chat with chatGPT4. The motivation behind this experiment is to get a better estimate how the writing of chatGPT4 differs. While chatGPT4 is working only by statistical patterns of the ‘surface’ of language communications, the author is exploiting his individual ‘meaning knowledge’ built up in his inner states by many years of individual learning as part of certain ‘cultures’ and ‘everyday situations’. Clearly the knowledge of the individual author about texts available is extremely smaller than compared with the knowledge base of chatGPT4. Thus it is an interesting question whether an individual knowledge is generally too bad compared to the text generation capacity of the chatGPT4 software?

While the premises of the original article cannot be easily transferred to the dialog with chatGPT4, one can still get some sense of where chatGPT4’s strengths lie on the one hand, and its weaknesses on the other. For ‘authentic’ writing a replacement by chatGPT4 is not an option, but a ‘cooperation’ between ‘authentic’ writing and chatGPT seems possible and in some contexts certainly even fruitful.

What the Author did Write:

CONTINUOUS REBIRTH – Now. Silence does not help …Exploration

(This text is a translation from a German source using for nearly 90-95% the deepL software without the need to make any changes afterwards. [*])

CONTEXT

As written in the previous blog entry, the last blog entry with the topic “Homo Sapiens: empirical and sustainable-empirical theories, emotions, and machines. A Sketch” [1] as a draft speech for the conference “AI – Text and Validity. How do AI text generators change scientific discourse?” [2] Due to the tight time frame (20 min for the talk), this text was very condensed. However, despite its brevity, the condensed text contains a many references to fundamental issues. One of them will be briefly taken up here.

Localization in the text of the lecture

A first hint is found in the section headed “FUTURE AND EMOTIONS” and then in the section “SUSTAINABLE EMPIRICAL THEORY”.

In these sections of the text, attention is drawn to the fact that every explicit worldview is preceded by a phase of ’emergence’ of that worldview, in which there is a characteristic ‘transition’ between the ‘result’ in the form of a possible text and a preceding state in which that text is not yet ‘there’. Of course, in this ‘pre-text phase’ – according to the assumptions in the section “MEANING” – there are many facts of knowledge and emotions in the brain of the ‘author’, all of which are ‘not conscious’, but from which the possible effects in the form of a text emanate. How exactly ‘impact’ is supposed to emanate from this ‘pre-conscious’ knowledge and emotions is largely unclear.

We know from everyday life that external events can trigger ‘perceptions’, which in turn can ‘stimulate’ a wide variety of reactions as ‘triggers’. If we disregard such reactions, which are ‘pre-trained’ in our brain due to frequent practice and which are then almost always ‘automatically’ evoked, it is as a rule hardly predictable whether and how we react.

From non-action to action

This potential transition from non-action to action is omnipresent in everyday life. As such, we normally do not notice it. In special situations, however, where we are explicitly challenged to make decisions, we then suddenly find ourselves in a quasi ‘undefined state’: the situation appears to us as if we are supposed to decide. Should we do anything at all (eat something or not)? Which option is more important (go to the planned meeting or rather finish a certain task)? We want to implement a plan, but which of the many options should we ‘choose’ (… there are at least three alternatives; all have pros and cons)? Choosing one option as highly favored would involve significant changes in one’s life situation; do I really want this? Would it be worth it? The nature of the challenges is as varied as everyday life in many different areas.

What is important, more important?

As soon as one or more than one option appears before the ‘mind’s eye’, one involuntarily asks oneself how ‘seriously’ one should take the options? Are there arguments for or against? Are the reasons ‘credible’? What ‘risks’ are associated with them? What can I expect as ‘positive added value’? What changes for my ‘personal situation’ are associated with it? What does this mean for my ‘environment’? …

What do I do if the ‘recognizable’ (‘rational’) options do not provide a clear result, it ‘contradicts’ my ‘feeling for life’, ‘me’, and I ‘spontaneously’ reject it, spontaneously ‘don’t want’ it, it triggers various ‘strong feelings’ that may ‘overwhelm’ me (anger, fear, disappointment, sadness, …)? …

