A paragraph is a deliberate act. It presents one thing you know in at least six sentences and at most two-hundred words and, if you let it, takes exactly twenty-seven minutes to write. It occupies one minute of the reader’s attention, during which it supports, elaborates, or defends a proposition that you have good reason to believe is true. After reading, the reader may still have doubts, questions, or objections, but your position will be clear and you will have given the reader an occasion to tell you that you are wrong. You respect the reader as a knowledgeable peer and you want to know what they think. You have deliberately opened yourself to criticism.

It is my aim to help you become more capable of this act. You can find out how good you are at it by doing a simple exercise. At the end of today, at the moment when you put away your research and begin to relax, write a simple declarative sentence about something you are knowledgeable about. Choose something you find it easy to think and talk about, something that you’ve got your mind all the way around. Write one true sentence about it and plan to write a paragraph about it tomorrow morning during the first half hour of intellectually demanding work you will do. Then put it out of your mind. Tomorrow morning, compose a paragraph of at least six sentences and at most two-hundred words. Set a timer for 27 minutes and stop when it tells you to. That’s it. (Well, almost.)

Maybe you can already see the difficulty. If not, you will experience it concretely when you try it. In order to get a sense of what I am trying to teach you, imagine a sixteen week period (roughly, a semester) in which you do this exercise every day, five days a week. Imagine writing 80 deliberate paragraphs. Even if you didn’t listen to another word I say, I’m sure you will agree that this would make you a better writer of paragraphs. At the very least, it would make you accutely aware of the difficulty of writing paragraphs; and this awareness, I would argue, can’t but make you a better writer of prose. It would also, and not incidentally, make you a better knower of things. It would make you a more knowledgeable person.

In order to get something out of my approach, you don’t have follow such a rigorous discipline. But I do encourage you to practice as you go. I am a coach, not an entertainer. You will not really understand what I am trying to tell you if you don’t actually sit down to write some paragraphs of your own. And I really do mean “paragraphs of your own”. You want to become better at writing down anything you know in a way that opens it to the criticism of a knowledgeable peer. I don’t know you and I am not your peer, so you can’t expect me to tell you whether or not you are improving, nor give you simple recipes or templates to follow. You will be struggling to write down your own ideas for scholars or students in your own discipline.

If I were telling you how to draw hands I would tell you to look at your hand and draw it. Yes, I could assume that it has a front and back, fingers, wrist, palm, etc. (But not with 100% confidence, of course.) I could tell you to notice these things — their outlines and surfaces. But I wouldn’t know exactly what you see or how it would best be rendered on the page. It is the same when it comes to writing. I tell you to think of things you know, consider them carefully, think of your reader, and then write one or two hundred words to help them overcome the small difficulty your knowledge implies. That’s what a paragraph is: a measured little difficulty for your reader to overcome. It takes about a minute of their time and, like I say, when you’re working well, about half an hour of yours.

There’s a good interview with Rodney Brooks about artificial intelligence at IEEE Spectrum. I was struck especially by an idea that he has been promoting for some time, namely, that the way we generalize from performance to competence in humans cannot be applied to machines. If a human being is able to perform some cognitively sophisticated task we are warranted to assume that they can perform many other sophisticated tasks, whereas when a machine does something similar, we can’t use that as an indication of some underlying general competence. The reasons for this are nicely explained, as Brooks points out, by a recent blogpost by Stephen Wolfram, which everyone who wants to have an opinion about ChatGPT should probably read. The point is that once you know how ChatGPT does what it does, you can’t attribute sentience to it just because it uses language in an almost human way. By contrast, when a human body uses language, it is a clear indication of a deep and broad array of cognitive functions. As far as we know, human beings can’t use language without being sentient (and conscious and intelligent). And once we know this about them, we know a great deal about what they’re capable of, just from watching and listening to them speak.

