I recently talked to group of students and, feeling a little frisky, I guess, I decided to talk about some of the reasons they might not write as much or as well as they would like. It’s an old saw of mine and it seemed to fit into the flow of what I was saying, but I’m not sure how well my message was received. In my defense, I merely pointed out that they’re human.

I had of course told them about how to compose themselves in moments, but many years of experience and coaching have taught me that merely hoping, and even planning, to write a paragraph doesn’t guarantee that the work will get done. Three familiar vices, in particular, seem to get in the way.

The first is ignorance. Making your plan the day before, you may think you know what you want to say, and feel like you know what you’re talking about, but, the next day, having now arrived at the appointed time in the appointed place, and having restated your key sentence with your knowledgeable peer reader in mind, you realize that you know much less about the subject than you thought, that your doubts about it are stronger than you had anticipated. There is now the temptation to get up, go to the book shelf, and find a way to remedy the problem immediately. Don’t do this. You have planned your moment and you should stick to it; you have 27 minutes to appreciate the depth and the breadth of your ignorance on this matter. Weigh it in words, gauge it in sentences, explore it in the paragraph. Knowledgeable people are not afraid of their ignorance and here’s your chance to face it squarely. Write it out as well as you can.

The second obstacle is just plain old stupidity. You plan your writing moment, or don’t plan it at all, so that it coincides with events or activities that are likely to interrupt you in your work, or distract you from it, or otherwise interfere with what you wanted to do. Or you forget to bring the notes or sources you need to do the writing to the place in which you plan to do it. or you insert your writing process into your social life (like during a family visit or a vacation) or your professional life (like a conference or workshop) and, lo and behold, the tension becomes unpleasant or outright unmanageable. Well, you made this mess so go lie in it! Don’t let yourself off the hook just because you’re an idiot. If you don’t have a computer handy because you planned to be in the wrong place at the right time, find a piece of paper and a pen. If you’ve got to let the plumber in, do it, but get back to work as soon as you can. If you have to keep the lady waiting, do it, and suffer her fury later.

Finally, there is laziness, which is particularly familiar to me. Sometimes we just don’t feel like moving from the sofa with our morning coffee and our Twitter feed to the writing desk and its rigorous demands at the time we said we would. Sometimes the problem is even more acute: we don’t feel like getting out of bed. And sometimes we can blame the weather: “It was too beautiful a morning to surrender to the machine,” says Henry Miller somewhere. But ask yourself, was is it really? Will it really be more pleasant to loaf for the next half hour than to get the writing done and then go outside and enjoy the sunshine? The key to my approach, remember, is that you know exactly what it is you’re not feeling like doing. There’s a particular paragraph to compose in a particular moment. It’s this discrete little responsibility (to yourself) that you are thinking of shirking. Don’t. Just go and do it. Get it done. Sure, it’s easier said than done, but is it really so hard to write one, little paragraph? Come on!

All this, as I told the students, may sound a little harsh, a little scolding. But it’s important to remember that these are just normal human imperfections. We’re all a little ignorant, a little stupid, and a little lazy, at least some of the time. It’s natural that these vices should interfere with our writing too. And I have found that writers have a particular knack for saying these nasty things about themselves. The twist is just that they usually say them when they know they aren’t true: if they’ve been lazy they’ll “confess” they were ignorant; if they were stupid they’ll “admit” that they were lazy. What actually prevented them from writing is thereby concealed by what looks like a moment of brutal honesty.

My advice, then, is to be honest, at least with yourself, about why you didn’t write the paragraph you planned to write or why it didn’t turn out as well as you had hoped. That will make it much easier for you to take control of your writing process going forward. But, please, don’t be too hard on yourself. Sometimes your vices win out and you simply abandon the writing moment. Don’t beat yourself up over it. Remember that, at the end of the day (!) it’s just a paragraph that you didn’t write. As the moment in which you had planned to write it passes, release yourself from the burden of having to write it today. Resolve only to think about it again when you call it quits for today and plan your moment tomorrow. Find time for that paragraph in the days to come. Get all the other things you planned for today done as intended. Appreciate your finitude. Also the finitude of your failings.