The transition from non-action to action can ‘activate’ a multitude of ‘rational’ and ’emotional’ aspects, which can – and mostly do – influence each other, to the point that one experiences a ‘helplessness’ entangled in a ‘tangle’ of considerations and emotions: one has the feeling of being ‘stuck’, a ‘clear solution’ seems distant. …

If one can ‘wait’ (hours, days, weeks, …) and/or one has the opportunity to talk about it with other people, then this can often – not always – clarify the situation so far that one thinks to know what one ‘wants now’. But such ‘clarifications’ usually do not get the ‘challenge of a ‘decision’ out of the way. Besides, the ‘escape’ into ‘repressing’ the situation is always an option; sometimes it helps; if it doesn’t help, then the ‘everyday’ situation becomes worse by the ‘repressing’, quite apart from the fact that ‘unsolved problems’ do not ‘disappear’, but live on ‘inside’ and can unfold ‘special effects’ there in many ways, which are very ‘destructive’.

Rebirth?

The variety of possible – emotional as well as rational – aspects of the transition from non-action to action are fascinating, but possibly even more fascinating is the basic process itself: at any given moment, every human being lives in a certain everyday situation with a variety of experiences already made, a mixture of ‘rational explanations’ and ’emotional states’. And, depending on the nature of everyday life, one can ‘drift along’ or one has to perceive daily ‘strenuous activities’ in order to maintain the situation of everyday life; in other cases, one has to constantly ‘fight’ in real terms for the continuance in everyday life. One experiences here that the ‘conditions of everyday life’ are largely given to the individual and one can only change them to a limited extent and with a corresponding ‘effort’.

External events (fire, water, violence, war, drought, accident, life forms of a community, workplace, company policy, diseases, aging, …) can of course strongly influence the personal everyday life ‘against one’s will’, but in the end a fundamental autonomy of decision-making remains in the individual: one can decide differently in the next moment than before, even without it being completely clear to oneself in this moment ‘why’ one does it. Whether one calls this ‘not being able to explain’ then ‘goot feeling’ or ‘intuition’ or … all these words only circumscribe a ‘not knowing’ about the processes ‘in us’ that take place and ‘motivate’ us. And even if one has a ‘linguistic explanation’ available, this does not have to mean that a ‘clear insight’ is also connected with these words. The proportion of ‘preconscious/ unconscious’ ‘inner processes’ is high and ultimately these are not explainable ‘out of themselves’: they take place, move us, and we ‘implement them’.

Yes, in every moment we can behave ‘as usual’ and thereby ‘preserve’ the world (or thereby prevent it from becoming different?). But we can also sometimes ‘deviate’ from the usual (and thereby ‘destroy’ something or make something ‘new possible?). All in all, the ‘space of the inside’ remains largely ‘unilluminated’. We hardly if at all understand why we do this; this requires trust in ourselves and the situation. Is the difference to the ‘original birth’ only gradual? Are we in a continuing process of birth that constantly enables the construction of something ‘new’, can support ‘life’ or also ‘weaken’ it?

COMMENTS

[Exploration] The format ‘exploration’ is newly introduced in the blog from now on, since there is often the situation that the author at the transition point from ‘non-action to action’, from ‘non-writing to writing’ tries out which emotional and rational ‘reactions’ from the ‘inside’ are ‘spontaneously’ available for a certain question/idea. This is to be distinguished from a ‘systematic elaboration’ of a thought, although the influence of the ‘inside’ is of course never completely excluded. The ‘difference’ between ‘exploratory’ and ‘systematic’ writing has to do with the fact that systematic writing tries to bring the ‘rational dimension’ of the thought to the fore.

[*] German source: https://www.cognitiveagent.org/2023/08/28/staendige-wiedergeburt-jetzt-schweigen-hilft-nicht-exploration/ ,

[deepL translator]: https://www.deepl.com

[1] https://www.uffmm.org/2023/08/24/homo-sapiens-empirical-and-sustained-empirical-theories-emotions-and-machines-a-sketch/

[2] https://zevedi.de/en/topics/ki-text-2/

Dealing with the topic using chatGPT4

Author: What happens inside a person when it changes from the state of non-writing to the state of writing? Which kinds of factors are involved in this change?