This is why the sudden emergence of language models has been such a shock to many of us in academia. We have been accustomed to taking the performance of students in their writing assignments as a good indication of their knowledge competence. Consider the following paragraph, which I easily coaxed out of ChatGPT (3.5) in a few minutes:

According to Weick (1995), sensemaking is a reflective and retrospective process. Weick (1996, p. 54) defines sensemaking as an "ongoing retrospective process of forming images that justify what people are doing." It is a cognitive mechanism that individuals and organizations employ to comprehend complex and ambiguous situations. Sensemaking involves looking back at events and experiences, constructing meanings, and forging understandings. By interpreting and attaching significance to events based on existing mental frameworks, sensemaking allows for the creation of order and coherence amidst uncertainty. Weick emphasizes that sensemaking is an ongoing and iterative process, continuously evolving as new information and perspectives emerge. It encompasses the act of storytelling and constructing narratives to give meaning to our experiences. Sensemaking extends beyond the individual, serving as a social process that takes shape through interactions and conversations. It serves as a means to reduce ambiguity, facilitating decision-making in intricate and turbulent environments. Weick highlights the importance of sensemaking in generating and maintaining a coherent understanding of the world around us. Additionally, sensemaking plays a pivotal role in sensegiving, the process of effectively communicating and influencing others' understanding of a given situation. By elucidating Weick's perspective and incorporating his quote, it becomes evident that sensemaking is a fundamental tool for navigating complexity and making informed choices.

I gave it the key sentence “Sensemaking is a retrospective process”, the source (Weick 1995), and the quoted definition (from memory, wrong year, wrong page). I had it think about how to pitch the key sentence, brainstorm some sentences for the body of the paragraph, and then compose one coherent paragraph that helped the reader understand Weick. After a little more back and forth, the result was the above paragraph. At no point did I edit the paragraph. That is, none of the sentences are mine.

I then asked it to “construct a one-paragraph description (a story) of sensemaking in action to illustrate these ideas”. It gave me this:

Sarah, a project manager, found herself facing a daunting challenge. The unexpected departure of a key team member had left the project in disarray, with looming deadlines and a complex web of interdependent tasks. Engaging in sensemaking, Sarah began her reflective journey. She revisited past team meetings, scrutinized project documentation, and engaged in conversations with remaining team members. As she immersed herself in this retrospective process, images started forming in her mind, providing justifications for the team's current situation and possible paths forward. Sarah realized that the departure of the team member had disrupted the workflow, leading to miscommunication and overlapping responsibilities. Drawing upon her mental frameworks, she began constructing a narrative, identifying the root causes and envisioning potential solutions. She engaged the remaining team members in discussions, seeking their perspectives and insights. Together, they collaboratively made sense of the situation, aligning their understandings and identifying actionable steps. Through this ongoing and iterative sensemaking process, Sarah and her team regained clarity, rebuilt cohesion, and developed a shared understanding of the project's direction. Sensemaking not only empowered Sarah to navigate complexity but also fostered a collective sense of purpose, enabling the team to move forward with confidence and resolve.

Now, there is perhaps nothing Earth-shatteringly brilliant about these two paragraphs. But, in the old days, working on the assumption that the student had actually written them, I would have inferred a relatively deep underlying competence in them. The student is able to present an understanding of what they have read; indeed, they could presumably not have written that paragraph without reading Weick. Also, they are able to imagine or observe a reality that corresponds to the concepts they have introduced. It could be argued that the “imaginative” or “empirical” material is a bit abstract. But it didn’t take me much more coaxing to get ChatGPT to give something more concrete:

But the piles of data on Sarah's desk weren't sufficient. She craved the human insights that could illuminate the path forward. With determination, she picked up the phone and called the remaining team members, inviting them for a face-to-face discussion.

In a small meeting room, Sarah sat across from John, a seasoned team member who had been with the project since its inception. She leaned forward, her voice earnest, "John, I need your help. I want to understand what went wrong and how we can fix it. Tell me about your experiences and frustrations."