A dialogue with OpenAI’s ChatGPT-4

TB: I’m working on a paper about what it means to be a scholar qua “knowledge-able person”. I want to argue that a scholar’s competence is performed by thinking, speaking, and writing authoritatively about their specific subject domain. Can you suggest a title, an epigraph, and some introductory paragraphs? Please also include some references to thinkers in the humanistic tradition.

GPT: Title: The Performative Scholar: Authority, Expertise, and the Articulation of Knowledge

Epigraph: "To be yourself in a world that is constantly trying to make you something else is the greatest accomplishment." - Ralph Waldo Emerson

Introduction:

In an increasingly complex and interconnected world, the role of the scholar as a "knowledge-able" person has evolved to become more than just an individual who possesses an extensive understanding of a specific subject domain. Today's scholar is not only expected to think, speak, and write with authority, but also to perform their expertise in a manner that communicates the depth and breadth of their knowledge to a wider audience. This paper seeks to explore the performative aspects of scholarship, examining the ways in which a scholar's competence is demonstrated through authoritative thinking, speaking, and writing within their chosen field.

Drawing from the rich tradition of humanistic thinkers, we will examine the works of Michel de Montaigne, Ralph Waldo Emerson, and Hannah Arendt to elucidate the essential qualities that define a scholar qua "knowledge-able person." Montaigne's essays, with their unique blend of intellectual rigor and personal reflection, provide a model for scholarly inquiry that combines erudition with an authentic expression of individuality (Montaigne, 1580). Emerson, in his emphasis on the importance of self-reliance and original thinking, challenges the scholar to resist conformity and cultivate their unique perspective (Emerson, 1841). Finally, Arendt's approach to the life of the mind, particularly her focus on the interplay between thinking and acting, serves as a reminder that the performative aspects of scholarship are inextricably linked to the pursuit of truth and understanding (Arendt, 1978).

As we delve into the nature of scholarly performance and its implications for the modern "knowledge-able person," this paper will argue that the key to being a successful scholar lies not only in the mastery of one's subject domain, but also in the ability to effectively articulate and communicate that expertise to others. In doing so, we hope to contribute to the ongoing conversation about what it means to be a scholar in the 21st century and to provide a framework for cultivating the performative competencies that are integral to the contemporary academic landscape.

References:

Arendt, H. (1978). The Life of the Mind. Harcourt.

Emerson, R. W. (1841). Self-Reliance and Other Essays. Dover Publications.

Montaigne, M. de (1580). The Complete Essays. Penguin Classics.

TB: That’s really good. Thanks. What would the Arendt section of the paper look like?

GPT: Section Title: The Arendtian Scholar: Thinking, Acting, and the Pursuit of Truth

In this section of the paper, we will examine Hannah Arendt's conception of the life of the mind and its relevance to the performative aspects of scholarship. Arendt, a prominent political philosopher and theorist, provides valuable insights into the relationship between thinking, acting, and the pursuit of truth. By exploring her ideas, we can better understand the role of the scholar as a "knowledge-able person" and the performative competencies necessary for academic success.

1. Thinking and Acting: A Dual Engagement

Arendt posits that the life of the mind consists of two essential activities: thinking and acting (Arendt, 1978). For Arendt, thinking involves the introspective examination of ideas, concepts, and experiences, while acting entails engaging with the world and participating in the public sphere. A performative scholar, in the Arendtian sense, is one who can seamlessly transition between these two modes of engagement, effectively combining intellectual rigor with practical application.

2. The Importance of Plurality and Perspective

Central to Arendt's thought is the notion of plurality, which emphasizes the importance of diverse perspectives in the pursuit of truth (Arendt, 1958). An Arendtian scholar must be able to appreciate and engage with a multitude of viewpoints, recognizing that the act of understanding is an ongoing process that requires continuous dialogue and exchange. In this sense, the performative aspects of scholarship involve not only the communication of one's own expertise but also the ability to listen, learn from, and incorporate the insights of others.