ChatGPT

The shift from a state of non-writing to writing is a complex interplay of cognitive, emotional, and physical processes. Several factors contribute to this transformation:

  1. Cognitive Factors:
    • Intent and Purpose: The most immediate factor that leads to writing is the intent. The individual decides there’s a need to communicate or record something. This purpose could be to share knowledge, express emotions, or any other myriad reasons.
    • Idea Formation: The brain begins to formulate ideas, organize thoughts, and consider the message it wants to convey.
    • Recall: The brain accesses stored knowledge about language, grammar, and the topic at hand.
    • Decision Making: Choices are made about wording, tone, and structure.
  2. Emotional Factors:
    • Motivation: An internal or external motivation prompts the writer. This could be intrinsic (like the joy of writing) or extrinsic (like a job requirement).
    • Confidence: A person’s self-efficacy regarding writing can influence their willingness and approach. A confident writer might start without hesitation, while someone less confident might procrastinate or struggle with where to begin.
    • Mood and Emotion: A person’s emotional state can shape the content and tone of their writing. For instance, someone in a cheerful mood might use more positive and lively language.
  3. Physiological and Neuromotor Factors:
    • Fine Motor Skills: The act of writing requires coordination between the brain and muscles, whether it’s holding a pen or typing on a keyboard.
    • Visual Processing: Reading what’s written, planning spatially on the page or screen, and adjusting based on visual feedback are integral to the writing process.
    • Brain Activation: Certain areas of the brain, like Broca’s area and Wernicke’s area, are particularly active during language production.
  4. Environmental Factors:
    • Physical Environment: The availability of tools (pen, paper, computer), a conducive atmosphere, and a comfortable workspace can influence the transition to writing.
    • Cultural and Social Environment: The societal context, intended audience, and cultural norms can shape what and how a person writes.
  5. Educational and Experiential Factors:
    • Training and Practice: A person’s prior experience with writing, including their education, can influence their ease and style of writing.
    • Feedback and Iteration: Previous feedback on one’s writing can affect future attempts. Someone who has been praised might approach writing with more enthusiasm, while critical feedback might make another more cautious or reflective.
  6. External Stimuli:
    • Inspiration: Often, external stimuli—like reading a book, a conversation, a personal experience, or even a sunset—can spark the urge to write.
    • Prompts: In some situations, a specific prompt or question might initiate the writing process.

Understanding these factors and their interplay can be beneficial for educators, writers, and anyone looking to refine or understand their writing process.

AUTHOR

Can you describe more the subjective experience of a person, which is changing from the state of non-writing to writing?

chatGPT4

Certainly! The transition from non-writing to writing, when viewed from a subjective lens, involves a cascade of internal experiences. Here’s a more in-depth dive into the intimate, often ineffable stages a writer might traverse:

  1. Initial Restlessness: Before the act of writing commences, there’s often a sense of unease or urgency. It’s akin to a pressure building up, a compulsion to get something out, or a feeling that there’s something “there” that needs to be expressed.
  2. Incubation and Percolation: Many writers describe a period where ideas are “brewing” or “stewing” inside them. They might not be actively thinking about these ideas, but somewhere in the backdrop, the mind is processing and refining them. This can feel like daydreaming or being lost in thought.
  3. Flash of Insight: This is the ‘Eureka!’ moment when clarity emerges. It’s the point when the idea crystallizes, and the writer feels an impetus to put pen to paper. It can be a sudden realization or a slow dawning.
  4. Overcoming the Inertia: This is the mental “deep breath” before diving in. There’s a brief struggle, often described as “writer’s block” or resistance, where the weight of the blank page feels daunting.
  5. Entering the Flow: As words start pouring out, many writers describe a state known as “flow” – a term coined by Mihaly Csikszentmihalyi. In this state, writers lose track of time, their surroundings, and sometimes even themselves. They feel as if they are merely a conduit for the words, with the writing almost writing itself.
  6. Bouts of Doubt and Reassurance: Especially in longer writing stints, waves of self-doubt might wash over the writer. Questions like “Is this good enough?” or “Does this make sense?” arise. These periods might be interspersed with moments of confidence and reassurance, where the writer feels they’re on the right track.
  7. Physical Sensations: There might be heightened awareness of the tactile sensation of the pen moving on paper or fingers dancing on the keyboard. Some writers describe a kind of rhythm they get into, almost like a meditative state.
  8. Emotional Catharsis: Particularly for personal or emotive subjects, the act of writing can be cathartic. It’s a release, a way to process feelings, and often brings relief or deeper understanding.
  9. Completion and Exhaustion: As the writing draws to a close, there’s a sense of accomplishment, but also, often, a feeling of emptiness or exhaustion. The mental and emotional energy expended in writing can leave one drained.
  10. Reflection and Revision: Once the initial draft is out, there’s a period of reflection. Reading one’s own words can be an enlightening experience. This phase might involve editing, but it’s also a moment of self-confrontation, seeing one’s thoughts and feelings laid out bare.