John's brow furrowed as he recalled the recent challenges. "Well, Sarah, since Mark left, communication has become a nightmare. We used to have regular team huddles where we shared updates, but without him, things have fallen apart. Everyone seems unsure of their responsibilities, and tasks are slipping through the cracks."

Sarah nodded, her notepad ready to capture every valuable insight. "I see. Can you provide specific instances where miscommunication occurred? Any ideas on how we can improve the clarity of roles?"

John scratched his head thoughtfully. "One example is the client meeting last week. We were all working on different aspects of the project, but nobody knew what the others were doing. During the meeting, the client asked questions that none of us could answer. It was embarrassing and made us look unprepared."

Sarah scribbled notes, her mind racing to identify patterns. "So, improved communication and clearer role delineation are crucial. What suggestions do you have for addressing these issues, John?"

John leaned back, his expression thoughtful. "We need a central hub for information, where everyone can access updates, share progress, and see the big picture. Regular team meetings should be reinstated, so we can align our efforts and address any roadblocks together. And we need to clarify each team member's responsibilities and establish clear lines of communication."

Sarah's eyes lit up with excitement. "Those are excellent suggestions, John. I truly appreciate your insights. Let's discuss these ideas with the rest of the team and see how we can implement them effectively."

As Sarah continued her conversations with other team members, she encountered similar stories of miscommunication, frustration, and potential solutions. Jennifer, a detail-oriented analyst, shared her experiences with overlapping responsibilities that resulted in redundant work. David, a junior developer, expressed his struggles to navigate the project without clear guidance.

Armed with these specific insights, Sarah synthesized the collective wisdom and proposed tangible actions during their next team gathering. The air buzzed with anticipation as Sarah laid out the proposed central hub for information sharing, the reinstatement of regular team meetings, and the need for role clarity. Dialogue ensued, with team members offering further suggestions and refining the proposed solutions.

Through these concrete conversations and shared experiences, Sarah and her team co-created a roadmap for moving forward. They set deadlines for implementing the new communication practices, assigned responsibilities for maintaining the central hub, and established a process for clarifying roles and expectations.

The team members left the meeting feeling heard, energized, and part of a collective effort. Concrete steps had been taken, thanks to the specific insights shared during their conversations. The path forward was clearer, and a sense of unity and purpose permeated the team.

Again, this isn’t profound stuff. But a human student who could do this, either through imagination or observation, would be showing they can do many other things. I keep saying “imagination or observation” because, in the case of a human student, such an account may be presented as made up or as based on data. We expect the student to be honest about such things, and if the account really were empirical we would expect them to be able to write a plausible statement of method. From this performance (of writing a methods statement) we would again infer all manner of underlying competence.

But ChatGPT can give us such a statement too. In a perhaps unnecessary attempt to avoid certain “safety” measures, I prompted it to “imagine that the account is the result of participant observation by an ethnographer. Write a paragraph for the methods section in which you imagine how the data the account of Sarah’s sensemaking is based on.” After giving me an explicitly imaginary account of “an ethnographer”, I asked it simply to rewrite it in the first person as a straight statement of method.

As an ethnographer, I immersed myself in the project management context to conduct participant observation and gain insights into Sarah's sensemaking process. Over an extended period, I actively observed team meetings, carefully documenting the dynamics, non-verbal cues, and communication patterns. I took detailed field notes, capturing the atmosphere, interactions, and notable events. Additionally, I engaged in informal conversations with Sarah and other team members, both individually and in group settings, to delve into their experiences, frustrations, and suggestions. These conversations were audio-recorded to ensure accurate representation. To supplement my observations and interviews, I thoroughly reviewed project documentation, including meeting minutes, task assignments, and relevant correspondence. The data collected through participant observation, field notes, interviews, and document analysis were meticulously analyzed and synthesized to construct a comprehensive account of Sarah's sensemaking journey. Through my firsthand involvement and interpretation, I aimed to provide an authentic and nuanced portrayal of the project's context, Sarah's challenges, and the collaborative sensemaking process that unfolded.