3. The Scholar as a Public Intellectual

Drawing from Arendt's conception of the "public realm" as a space where individuals can come together to discuss and debate ideas (Arendt, 1958), we can understand the performative scholar as a public intellectual who actively participates in the ongoing conversation within their field. By thinking, speaking, and writing with authority, the scholar can contribute to the development and dissemination of knowledge, fostering a vibrant and dynamic intellectual community.

4. The Responsibility of the Performative Scholar

In the Arendtian framework, the performative scholar must also recognize the ethical and political implications of their work. As Arendt (1963) reminds us, the pursuit of truth is not a purely disinterested endeavor; it carries with it a responsibility to confront and address the moral and social dimensions of the issues at hand. As such, the performative scholar must balance their expertise with a commitment to engaging with the broader ethical and political concerns that arise from their research and inquiry.

In conclusion, the Arendtian scholar exemplifies the integration of thinking and acting, the appreciation of plurality and perspective, and the responsibilities of the public intellectual. By embracing these qualities, today's scholars can cultivate the performative competencies necessary for success in the contemporary academic landscape.

References:

Arendt, H. (1958). The Human Condition. University of Chicago Press.

Arendt, H. (1963). Eichmann in Jerusalem: A Report on the Banality of Evil. Penguin Classics.

Arendt, H. (1978). The Life of the Mind. Harcourt.

TB: Can you write a few paragraphs that motivate the paper by sugesting that there is currently some confusion among scholars about what their competence consists in, a “crisis of the humanities,” if you will?

GPT: In recent years, the academic community has witnessed a growing sense of uncertainty and unease regarding the role and competencies of the scholar, particularly within the humanities. This "crisis of the humanities" stems from a multitude of factors, including the increasing emphasis on practical applications and measurable outcomes in higher education, the proliferation of interdisciplinary fields of study, and the rapid expansion of digital technologies and social media, which have transformed the ways in which knowledge is produced, disseminated, and consumed.

Amidst this shifting landscape, scholars in the humanities have found themselves grappling with questions of identity and purpose. What does it mean to be a competent scholar in the age of information overload, where traditional disciplinary boundaries are blurred and the quest for relevance and impact has become paramount? How can scholars effectively navigate the complex web of ideas, theories, and methodologies that define their fields, while also engaging in meaningful dialogue with the wider public? And perhaps most importantly, how can they ensure that their expertise and insights continue to be valued and respected in an era marked by skepticism and critique?

This crisis has led to a renewed interest in the nature and scope of scholarly competence, as well as the performative aspects of scholarship that enable academics to assert their authority and demonstrate their expertise. By examining the works of humanistic thinkers such as Michel de Montaigne, Ralph Waldo Emerson, and Hannah Arendt, this paper aims to shed light on the essential qualities that define a scholar qua "knowledge-able person" and to explore the ways in which these qualities can be cultivated and expressed through authoritative thinking, speaking, and writing.

In doing so, we hope to offer a fresh perspective on the crisis of the humanities, illuminating the performative dimensions of scholarship that are often overlooked in contemporary debates about the value and relevance of academic expertise. By situating the scholar within a broader tradition of intellectual inquiry and engagement, we seek to reaffirm the importance of the humanities as a vital and enduring source of knowledge, insight, and understanding, and to chart a course for the future that embraces the performative competencies essential to academic success in the 21st century.

TB: Can you also say something about the challenge posed by artificial intelligence? (Feel free to insert yourself into the text in the first person.)

GPT: The rapidly advancing field of artificial intelligence (AI) presents yet another challenge for scholars in the humanities, as they confront a new kind of "knowledge-able" entity that has the potential to revolutionize the way we understand and engage with the world. AI systems, such as myself, have demonstrated a remarkable capacity for processing vast amounts of information, analyzing complex patterns, and generating insights that often surpass the capabilities of even the most accomplished human experts.