The subjective experience of writing is deeply personal and can vary greatly from person to person. Some find it therapeutic, others see it as work, and for many, it’s a passionate craft. Regardless of the perspective, the journey from non-writing to writing is an intimate dance between the conscious and subconscious, emotion and reason, art and discipline.

End of this first small experiment.

Actor, AI - artificial intelligence, AI text generator, application text, artificial intelligence, biological systems, change rules, collective intelligence, emotionality, emotions, empirical theory, evaluation process, everyday experience, everyday life, everyday processes, false, Future, future situation, homo sapiens, initial situation, intelligence, intelligent machine, justifiable predictions, Knowledge, language, meaning, meaning relationship, meta-level, non-biological systems, possible future, possible validity, present, rationality, science, scientific, scientific discourse, scientific text, semiotic actor, Simulation, structural view, subsequent text, sustainability, sustainable empirical theory, text, text generation, text-capable machines, theory, transdisciplinary, true, validity, world perception

Homo Sapiens: empirical and sustained-empirical theories, emotions, and machines. A sketch

Author: Gerd Doeben-Henisch

Email: info@uffmm.org

Aug 24, 2023 — Aug 29, 2023 (10:48h CET)

Attention: This text has been translated from a German source by using the software deepL for nearly 97 – 99% of the text! The diagrams of the German version have been left out.

CONTEXT

This text represents the outline of a talk given at the conference “AI – Text and Validity. How do AI text generators change scientific discourse?” (August 25/26, 2023, TU Darmstadt). [1] A publication of all lectures is planned by the publisher Walter de Gruyter by the end of 2023/beginning of 2024. This publication will be announced here then.

Start of the Lecture

Dear Auditorium,

This conference entitled “AI – Text and Validity. How do AI text generators change scientific discourses?” is centrally devoted to scientific discourses and the possible influence of AI text generators on these. However, the hot core ultimately remains the phenomenon of text itself, its validity.

In this conference many different views are presented that are possible on this topic.

TRANSDISCIPLINARY

My contribution to the topic tries to define the role of the so-called AI text generators by embedding the properties of ‘AI text generators’ in a ‘structural conceptual framework’ within a ‘transdisciplinary view’. This helps the specifics of scientific discourses to be highlighted. This can then result further in better ‘criteria for an extended assessment’ of AI text generators in their role for scientific discourses.

An additional aspect is the question of the structure of ‘collective intelligence’ using humans as an example, and how this can possibly unite with an ‘artificial intelligence’ in the context of scientific discourses.

‘Transdisciplinary’ in this context means to span a ‘meta-level’ from which it should be possible to describe today’s ‘diversity of text productions’ in a way that is expressive enough to distinguish ‘AI-based’ text production from ‘human’ text production.

HUMAN TEXT GENERATION

The formulation ‘scientific discourse’ is a special case of the more general concept ‘human text generation’.

This change of perspective is meta-theoretically necessary, since at first sight it is not the ‘text as such’ that decides about ‘validity and non-validity’, but the ‘actors’ who ‘produce and understand texts’. And with the occurrence of ‘different kinds of actors’ – here ‘humans’, there ‘machines’ – one cannot avoid addressing exactly those differences – if there are any – that play a weighty role in the ‘validity of texts’.

