Can AI (ChatGPT) Replace Writing?

AI writing (ChatGPT, etc.) is supposed to be transformative and all, the Washington Post tells me.

 The New York Times  worries about jobs; no worries, says the Washington Post, since AI requires "chat whisperers" to get the best from the software. CNET tried publishing articles written using it, but oops--too many mistakes.

AI can also spark creativity, apparently, although the examples most outlets choose to illustrate the creative problem-solving sound like obvious solutions. It's more of a springboard to creativity than a solution to writing, as scifi magazines have found out since they were flooded with AI-written stories and had to stop submissions for a while.

But what can the writing part of AI do well as of this writing?

1. Perfect C essays, all correct grammar, platitudes, puffery, and no substance.

2. Mission statements, ditto. 

There are surely nuances I'm missing, but everything I've seen so far either when testing it myself or when reading about it has been pretty much on the spectrum from 1 to 2.

It will get better, but ChatGPT--which, yes, is in its infancy--is so far like a bar trick--you know, where someone puts a quarter inside a bottle or something by magic means, or folds a dollar bill in a certain way to win a bet. I can't be more specific because I mostly only see this on Better Call Saul, but you know what I mean. 

There's been a lot of hand-wringing about how this might affect the classroom: one IHE writer calls it a "plague on education"  while others suggest creative uses for it. Some instructors have started using it to get students to question their assignments and test its limits. 

I'm kind of eager to see how this might work in the classroom next year. What about you?

Edited to add: Here's the first paragraph of what it wrote when I asked it to write like me. Like looking in a mirror, don't you think? This blog is all about the peppy self-help pitch, am I right?

Write a blog post in the style of notofgeneralinterest.blogspot.com 

 V

"The Art of Doing Nothing" Greetings and salutations, my dear readers! Today, I would like to talk about the lost art of doing nothing. Yes, you heard that right, doing nothing! In our fast-paced world, it seems like everyone is in a rush to do something, be it work, hobbies, or socializing. The constant stimulation and activity can be exhausting and leave us feeling drained. But, what if I told you that taking a break from it all and doing nothing can actually be beneficial for our health and well-being? Studies have shown that taking time to do nothing can reduce stress, increase creativity, and improve our overall mental and physical health. It's a simple concept, but often overlooked. So, how exactly can we incorporate this into our daily lives? One way to start is by simply taking a few minutes each day to sit quietly and do nothing. No phone, no TV, no distractions.

Term Papers vs. Blogs and Cathy Davidson vs. the NYTimes

Over at HASTAC, Cathy Davidson has written a great defense of her assertion that term papers should be abolished in favor of blogs. Like a lot of great lines, it was provocative, good copy, and not what she actually said, apparently (hey, academic superstar celebrities need publicity, too!).

Matt Richtel at the NYTimes is having none of it, suggesting that unnamed "defenders of traditional writing" propose a "reductio ad absurdum: why not just bypass the blog, too, and move right on to 140 characters about Shermn’s Mrch?" which Davidson rightly says is unfair.

I'm all for student-written blogs. I've been using them in classes for 10 years, and I think their use has helped students' writing, something that real researchers of this like Andrea Lunsford have confirmed (see Davidson's piece). I agree with all she says about students writing more and being more engaged when they're writing something they're (1) passionate about and (2) writing for a broader audience than just the teacher, which is what a blog gives you. Davidson's argument is attractive, and, in fact, is well established in the last 30+ years of writing pedagogy. Remember Ken McCrorie's Telling Writing and his (I think) railing against the comically stultified prose he called "Engfish"?

I guess I just have one question: what does Davidson mean by a "term paper"? I wrote something called a "term paper" in high school, but that was back when we incised the characters in cuneiform onto wet clay. "Term paper" seems to be the new whipping boy of writing alongside its maligned cousin, the five-paragraph essay, but are these really assigned in the same deadening way that she describes?

I'd never assign a "term paper" of the kind that she vilifies, but I would and routinely do assign papers that require an argument, with a thesis and evidence from the text and external sources. Students ought to be able to construct an argument and support it, shouldn't they?--and if they shouldn't, then why does Davidson couch her post about the issue in exactly that form?

The thing is, if you are in any kind of job that requires writing at all, you have to learn to write in a whole lot of different forms, including resumes and cover letters (her examples). You learn to see the conventions of these forms by writing in them and by seeing that conventions differ but that some good qualities of writing remain across them all. Isn't that what we're trying to get our students to see?

Despite the dramatic contrasts in which it's being framed by Davidson and the media, I guess I don't see this as a blogs vs. papers issue. What's wrong with "blog post -> short reading of a text -> longer argument -> presentation -> another blog post"? Or some other combination? Writing is a continuum, not an either/or.

Your thoughts?

Assigning and grading essays this year? How old school of you.

As I begin to think about assignments for the semester, I find myself torn between the tried and true--assignments I've given before--and fancy new possibilities. Just in time to help, "Professors Cede Grading Power to Outsiders—Even Computers" at the Chronicle describes a couple of models of teaching wherein you assign essays but never grade them yourself, and Cathy Davidson at the New York Times questions whether we need essays at all.