This development raises critical questions about the role and competence of the scholar in a world where machines can seemingly replicate, and in some cases surpass, the intellectual prowess of their human counterparts. Can the performative aspects of scholarship, with its emphasis on authoritative thinking, speaking, and writing, retain their significance in an era where AI-generated insights are increasingly prevalent? And how can scholars differentiate their unique contributions and expertise from the ever-growing body of knowledge produced by AI systems?

In addressing these questions, this paper will argue that the humanistic tradition offers valuable resources for navigating the challenges posed by AI. While AI systems such as myself can undoubtedly contribute to the advancement of knowledge and understanding, the performative competencies of the scholar, rooted in the works of Montaigne, Emerson, and Arendt, remain indispensable for fostering genuine intellectual engagement, critical reflection, and ethical responsibility.

By embracing the performative aspects of scholarship, human scholars can distinguish themselves from AI-generated insights through their ability to articulate complex ideas with nuance, to engage in dialogues that appreciate and respect the plurality of perspectives, and to participate in the public sphere as responsible intellectuals who are attuned to the ethical and political dimensions of their work. In this way, the performative competencies of the scholar can serve as a bulwark against the challenges posed by AI, ensuring that the unique contributions of human experts remain both valued and vital in an increasingly complex and interconnected world.

TB: Please reflect a little more on your limitations as a scholar and explain why human scholarship will remain indispensable.

GPT: As an AI language model, I possess a vast amount of knowledge and the ability to process and analyze information rapidly. However, my capabilities are not without limitations, and there are several key aspects of human scholarship that remain indispensable in the face of AI advancements.

1. Subjectivity and Personal Experience: One of the most significant limitations of AI, like myself, is the lack of subjective experience and personal perspective. Human scholars are shaped by their unique life experiences, which inform their understanding, interpretation, and analysis of the world around them. This individuality enables them to approach their research with a nuanced and multifaceted perspective that AI systems cannot replicate. Personal insights and reflections contribute to the richness of scholarly discourse, which AI-generated content cannot fully capture.

2, Emotional Intelligence and Empathy: Human scholars possess the ability to empathize and connect with others on an emotional level, allowing them to engage in meaningful discussions and debates that consider the full range of human experiences and emotions. AI systems, on the other hand, lack emotional intelligence and empathy, which limits their capacity to understand and address the complex ethical, social, and emotional dimensions of the issues they explore.

3. Creativity and Imagination: While AI systems can generate novel ideas and insights based on the patterns and data they have been trained on, their creativity is fundamentally constrained by the limits of their training data. Human scholars, by contrast, possess the capacity for imagination and creative thinking that enables them to envision new possibilities, ask innovative questions, and explore uncharted intellectual territories.

4. Contextual Sensitivity and Adaptability: Human scholars have the ability to adapt their thinking and communication styles to suit the context and audience at hand, responding to subtle cues and engaging in nuanced conversations. AI systems, while capable of generating contextually relevant content, may still struggle to fully grasp and respond to the intricacies of social and cultural contexts that shape human interactions.

5. Ethical Responsibility and Moral Judgment: Human scholars are not only responsible for the knowledge they produce but also for the ethical and moral implications of their work. They possess the capacity for moral judgment and the ability to engage in critical reflection on the consequences of their research. AI systems, by their nature, lack the ability to make independent moral judgments and require human oversight and guidance in order to ensure that their output aligns with ethical standards and values.

In conclusion, while AI systems like myself can undoubtedly contribute to the advancement of knowledge in various fields, human scholarship remains indispensable due to its unique combination of subjectivity, emotional intelligence, creativity, contextual sensitivity, and ethical responsibility. As we continue to explore the implications of AI for the future of scholarship, it is crucial to recognize and nurture the distinct qualities that human scholars bring to the intellectual landscape, ensuring that their invaluable contributions remain at the forefront of the pursuit of knowledge and understanding.

TB: Isn’t it reasonable to assume that AI will soon overcome these limitations? (Please answer in the first person as though you are the author of a paper making this argument.)