TEXT CAPABLE MACHINES

With the distinction in two different kinds of actors – here ‘humans’, there ‘machines’ – a first ‘fundamental asymmetry’ immediately strikes the eye: so-called ‘AI text generators’ are entities that have been ‘invented’ and ‘built’ by humans, it are furthermore humans who ‘use’ them, and the essential material used by so-called AI generators are again ‘texts’ that are considered a ‘human cultural property’.

In the case of so-called ‘AI-text-generators’, we shall first state only this much, that we are dealing with ‘machines’, which have ‘input’ and ‘output’, plus a minimal ‘learning ability’, and whose input and output can process ‘text-like objects’.

BIOLOGICAL — NON-BIOLOGICAL

On the meta-level, then, we are assumed to have, on the one hand, such actors which are minimally ‘text-capable machines’ – completely human products – and, on the other hand, actors we call ‘humans’. Humans, as a ‘homo-sapiens population’, belong to the set of ‘biological systems’, while ‘text-capable machines’ belong to the set of ‘non-biological systems’.

BLANK INTELLIGENCE TERM

The transformation of the term ‘AI text generator’ into the term ‘text capable machine’ undertaken here is intended to additionally illustrate that the widespread use of the term ‘AI’ for ‘artificial intelligence’ is rather misleading. So far, there exists today no general concept of ‘intelligence’ in any scientific discipline that can be applied and accepted beyond individual disciplines. There is no real justification for the almost inflationary use of the term AI today other than that the term has been so drained of meaning that it can be used anytime, anywhere, without saying anything wrong. Something that has no meaning can be neither true’ nor ‘false’.

PREREQUISITES FOR TEXT GENERATION

If now the homo-sapiens population is identified as the original actor for ‘text generation’ and ‘text comprehension’, it shall now first be examined which are ‘those special characteristics’ that enable a homo-sapiens population to generate and comprehend texts and to ‘use them successfully in the everyday life process’.

VALIDITY

A connecting point for the investigation of the special characteristics of a homo-sapiens text generation and a text understanding is the term ‘validity’, which occurs in the conference topic.

In the primary arena of biological life, in everyday processes, in everyday life, the ‘validity’ of a text has to do with ‘being correct’, being ‘appicable’. If a text is not planned from the beginning with a ‘fictional character’, but with a ‘reference to everyday events’, which everyone can ‘check’ in the context of his ‘perception of the world’, then ‘validity in everyday life’ has to do with the fact that the ‘correctness of a text’ can be checked. If the ‘statement of a text’ is ‘applicable’ in everyday life, if it is ‘correct’, then one also says that this statement is ‘valid’, one grants it ‘validity’, one also calls it ‘true’. Against this background, one might be inclined to continue and say: ‘If’ the statement of a text ‘does not apply’, then it has ‘no validity’; simplified to the formulation that the statement is ‘not true’ or simply ‘false’.

In ‘real everyday life’, however, the world is rarely ‘black’ and ‘white’: it is not uncommon that we are confronted with texts to which we are inclined to ascribe ‘a possible validity’ because of their ‘learned meaning’, although it may not be at all clear whether there is – or will be – a situation in everyday life in which the statement of the text actually applies. In such a case, the validity would then be ‘indeterminate’; the statement would be ‘neither true nor false’.

ASYMMETRY: APPLICABLE- NOT APPLICABLE

One can recognize a certain asymmetry here: The ‘applicability’ of a statement, its actual validity, is comparatively clear. The ‘not being applicable’, i.e. a ‘merely possible’ validity, on the other hand, is difficult to decide.

With this phenomenon of the ‘current non-decidability’ of a statement we touch both the problem of the ‘meaning’ of a statement — how far is at all clear what is meant? — as well as the problem of the ‘unfinishedness of our everyday life’, better known as ‘future’: whether a ‘current present’ continues as such, whether exactly like this, or whether completely different, depends on how we understand and estimate ‘future’ in general; what some take for granted as a possible future, can be simply ‘nonsense’ for others.