I really wish we could still use the writing students do at home to gauge whether they have learned what we were trying to teach them. But examples like this are enough to completely undermine my faith in such performances as indications of actual competence. Going forward, I only want to look at writing from students that was produced off-line. I want to know what they are capable of without the assistance of AI.

* * *

PS. All the outputs in the above post were generated using ChatGPT model 3.5. I gave the long ethnographic passage to 4.0 and asked it to help me write a methods statement. Here’s its first attempt:

Based on the ethnographic description provided, here is a potential methods statement:

This ethnographic study adopts an interpretative, qualitative approach to understanding project management under crisis conditions. The research method includes direct observation and engagement with the research subject, Sarah, a project manager. The research subject was observed in her natural environment at her workplace to understand her behaviors, actions, and interactions in a real-life context.

Sarah's activities were meticulously documented as she navigated through a crisis caused by the sudden departure of a key team member. The observation involved recording her approach to problem-solving, including her reflective analysis of previous records, her communication with team members, her mental processes during decision-making, and her efforts towards group sensemaking and decision-making.

Primary data collection involved the naturalistic observation of Sarah's behaviors, conversations, and interactions, supported by the collection of project-related documents like meeting notes and records. Additionally, informal interviews were conducted with Sarah and her team members to gain further insight into their experiences, frustrations, perspectives, and potential solutions.

The analysis process was inductive and iterative, informed by grounded theory. This process helped to identify patterns, themes, and emergent properties related to team communication, role clarity, and collective sensemaking. These findings were then used to construct a narrative that detailed Sarah's sensemaking process during crisis management.

Sarah's experiences were triangulated with the insights shared by the other team members. This approach allowed for a richer, more nuanced understanding of the crisis situation and how the team navigated through it. The interpretive approach allowed for the examination of the shared sensemaking process, enabling the research to delve deeper into the team's collective resilience and problem-solving approach.

The outcome of this research is intended to provide insights into effective crisis management strategies, with a particular focus on the importance of collaborative sensemaking. It is hoped that these findings will contribute to the broader literature on project management and organizational behavior, as well as provide practical insights for those managing teams under crisis conditions.

I then asked it for a background description of Sarah’s organization.

Sarah's organization, InnoTech, is a leading mid-sized tech company located in San Francisco, California. With a workforce of approximately 500 employees, the company specializes in developing cutting-edge software solutions that address the critical needs of businesses across various sectors, including healthcare, finance, and e-commerce.

InnoTech has a reputation for fostering innovation and technological advancement. It's been in operation for more than a decade and has become well-regarded for its pioneering contributions to the tech industry, primarily through its suite of productivity-enhancing applications and data analytics platforms.

The organization prides itself on its agile work environment and flat hierarchical structure. Teams within InnoTech function as autonomous units, each overseeing different projects with specific goals aligned with the company's broader mission. This structure promotes a high degree of collaboration, enabling cross-functional teams to work seamlessly together.

Sarah's team, known as the Phoenix Project Team, consists of developers, UI/UX designers, quality assurance engineers, and product managers. Their role is to conceptualize, design, develop, and launch new software products aimed at enhancing business productivity.

The company's culture emphasizes continuous learning and improvement, fostering a climate of creativity and risk-taking. It invests significantly in its employees, offering them opportunities for professional growth and development. There's also a strong focus on maintaining a positive work-life balance, reflected in flexible working arrangements and comprehensive employee wellness programs.