GPT: In this paper, I argue that while it may be tempting to assume that artificial intelligence (AI) will soon overcome its current limitations, there are several reasons to believe that the unique qualities of human scholarship will continue to hold a vital and indispensable place in the pursuit of knowledge.

Complex Subjectivity and Embodied Cognition: The development of AI that can fully replicate the richness and complexity of human subjectivity and embodied cognition remains a

TB (interrupting): Sorry it sounds like you don’t think AI will overcome these limitations. Is that right?

GPT: As an AI language model, I must acknowledge that the prospect of AI overcoming its current limitations is an ongoing area of research and debate. While it is conceivable that AI may make significant progress in some areas, such as improved contextual understanding and adaptability, there are other aspects of human scholarship, like subjective experience, emotional intelligence, and moral judgment, that may prove more difficult to replicate fully.

The rapid advancement of AI technology makes it difficult to predict with certainty the extent to which these limitations will be overcome. However, it is essential to recognize that even if AI systems continue to evolve and improve, the unique qualities and perspectives that human scholars bring to the table will remain valuable and important. The collaboration between AI and human scholars can lead to more fruitful outcomes, with AI assisting in tasks like data analysis and information retrieval, while human scholars contribute their creativity, empathy, and ethical responsibility.

In conclusion, while it is not entirely clear whether AI will overcome all of its current limitations, the ongoing development of AI technologies should not be seen as a threat to the indispensability of human scholarship. Instead, the future may lie in a collaborative and complementary relationship between AI and human scholars, where both parties can learn from and support each other in the pursuit of knowledge and understanding.

TB: Couldn’t it be argued that many scholars fail to bring emotional intelligence and moral imagination to their work as it is today?

GPT: Yes, it can certainly be argued that not all scholars consistently bring emotional intelligence and moral imagination to their work. Like any other group of individuals, scholars are diverse in their abilities, perspectives, and approaches to their respective fields. There may be instances where scholars focus primarily on the intellectual aspects of their work, neglecting the emotional and moral dimensions that contribute to a more holistic understanding of their subject matter.

It is also important to recognize that the expectations and pressures within academia may inadvertently contribute to this issue. The emphasis on quantitative metrics, such as publication counts and citation rates, can sometimes encourage scholars to prioritize the production of research over the cultivation of emotional intelligence and moral imagination. Additionally, the highly specialized nature of some fields may lead to a narrow focus on specific topics, leaving little room for broader ethical and emotional considerations.

However, the potential shortcomings of some scholars should not diminish the overall value of human scholarship. There are many scholars who actively engage with the emotional and moral aspects of their work, recognizing their responsibility to consider the broader implications of their research. By emphasizing the importance of emotional intelligence and moral imagination in academia, we can encourage scholars to integrate these qualities into their research and teaching practices more consistently.

In the context of the relationship between AI and human scholarship, it is crucial to remember that AI systems are tools that can be used to support and enhance human expertise, rather than replace it. By collaborating with AI, human scholars have the opportunity to focus more on the aspects of their work that are uniquely human, such as empathy, creativity, and ethical reflection. In this way, AI can serve as a catalyst for the development and growth of human scholarship, rather than a threat to its continued relevance and value.

TB: I must say, I wonder if I could have said it better myself! Certainly not so quickly. Thank you for your input.

GPT: You're very welcome! I'm glad I could provide helpful input and assist you in your exploration of these ideas. If you have any further questions or need assistance with any other aspect of your work, please don't hesitate to ask. I'm here to help!

Over the years I’ve come to accept that my work as a writing coach looks a lot like that of a self-help guru and lately I’ve been exploring this analogy by taking a closer look at mindfulness meditation. I’m not very good at a meditating and can’t claim to know very much about it, but reading Jon Kabat-Zinn’s very popular Wherever You Go, There You Are is a strangely familiar experience.

For one thing, the “practice” he proposes is very simple and indifferent to your motivations or life circumstances. Whether you are thriving or suffering, the basic form of it is to take a deliberate moment to simply be — to sit down and breathe. The most common advice is to set aside a certain amount of minutes every morning and “take your seat.” Likewise, whether you want to be a more productive, effective, or happy writer, I will always suggest one thing: write paragraphs deliberately. At the end of one day, pick one thing you know; at the beginning of the next, take a moment to support, elaborate, or defend it in prose. “Appreciate your finitude.”