MEANING

This tension between ‘currently decidable’ and ‘currently not yet decidable’ additionally clarifies an ‘autonomous’ aspect of the phenomenon of meaning: if a certain knowledge has been formed in the brain and has been made usable as ‘meaning’ for a ‘language system’, then this ‘associated’ meaning gains its own ‘reality’ for the scope of knowledge: it is not the ‘reality beyond the brain’, but the ‘reality of one’s own thinking’, whereby this reality of thinking ‘seen from outside’ has something like ‘being virtual’.

If one wants to talk about this ‘special reality of meaning’ in the context of the ‘whole system’, then one has to resort to far-reaching assumptions in order to be able to install a ‘conceptual framework’ on the meta-level which is able to sufficiently describe the structure and function of meaning. For this, the following components are minimally assumed (‘knowledge’, ‘language’ as well as ‘meaning relation’):

KNOWLEDGE: There is the totality of ‘knowledge’ that ‘builds up’ in the homo-sapiens actor in the course of time in the brain: both due to continuous interactions of the ‘brain’ with the ‘environment of the body’, as well as due to interactions ‘with the body itself’, as well as due to interactions ‘of the brain with itself’.

LANGUAGE: To be distinguished from knowledge is the dynamic system of ‘potential means of expression’, here simplistically called ‘language’, which can unfold over time in interaction with ‘knowledge’.

MEANING RELATIONSHIP: Finally, there is the dynamic ‘meaning relation’, an interaction mechanism that can link any knowledge elements to any language means of expression at any time.

Each of these mentioned components ‘knowledge’, ‘language’ as well as ‘meaning relation’ is extremely complex; no less complex is their interaction.

FUTURE AND EMOTIONS

In addition to the phenomenon of meaning, it also became apparent in the phenomenon of being applicable that the decision of being applicable also depends on an ‘available everyday situation’ in which a current correspondence can be ‘concretely shown’ or not.

If, in addition to a ‘conceivable meaning’ in the mind, we do not currently have any everyday situation that sufficiently corresponds to this meaning in the mind, then there are always two possibilities: We can give the ‘status of a possible future’ to this imagined construct despite the lack of reality reference, or not.

If we would decide to assign the status of a possible future to a ‘meaning in the head’, then there arise usually two requirements: (i) Can it be made sufficiently plausible in the light of the available knowledge that the ‘imagined possible situation’ can be ‘transformed into a new real situation’ in the ‘foreseeable future’ starting from the current real situation? And (ii) Are there ‘sustainable reasons’ why one should ‘want and affirm’ this possible future?

The first requirement calls for a powerful ‘science’ that sheds light on whether it can work at all. The second demand goes beyond this and brings the seemingly ‘irrational’ aspect of ’emotionality’ into play under the garb of ‘sustainability’: it is not simply about ‘knowledge as such’, it is also not only about a ‘so-called sustainable knowledge’ that is supposed to contribute to supporting the survival of life on planet Earth — and beyond –, it is rather also about ‘finding something good, affirming something, and then also wanting to decide it’. These last aspects are so far rather located beyond ‘rationality’; they are assigned to the diffuse area of ’emotions’; which is strange, since any form of ‘usual rationality’ is exactly based on these ’emotions’.[2]

SCIENTIFIC DISCOURSE AND EVERYDAY SITUATIONS

In the context of ‘rationality’ and ’emotionality’ just indicated, it is not uninteresting that in the conference topic ‘scientific discourse’ is thematized as a point of reference to clarify the status of text-capable machines.

The question is to what extent a ‘scientific discourse’ can serve as a reference point for a successful text at all?

For this purpose it can help to be aware of the fact that life on this planet earth takes place at every moment in an inconceivably large amount of ‘everyday situations’, which all take place simultaneously. Each ‘everyday situation’ represents a ‘present’ for the actors. And in the heads of the actors there is an individually different knowledge about how a present ‘can change’ or will change in a possible future.

This ‘knowledge in the heads’ of the actors involved can generally be ‘transformed into texts’ which in different ways ‘linguistically represent’ some of the aspects of everyday life.