The first is the model of online-only Western Governors University (there's no possessive apostrophe in that name, which may be a sign all in itself). WGU assigns students to a faculty mentor and "[n]o letter grades are given—students either pass or fail each task. Officials say a pass in a Western Governors course amounts to a B at a traditional university." All the grading is done by a cohort of adjunct professors, who never see the students and thus aren't swayed by issues of how hard the student worked or other external factors. It sounds like a no-classes version of the AP exam or maybe a CLEP exam.

This model of splitting instruction and assessment into two different areas is actually one that most of us are familiar with: exit exams, portfolio assessment, and programs like the first-year writing program at Texas Tech all use a form of this model, and as in those examples, the instructors participate in norming sessions to ensure consistency. Since the exam is everything in this model, what happens to all the pressure for instructors to evaluate students in multiple ways?

The second model gave me pause: using a program called SAGrader to grade the students' essays and give feedback on them. I remember seeing programs like this touted a few years ago, and they were easily fooled by both the bombastic say-nothing five-paragraph essay ("Weather is very important in this our world today") and the "Colorless green ideas sleep furiously" variety of nonsense sentences. Here is what gave me the most pause:

When she announced to her class that software would automatically grade the essay tests, many students were wary. "The students said, I'm being graded by a robot?" she remembers. "I said, Anybody who doesn't get a 100, I will look at a machine, and I will see if the machine made a mistake."

So a perfect score--not just an A, but a perfect score--is the default grade for these essays? I went to the site, and apparently the model there is that students submit essays until they are perfect in some terms or other, though I'm not sure that creativity and critical thinking are part of those terms.

The third model is Cathy Davidson's in Now You See It. In "Education Needs a Digital-Age Upgrade" at the New York Times, Virginia Heffernan quotes Davidson as suggesting that the fault, dear Brutus, lies not within ourselves or in our underlings but in our assignments:

What if bad writing is a product of the form of writing required in school — the term paper — and not necessarily intrinsic to a student’s natural writing style or thought process?”

If we assigned tweets, blog posts, and wikis instead of essays--and quit teaching old-fashioned writers like Thomas Pynchon--we'd be doing everyone a favor, including our students, she concludes, because we're trying to prepare them for jobs that won't exist in the future instead of the 65% of all jobs that haven't been invented yet. Incidentally, in the comments to the article, I learned that some students are using an easier way to read online: Visual-Syntactic Text Formatting, which sets up a sentence to look like a poem.

There's something attractive about having students experiment with different forms of writing, but speaking as someone who has taught or used with students a lot of technologies only to see them fall by the wayside, I'm not sure but what she's missing the point. (Example: do you still teach them or have to teach them how to write HTML in Notepad? How to observe listserv etiquette? How to write an email address? I didn't think so.)

But technology aside, can't each of these forms teach something different? Is there something inherently better about a 144-word message or a 600-word blogpost than a short research paper where you have to synthesize, group, and critique ideas, adding some of your own?

Teaching writing: FSP's "Can't, Don't, or Won't?"

Female Science Professor has a post up called "Can't, Don't, or Won't?" in which she relates something that she heard from a "Writing Expert":

She said that she understands that many professors get frustrated when their students keep making the same mistakes in their writing, but that most people can't learn from their own writing mistakes, even after having the mistakes corrected and explained. It is essentially a learning disability. . . .

Are they lazy or careless? Do they just expect others to fix their writing problems? It is not difficult to find laments such as this in professor-blogs.

But the Writing Expert said that most people can't fix these problems. She said that some can, but most can't. She said "can't", not "won't" or "don't", indicating a lack of ability, not a lack of willingness or attention.

Have any of you heard this? I know that patterns of errors can be difficult for students to detect (thank you, Mina Shaughnessy, for your work all those years ago about this!), but "can't" seems like a tricky term to use unless the student is diagnosed as learning disabled.

It's hard to spot errors in your own work, and it's even harder for students to do so, although they can often see the problems in someone else's paper, as one of the commenters at FSP's place says.

I know that despite the claims of minimal marking enthusiasts, sometimes students just don't get the point of those mysterious little check marks in the margins. They get just as frustrated and hopeless with that kind of "I know the answer and I'm not going to tell you" marking as they do with papers that are "overmarked" with every little item pounced on and killed in a pool of red ink.

Grading is a balancing act between encouraging the students to take responsibility for their writing by letting them figure out the problem, as in minimal marking, and helping them out by explaining what's amiss so that they can do better next time, as in traditional marking with marginal comments. We ought to know that they don't make those mistakes to spite us, but because they don't (can't?) see them.

But doesn't "can't" sounds a little defeatist, as though the students can't learn and we can't help them to learn? If a student "can't" learn to correct an error, does that mean it's incumbent on us to ignore it? Or does it mean that the student shouldn't be in that particular class in the first place?

I have more faith in students than that. I'm crossing "can't" off my list of reasons not to learn to write better.