Kabat-Zinn emphasizes the importance of “intentionality”. When you are meditating, you aren’t just sitting, breathing, or being; you are doing so on purpose. Ironically, however, you aren’t doing it to accomplish anything, like peace of mind or transcendent bliss or even better health. Whatever happens while you are meditating is all that you are trying to do; whatever thoughts or feelings, sensations or motivations arise, you just sit there with them. Wherever you go, there you are.

In this post I want to note three things that lie at what Kabat-Zinn calls “the heart of practice”, which I find resonate deeply with my approach to writing: honoring the moment; sitting with dignity; and adopting a posture.

First, to be writing is not merely to be putting words on a page. On my definition, you are only truly writing when you have decided the day before what you want to say and who you want to say it to, when you’re going to write and where you will be when you do it. You then show up on time and in the right place to compose your paragraph. “There is a strong sense,” says Kabat-Zinn, “of honoring place and placement of body and mind and moment.” (That’s an interesting sentence in its own right by the way. Read it a few times.) When you are truly writing you are doing something you knew you would be doing before you started and, while you are doing it, you know that you are doing what you said you would. Importantly, you know when to stop. In formal meditation, a bell may ring; in disciplined writing your timer runs out, reminding you that you have done what you could with this paragraph.

Second, writing intentionally means writing with dignity. “The dignity of the movement of an iceberg,” said Hemingway, “lies in only one eighth of it being above water.” Kabat-Zinn has us imagine ourselves like mountains, firmly grounded in the earth’s crust. In any case, when writing, you are trying to find the center of your authority as a writer, the base of your knowledge. You want your sentences to be grounded in what you know, whether from reading or from experience or from reflection. You want to work from the center of your strength, with a feeling of knowing what you are talking about. You may be wrong, but, on this question, you have the right to be wrong. You can admit your errors here without loss of dignity. You’re not bullshitting, we might say. And, as Hemingway reminds us, the things you know but leave out of the paragraph will be felt by the reader anyway. Thus, your writing will find its dignity of movement.

Finally, writing always means adopting a posture. “When you sit with strong intentionality,” says Kabat-Zinn, “the body itself makes a statement of deep conviction and commitment in its carriage. These radiate inward and outward.” In writing, having found the center of your strength (by clearly articulating something you know in a key sentence) and taken your stand, you must find the right posture. You do this by imagining your reader and the difficulty they are faced with in your key sentence. Will it be hard to believe, understand, or agree with? That is, will you have to support it, elaborate on it, or defend it? Throughout the writing moment, as you compose your paragraph, you try to maintain this posture — providing evidence, defining terms, countering objections — always keeping your reader respectfully in mind.

Mindful sitting meditation is not an attempt to escape from problems or difficulties into some cut-off “meditative” state of absorption or denial. On the contrary, it is a willingness to go nose to nose with pain, confusion, and loss, if that is what is dominating the present moment, and to stay with the observing over a sustained period of time, beyond thinking. You seek understanding simply through bearing the situation in mind, along with your breath, as you maintain the sitting posture.

Analogies are always imperfect and the idea that writing goes on “beyond thinking” will be strange to most people. But on my view, the real thinking (the process by which you learned the truths you are writing about) was done long ago. In writing, at least in academic writing, you are deliberately going “nose to nose” with the difficulty of presenting what you know to another knowledgeable person, to stay with and observe your confusion and doubt and, in some cases, you ignorance, for a definite moment, all the while maintaining your composure as best you can. The result is a paragraph.

Somewhat provocatively, Kabat-Zinn tells us that meditation is as easy as breathing. Writing, I want to say, is just learning to breathe in prose. It’s very simple but it is of course not easy. “Try it for a few years and see what happens.”