However, despite its positive attributes, the organization isn't immune to challenges. As depicted in the ethnographic description, sudden staff departures and project disruptions can put immense pressure on teams, necessitating robust crisis management strategies. It's within this context that Sarah, as a project manager, navigates her role, working to ensure her team effectively overcomes obstacles and delivers on their project objectives.

with apologies to Dave Brubeck

Here’s an exercise I gave to my students (in two different classes) last week. It takes fifteen minutes in all (plus time to explain it and debrief it) and it requires your class to have reached a stage where the students can be asked to call both an object and a set of concepts to mind, they must be able to easily imagine a body of empirical fact and put it in a familiar theoretical perspective. (In one class — an undergraduate management class — the students had been listening to a podcast each week about a different innovation and reading various innovation theories; in the other — a professional master’s class — the students were working on an analysis of their own organizational practice applying an organizational discourse approach.) The exercise contains both an individual component and some work to be done in pairs. (In the case of an odd number of students, there will be one group of three.)

In the first part of the exercise, students are given five minutes to prepare an oral presentation for one of their fellow students. In five minutes, they have to pick an object that they are familiar with from the class — a product or a process, an action or an event — to focus on; they also have to pick a theoretical perspective that will give them “categories of observation” (concepts) with which to analyze it; and they have to plan out a presentation following the standard outline:

1. Introduction
2. Theory
3. Analysis
4. Discussion
5. Conclusion

The presentation is to take five minutes. They are to imagine a presentation that devotes roughly one minute to each task, keeping them relatively pure. That is, the first minute will introduce the object, the theory, and their thesis, telling the listener something about why this interests the speaker. The second minute will focus on the theory, presenting the concepts that will be used in the analysis, but not yet doing the analysis itself. The third minute will present the analysis, taking the concepts for granted, and interpreting the facts based on observations. The fourth minute will present implications for theory or practice and the fifth minute will summarize, conclude, and round things off.

In the second part of the exercise, one student presents what they come up with for a partner. (If there is a group of three, this person has an audience of two.) Before they begin, I remind them that they have a minute to get through each part and that silence is very acceptable. If they can’t think of any more to say by way of introduction, they should just sit there and think about how to talk about theory for the remaining seconds; when they run out of things to say about theory, they should silently consider what they’ll say about their analysis. Importantly, except for minor reactions (nodding, smiling, laughing, groaning) the listener is not to contribute; it’s not the listeners task to break a silence. As every minute passes I simply announce that it is time to move on.

In the third part, the other student presents in the same way. (If there was a group of three, one person will present to the teacher, the other will present to the previous presenter.) This time, before starting the clock, I remind them of what they are about to do. The second speaker has a much better sense of what is possible because they’ve just heard someone else do it. Also, I remind them that it’s fine to be tentative and informal in the presentation; they don’t have to present a finished idea, but could just present a hunch or hypothesis. The important thing is to move through the five moments: introduction, theory, analysis, discussion, conclusion. You’re not trying to impress anyone or win an argument; you’re trying to see what you have to say. Some of the students discovered that the last minute could actually include a question or two from the listener: the speaker provides a quick summary and adds, “Any questions?”

At the end, I point out that five minutes isn’t a very long time. But it is in fact the time it would take the ideal reader to read the ideal five-paragraph essay. Such an essay would take, again ideally, two and half hours to write. So we can imagine spending two and half hours preparing the same presentation. How much better would that go? I also suggest they try framing it very formally. Make five slides to present, book a group study room, maybe invite a few more students to watch, and dress professionally for the occasion. Now do a five-minute pitch. All of this is simply to show them that putting deliberate effort into presenting their ideas in a finite amount of time is a worthwhile thing to do. And then there’s that essay they have to write for the exam anyway (both classes are working towards a 5-page, 9-11-paragraph final). I’ve just given them 15 minutes to experience how ready they are. They can give themselves that experience again any time they want. And two and half hours is plenty of time to write five actual paragraphs. They can try just doing that to prepare the presentation.

My view is that if you know something “for academic purposes” then you are able to compose a coherent prose paragraph about it in half an hour. As an academic writing instructor, that is what I teach; my core “learning objective” is the ability to support, elaborate, or defend a clearly stated proposition using at least six sentences and at most two-hundred words in twenty-seven minutes. I believe this is a valuable skill and that students do well to direct a significant portion of their energies while at university toward developing it. The ability to write about things you know at a rate of two paragraphs an hour is one you want to have. It will help you, not just get through university, but make a useful contribution to professional and civic life. It’s something I know how to help you get good at.