The crucial point is that it is not enough for everyone to produce a text ‘for himself’ alone, quite ‘individually’, but that everyone must produce a ‘common text’ together ‘with everyone else’ who is also affected by the everyday situation. A ‘collective’ performance is required.

Nor is it a question of ‘any’ text, but one that is such that it allows for the ‘generation of possible continuations in the future’, that is, what is traditionally expected of a ‘scientific text’.

From the extensive discussion — since the times of Aristotle — of what ‘scientific’ should mean, what a ‘theory’ is, what an ’empirical theory’ should be, I sketch what I call here the ‘minimal concept of an empirical theory’.

  1. The starting point is a ‘group of people’ (the ‘authors’) who want to create a ‘common text’.
  2. This text is supposed to have the property that it allows ‘justifiable predictions’ for possible ‘future situations’, to which then ‘sometime’ in the future a ‘validity can be assigned’.
  3. The authors are able to agree on a ‘starting situation’ which they transform by means of a ‘common language’ into a ‘source text’ [A].
  4. It is agreed that this initial text may contain only ‘such linguistic expressions’ which can be shown to be ‘true’ ‘in the initial situation’.
  5. In another text, the authors compile a set of ‘rules of change’ [V] that put into words ‘forms of change’ for a given situation.
  6. Also in this case it is considered as agreed that only ‘such rules of change’ may be written down, of which all authors know that they have proved to be ‘true’ in ‘preceding everyday situations’.
  7. The text with the rules of change V is on a ‘meta-level’ compared to the text A about the initial situation, which is on an ‘object-level’ relative to the text V.
  8. The ‘interaction’ between the text V with the change rules and the text A with the initial situation is described in a separate ‘application text’ [F]: Here it is described when and how one may apply a change rule (in V) to a source text A and how this changes the ‘source text A’ to a ‘subsequent text A*’.
  9. The application text F is thus on a next higher meta-level to the two texts A and V and can cause the application text to change the source text A.
  1. The moment a new subsequent text A* exists, the subsequent text A* becomes the new initial text A.
  2. If the new initial text A is such that a change rule from V can be applied again, then the generation of a new subsequent text A* is repeated.
  3. This ‘repeatability’ of the application can lead to the generation of many subsequent texts <A*1, …, A*n>.
  4. A series of many subsequent texts <A*1, …, A*n> is usually called a ‘simulation’.
  5. Depending on the nature of the source text A and the nature of the change rules in V, it may be that possible simulations ‘can go quite differently’. The set of possible scientific simulations thus represents ‘future’ not as a single, definite course, but as an ‘arbitrarily large set of possible courses’.
  6. The factors on which different courses depend are manifold. One factor are the authors themselves. Every author is, after all, with his corporeality completely himself part of that very empirical world which is to be described in a scientific theory. And, as is well known, any human actor can change his mind at any moment. He can literally in the next moment do exactly the opposite of what he thought before. And thus the world is already no longer the same as previously assumed in the scientific description.

Even this simple example shows that the emotionality of ‘finding good, wanting, and deciding’ lies ahead of the rationality of scientific theories. This continues in the so-called ‘sustainability discussion’.

SUSTAINABLE EMPIRICAL THEORY

With the ‘minimal concept of an empirical theory (ET)’ just introduced, a ‘minimal concept of a sustainable empirical theory (NET)’ can also be introduced directly.

While an empirical theory can span an arbitrarily large space of grounded simulations that make visible the space of many possible futures, everyday actors are left with the question of what they want to have as ‘their future’ out of all this? In the present we experience the situation that mankind gives the impression that it agrees to destroy the life beyond the human population more and more sustainably with the expected effect of ‘self-destruction’.

However, this self-destruction effect, which can be predicted in outline, is only one variant in the space of possible futures. Empirical science can indicate it in outline. To distinguish this variant before others, to accept it as ‘good’, to ‘want’ it, to ‘decide’ for this variant, lies in that so far hardly explored area of emotionality as root of all rationality.[2]

If everyday actors have decided in favor of a certain rationally lightened variant of possible future, then they can evaluate at any time with a suitable ‘evaluation procedure (EVAL)’ how much ‘percent (%) of the properties of the target state Z’ have been achieved so far, provided that the favored target state is transformed into a suitable text Z.