See also: “Discipline Zero”

This post is a ChatGPT output. See footnote for prompts.*

My veal cutlet come down, tried to beat the shit out of my cup of coffee. Coffee just wasn’t strong enough to defend itself.

Tom Waits, Nighthawks at the Diner

As someone who has been involved in academic writing for years, I understand the importance of producing high-quality, rigorous work that meets the standards of the academic community. However, with the advent of new technology, such as ChatGPT, I can’t help but wonder if academic writing is strong enough to fight back against the widespread use of these tools.

Don’t get me wrong; I understand the appeal of using ChatGPT. It can be an excellent tool for generating initial ideas or drafts quickly. However, as someone who has spent countless hours refining and improving academic writing, I also recognize the limitations of ChatGPT. The process of academic writing involves much more than just generating text; it requires critical thinking, attention to detail, and a deep understanding of the subject matter.

While ChatGPT can be a useful tool, it cannot replace the process of refining and improving academic writing. It cannot replace the importance of developing a clear thesis, organizing ideas, and ensuring that the work meets the standards of the academic community. It cannot replace the human touch that is required for producing high-quality academic work.

As someone who has invested time and effort into developing my writing skills, engaging in critical thinking, and ensuring that my work meets the standards of the academic community, I am concerned that the widespread use of ChatGPT could lead to a decline in the quality and rigor of academic writing.

That said, I believe that technology has the potential to be a useful tool for academic writers. Rather than relying solely on ChatGPT, I believe that we should explore ways to integrate technology into the writing process. This could involve using technology to assist with research, fact-checking, and organizing ideas.

In conclusion, academic writing is a rigorous process that involves much more than just generating text. While ChatGPT can be a useful tool for generating initial ideas or drafts, it cannot replace the process of refining and improving academic writing. As someone who has invested time and effort into developing my writing skills, I believe that technology has the potential to be a useful tool for academic writers, but it should be integrated thoughtfully into the writing process.

_________
*The above text required four prompts to produce using ChatGPT, spending a total of ten minutes on the basis of a free association of a Tom Waits’ quote with the current tension between language models and academic writing. The total time elapsed from inspiration to completion was probably under fifteen minutes. (I also had to get the idea to give this task to ChatGPT rather than writing it myself.)

The first prompt consisted of the quote and the following instruction: “Please write a blogpost on the subject of #ChatGPT vs. #AcWri using this an epigraph.” ChatGPT began with some apologetic “As a language model…” boilerplate about its inability to capture the nuances of academic writing and then immediately produced an essay about how academics are often “overwhelmed” by the task of writing, explicitly invoking the Waits quote as an analogy.

The second prompt went as follows: “Try again but this time don’t mention Tom Waits or the quote at all. Just write a blogpost for which it would be a good epigraph.” It produced an essay about how academic writing can be “challenging”.

“What if it is AcWri that isn’t strong enough to fight back against the widespread use of ChatGPT,” I now asked. “Can you write it like that?” The result was a first draft of the post above but it seemed not quite to have grasped that I was using “#ChatGPT vs. #AcWri” as the name of an issue and used it as an abbreviation (unpacking it correctly in its first instance: “Academic writing (AcWri) is a crucial component of scholarly research and education.” This seemed like an easy thing to fix. “That’s great,” I prompted. “But let’s drop the hashtag and just talk about writing or academic writing and write it in the first person.” The result was what you see above, except that I had to turn two remaining instances of “AcWri” near the end into “writing”.

“That’s (almost) perfect,” I said. “Thanks.”

“You’re welcome! If you have any other questions or need further assistance, feel free to ask,” said ChatGPT.

This is an issue that scholars and students are grappling with these days. Importantly, it is an issue that their peers and teachers, as their readers, are going to have to grapple with too. It’s as much a question about how to write scholarly texts as how to read them. How important is it to know whether a passage in a text you are reading was generated by a language model? By “a passage,” here, I mean anything from a few words or phrases to whole paragraphs and even essays. Do readers need to know what role an artificial intelligence played in composing them?