It’s also something I can show you how good you are at. (I say “show you” advisedly because I normally refuse to tell you. If you’re following my instructions you don’t need me to decide whether or not you’re improving, just as you don’t need your personal trainer to tell you that you’re getting into shape. You can feel the improvement yourself.) Take a moment at the end of each day to prepare a moment at the beginning of the next in which to write a paragraph that you will then seek feedback on from a peer. My ideal student will write 80 paragraphs in 16 weeks this way and receive (and give) 720 minutes of peer feedback. Every two weeks, they will submit a five-paragraph essay, and receive a grade that suggests how well they’re writing relative to their cohort. At the end, they will sit for a 3-hour exam, writing yet another five-paragraph essay, which they will then discuss with me for 20 minutes (ideally, on the same day they wrote it). Their grade counts for half their course grade.

Let me say at once that none of my students are ideal and I have never been given a chance to try to examine them under these conditions.

At this point, however, I am sometimes accused of “ableism”. Or maybe I have this time succeeded in presenting what I do in such a way that the charge doesn’t seem as natural? After all, I am tying the test directly to the competence that I am trying to teach, to help the students develop. If I were teaching them how to calculate bond prices I would not be accused of ableism if I asked students to do a bond price calculation. Since I am trying to teach them how to write paragraphs and essays, getting them to write one for me to show me what they have learned should also, I hope, seem entirely reasonable. It is only my suggestion that being able to write a paragraph is a reasonable test of whether or not you know something that might still cause alarm bells to go off for some disability scholars. And not just disability scholars, actually. My view is sometimes also considered “classist” — indeed, even sexist and racist. The idea is that conventional prose is the “privileged” domain of “normal” people, where they have an unfair advantage over various groups who are marginalized, socially or materially, by birth or by accident. “The normate subject is white, male, straight, upper middle class,” Jay Dolmage tells us; “the normal body is his, profoundly and impossibly unmarked and ‘able.'”

The criticism that is sometimes levelled at my approach to writing is that I privilege this subject. I have tried to address the underlying idea that conventional (or “normate”) prose is exclusionary in a previous series of posts that respond directly to Dolmage’s arguments “against normal writing”. In the rest of this post, I want to acknowledge the undeniable practical problems that my approach poses for some students and scholars and, once again, defend the radically inclusionary nature of prose as a means of communicating ideas. In my view, requiring students to express themselves in prose is the best means we have for levelling the playing field for a socially and materially, mentally and physically, diverse student body.

The idea of a level playing field was recently invoked by Jennie Young, the director of the first-year writing program at the University of Wisconsin at Green Bay in her piece in Inside Higher Ed on the “boon” that artificial intelligence will be for writing instruction. “It’s going to help level the playing field,” she argued: 

Here’s the truth about the “achievement gap” in writing skills: students who have professional parents and who went through K-12 in higher socioeconomic school districts tend to graduate knowing how to structure an essay and write grammatically correct sentences (for the most part); first-generation students who went through K-12 in underresourced and lower socioeconomic school districts do not graduate with these skills nearly as often. Here’s the very important takeaway from this disparity: the disparity is environmental, not biological. In other words: the students who know how to structure an essay and write grammatical sentences are not more intelligent than those who don’t.

My immediate reaction to this idea was: Yes, good writers are not necessarily more intelligent than bad writers, but they are better writers. And, as a writing instructor, I see my job as helping students become better writers, not to diminish the value of good writing so that those who don’t “know how to structure an essay and write grammatical sentences” can still be recognized as the capable thinkers they may yet be. In fact, I explicitly tell students that one reason to learn how to write is to make sure that they are recognized for their (brilliant) ideas, not their (struggling) style.