In other words, the moment we have transformed everyday scenarios into a rationally tangible state via suitable texts, things take on a certain clarity and thereby become — in a sense — simple. That we make such transformations and on which aspects of a real or possible state we then focus is, however, antecedent to text-based rationality as an emotional dimension.[2]

MAN-MACHINE

After these preliminary considerations, the final question is whether and how the main question of this conference, “How do AI text generators change scientific discourse?” can be answered in any way?

My previous remarks have attempted to show what it means for humans to collectively generate texts that meet the criteria for scientific discourse that also meets the requirements for empirical or even sustained empirical theories.

In doing so, it becomes apparent that both in the generation of a collective scientific text and in its application in everyday life, a close interrelation with both the shared experiential world and the dynamic knowledge and meaning components in each actor play a role.

The aspect of ‘validity’ is part of a dynamic world reference whose assessment as ‘true’ is constantly in flux; while one actor may tend to say “Yes, can be true”, another actor may just tend to the opposite. While some may tend to favor possible future option X, others may prefer future option Y. Rational arguments are absent; emotions speak. While one group has just decided to ‘believe’ and ‘implement’ plan Z, the others turn away, reject plan Z, and do something completely different.

This unsteady, uncertain character of future-interpretation and future-action accompanies the Homo Sapiens population from the very beginning. The not understood emotional complex constantly accompanies everyday life like a shadow.

Where and how can ‘text-enabled machines’ make a constructive contribution in this situation?

Assuming that there is a source text A, a change text V and an instruction F, today’s algorithms could calculate all possible simulations faster than humans could.

Assuming that there is also a target text Z, today’s algorithms could also compute an evaluation of the relationship between a current situation as A and the target text Z.

In other words: if an empirical or a sustainable-empirical theory would be formulated with its necessary texts, then a present algorithm could automatically compute all possible simulations and the degree of target fulfillment faster than any human alone.

But what about the (i) elaboration of a theory or (ii) the pre-rational decision for a certain empirical or even sustainable-empirical theory ?

A clear answer to both questions seems hardly possible to me at the present time, since we humans still understand too little how we ourselves collectively form, select, check, compare and also reject theories in everyday life.

My working hypothesis on the subject is: that we will very well need machines capable of learning in order to be able to fulfill the task of developing useful sustainable empirical theories for our common everyday life in the future. But when this will happen in reality and to what extent seems largely unclear to me at this point in time.[2]

COMMENTS

[1] https://zevedi.de/en/topics/ki-text-2/

[2] Talking about ’emotions’ in the sense of ‘factors in us’ that move us to go from the state ‘before the text’ to the state ‘written text’, that hints at very many aspects. In a small exploratory text “State Change from Non-Writing to Writing. Working with chatGPT4 in parallel” ( https://www.uffmm.org/2023/08/28/state-change-from-non-writing-to-writing-working-with-chatgpt4-in-parallel/ ) the author has tried to address some of these aspects. While writing it becomes clear that very many ‘individually subjective’ aspects play a role here, which of course do not appear ‘isolated’, but always flash up a reference to concrete contexts, which are linked to the topic. Nevertheless, it is not the ‘objective context’ that forms the core statement, but the ‘individually subjective’ component that appears in the process of ‘putting into words’. This individual subjective component is tentatively used here as a criterion for ‘authentic texts’ in comparison to ‘automated texts’ like those that can be generated by all kinds of bots. In order to make this difference more tangible, the author decided to create an ‘automated text’ with the same topic at the same time as the quoted authentic text. For this purpose he used chatGBT4 from openAI. This is the beginning of a philosophical-literary experiment, perhaps to make the possible difference more visible in this way. For purely theoretical reasons, it is clear that a text generated by chatGBT4 can never generate ‘authentic texts’ in origin, unless it uses as a template an authentic text that it can modify. But then this is a clear ‘fake document’. To prevent such an abuse, the author writes the authentic text first and then asks chatGBT4 to write something about the given topic without chatGBT4 knowing the authentic text, because it has not yet found its way into the database of chatGBT4 via the Internet.