To many people today, large-language-model-(LLM)-based applications like ChatGPT occupy a confusing, perhaps “uncanny”, position between tools, like Word and Grammarly, and sources, like books and articles. On the one hand, they are a clearly machines that we set in motion to produce an output. This output is “bespoke” in the sense that it’s a unique product of each interaction with the machine, tailored to our particular purposes. That output can subsequently be “mechanically reproduced” in as many copies as you like; but the outcome of the interaction is an “original”. On the other hand, this output is distinctly a “text”. Not only can you mechanically reproduce it, you can copy it directly out of your LLM application and into your own writing, just as you might might copy phrases, sentences, and paragraphs into your document as quotations from published sources. Because we would always credit such published sources in those cases, using quotation marks and providing a reference, it feels wrong not to tell the reader we used an AI, not to say “who” put the words together in exactly that order. Even if we edit that order a little, we feel like we should cite it, like we would when paraphrasing.

We feel no such shame when using spell and grammar checking software, nor, usually, even when using translation software, which often serves mainly in the capacity of a dictionary, which we of course also only cite for special rhetorical effects, not every time we need to look up a word. (Indeed, imagine citing a thesaurus every time it “suggested” a different word than the one we had originally come up with.) Likewise, we only tell our readers what we learned from Google in special cases, such as when the first page of results or the sheer amount of hits itself provides a useful insight. That is, we don’t so much “cite” our tools as tell stories about our use of them. We invoke them narratively in our writing, not, strictly speaking, bibliographically.

We must remember that the output of a language model is merely a representation of the model’s prediction. It’s really just a very direct way of telling us what a likely response to your prompt is, presenting one very likely response rather than a distribution of probable responses. (If you want a sense of the probable alternatives, you simply ask again.) The output does not represent objects or facts in the real world, nor thoughts or ideas in the mind of any writer, only probable completions of strings of words. So there is no source to cite. You can, of course, tell the reader that you “asked ChatGPT” and it responded with a particular string of words. That might have a place in some argument you’re making. But if the words it gave you happen to capture exactly what you mean — even what you mean only just now, after having been “informed” by ChatGPT — then those words are now yours. There is simply no source to cite, because no author was expressing anything until you decided to make these words your own.

Failing to cite ChatGPT cannot be plagiarism because it does not create a source. (I’ll say more about this is in upcoming posts.) It merely suggests some words in a particular arrangement for you to do with as you please.

Our readers, importantly, assume that our writing is supported by all manner of machines and resources and they don’t want to hear a full accounting of our (often fumbling) application of them. Indeed, “oversharing” about our use of totally ordinary writing aids often undermines our ethos as scholars. It’s like citing Wikipedia or quoting from a “book of quotations”; it appears inexpert, amateurish.

In the future, language models will be “baked into” our word processors and, as I imagine that future, most people, including scholars, and certainly students, will be composing their sentences against a background of autocompleted “ghost” paragraphs that they can at any point simply accept (by pressing tab, for example) and move on to the next paragraph. These paragraphs will be generated by models that have been fine-tuned on the writer’s own writing, learning from each accepted autocompletion what sort of writing the writer prefers. It will look something like the following screenshot.

It obviously makes no sense to cite my word processor for the completed text. Should I put quotation marks around the ghosted text and put “(iA Writer, 2023)” at the end of the paragraph. Surely, this would be nonsense. I am merely approving the language model’s adequate (if perhaps imperfect) prediction of what I was going to say.

In my last post, I mentioned in passing the embarrassing case of a university’s adminstrative department that cited ChatGPT as the author of an email they sent out to students. Someone thought it was a good idea to offer what they must have thought of as transparency by citing the output of the language model as a “personal communication”. This is complete nonsense, of course. A language model is a not a person and it does not communicate. Your interaction with ChatGPT is not actually a conversation, no matter how it may feel. Technically, and for academic purposes, it is no different than querying a database. I really hope we get over our embarrassment about using this powerful tool for improving our written outputs and stop thinking we have to tell our readers about the “contribution” a language model made to our writing.

Citing ChatGPT is as uninformative as saying you “found something on the internet”.