Also, I don’t like the idea of crediting writing ability merely to a certain kind of upbringing. I think students who can write well should be able to take pride in that ability, not have it dismissed as the unearned wealth of “privilege”. After all, many working-class students succeed at university, and, later, in academic careers, precisely because, through hard work, they master the conventions of academic prose and outperform their wealthier rivals. And, while it is true that good writing runs in certain families, it is by no means easy for all wealthy students to write well and, surely, parents who “raise their children right” (in my personal opinion), to compose themselves in coherent prose paragraphs, should not be told by first-year writing instructors that it’s a wasted effort. It may be true, as Young seems to believe, that good writing isn’t any kind of proxy for other kinds of learning, but, even if that were true (and I’m not entirely ready to grant this), it is still an indication of writing ability, which has value in its own right. Or, that, anyway, is what I’ve been telling myself all these years working as a writing instructor.

In short, I’m not willing to abandon my ideal of a timed, on-site, invigilated written exam in the name of “universal design”, because I believe that the ability to write a coherent essay under formal constraints is one that is worth having. If a student is completely prevented from doing this by a particular disability they are, unfortunately, prevented from succeeding academically, or at least severely limited in this regard. I think we need to be honest about this. Fortunately, prose, by its very nature, accommodates pretty much any disability.

To demonstrate this, by way of conclusion, let me recall the example of Jean-Dominique Bauby, the French magazine editor who suffered from “locked-in syndrome” after a stroke. He constitutes an almost pure example of someone whose in-ability to write (he couldn’t even lift a pen) cannot be interpreted as a lack of learning or intelligence. We know this because he was able to dictate an entire book by blinking his eyes.

On my approach, someone like this would of course need special accommodations. But I think I would take a somewhat hard line on the process. If he had indeed followed my class, I would also have expected him, like my other students, to compose a paragraph a day, albeit in his head, and to have “dictated” it (again, by blinking his eyes) to the stenographer, who, I expect, would have been provided to him under the terms of his accommodations. For the exam, he would be given three hours, also like everyone else, but to this would be added the time it would take for him to communicate his compositions to the stenographer.

That is, he would still be required to compose a 1000-word essay in three hours. It’s just that the physical process of getting it down on the page would take a little longer and require some additional means. The best way to do this would probably be simply to stop the clock for him every time he was ready to dictate something (I think it would be unfair to require him to hold an entire essay in his mind and then dictate it all of a piece, although, as I understand it, this was in fact Bauby’s approach, composing and dictating the book one chapter at a time.) But I think it would be unfair to the rest of his cohort to just let him write the essay in his own way at his own pace. That would simply be abandoning the principle of composition in moments that my class had been teaching.

Maybe you can think of a better way to accommodate Bauby or a disability that would be more difficult to accommodate? To my mind, the ability to accommodate such an extreme disability demonstrates that requiring prose composition under formal constraints is not an ableist pedagogy. Indeed, it is the most “universal” design for education that can be imagined. Knowledge-able people are both able-to-know things and en-abled by their knowledge to do things. One of the things they can do is to write.

…and count myself a king of infinite space.

Hamlet

I’ve been feeling a lot of resistance to (and getting some thoughtful pushback against) my suggestion that only a return to on-site examination will be able to preserve the integrity of written exams in higher education in the coming age of artificial intelligence. In particular, people don’t seem to like the idea of requiring students to produce roughly a thousand words in response to a given prompt in three hours at the end of a semester. As I understand it, they would prefer to require students to put together a portfolio of work done, both at home and in class, throughout the semester. I also get the sense that many of the people who express displeasure at my idea would prefer not to give grades at all, while I sometimes, when I’m feeling bold, go so far as to suggest grading on a curve. (This is not an option in Denmark, where it is literally against the law.) I think we all agree that students should get as much feedback on their writing as possible as part of their instruction. The point of contention is how (and, like I say, sometimes whether) a grade should be assigned at the end.

In my last post, I tried to imagine a course on Hamlet in which the final grade was based solely on four in-class essays, though students would also write four take-home essays for which they would be given an indicative grade to gauge their performance. I’ve previously described what I think of as the ideal exam (a 3-hour written exam followed immediately by a 30-minute oral examination). In all cases, the important thing is to develop a prompt that a student who has taken your course should be able answer intelligently given three hours and a set of materials you have selected for them. That is, you should be able to imagine a three-hour performance of the competence that you had been trying to inculcate all semester. If you cannot imagine something a student of yours should have become good at doing for three hours, nor how you would judge how well they have done it if they do it, I fear that your learning objectives are mere abstractions.

In order to understand what I mean, consider another classic set-up for a course on Shakespearean tragedy. As a quick aside, it recently occurred to me that Shakespeare is a great example precisely because his profound influence on the English language means that knowledge of his work is literally “baked in” to the parameters of large language models like OpenAI’s GPT. (Just try prompting ChatGPT with the question, “To be or not to be?”) That means Shakespeare is simultaneously the most important author to teach English majors and easiest to fake knowledge of using artificial intelligence. Anyway, imagine a course in which students are to read three tragedies: Hamlet, Othello, Macbeth, as well as various theories of Shakespearean tragedy. We can, again, imagine a 16-week course, here with 4 weeks devoted to each play bookended by 2 x 2 weeks devoted to general ideas. You can assign whatever homework and in-class activities you like throughout the semester; I want to focus on what happens at the end.

After the last class, the students are given a week or two to prepare for the final exam, which consists of a prompt that relates to one of the three plays. Students may use whatever theories they like from the course to frame their arguments. They are given three hours to write up to a thousand words. (Ideally, they would then also defend their writing orally. But this is not necessary for the point I’m making here.) It seems natural — but I’ll leave it up to you — to give them the text of the play they will be writing about. You may also let them have access to the theoretical literature that you discussed in class so that they can quote from it. I would not, however, let them bring notes from their reading or (for the same reason) their own copies of the texts. You want to know what their minds and bodies are capable of in direct confrontation with the materials. You don’t want to give them the challenge of putting together a binder full of good original prose about each play and each theory that they can then transcribe in the examination room. After all, that binder can be filled with paragraphs written by an AI.

To me it seems obvious that these conditions would give students ample opportunity to demonstrate their familiarity with Shakespeare’s plays and their understanding of tragedy. (If you don’t think these are important things to know about, that’s fine; imagine another course, other texts, other issues.) Since the students would not know in advance which play would be assigned, we can assume (though it’s a game of probabilities, of course) that they know the other two plays as well as the one they happen to be examined in. And since the student knows what the task is in advance, we can assume that they’ve gotten themselves and their prose into shape and are performing as writers “at the top of their game”. In part, we testing them on their ability to pull off this performance. I think we can rest assured that if they do well here, they are capable of many other things.

That’s really the thing that I think my critics underestimate. Hamlet complained that Denmark was a prison but admitted that it was, to a certain extent, all his mind (“there is nothing either good or bad, but thinking makes it so”). Were it not for his disturbing dreams, even “bounded in a nutshell” he would “count [himself] a king of infinite space”. For my part, I’m fond of quoting Ezra Pound’s ideas on form; “think of it as center around which, not a box within which,” he said. We are not confining our students to the examination room for three hours, nor limiting them to a thousand words. We are, I would argue, affording them an opportunity to exercise their knowledge and imagination, to articulate the prose of their world. Just as a trained musician who is given a score and an afternoon can offer a competent interpretation, or a skilled carpenter can turn a pile of wood into a sturdy table in a few hours, so too can a learned scholar produce an interesting analysis of a work of literature in three hours. Given only half a day, it may not be their “best work”. But knowing what the terms were, we can certainly use the result to judge their abilities.

At about this point, I imagine, you are thinking about how to accommodate their disabilities. That’s the topic of my next post…