Toggle menu
Toggle preferences menu
Toggle personal menu
Not logged in
Your IP address will be publicly visible if you make any edits.

December 26, 2022

From Gerald R. Lucas

Playing with AI

I ’ve been playing around with ChatGPT over the last couple of days. Since this has been in the news quite a bit and some of the demonstrations on YouTube are pretty impressive, I wanted to try it out. Randomly, I chose to ask it about an essay/short story my students read in ENGL 1101 last semester: George Orwell’s “Shooting an Elephant.” First, I asked it to summarize the text:

Wow, that’s pretty good. It even gets into a bit of analysis. Next, I asked how the themes of “Shooting” might relate to America today. It returned:

Again, pretty impressive. This last question was similar to one of the exam questions I asked and that many chose to answer:

OK, so I fed ChatGPT that exact prompt. Here’s the response:

Holy shit. Yes, it’s pretty vague, especially the third paragraph, but damn, it’s a firm foundation for constructing a more detailed and specific essay. Not only that, it’s clearly written, so that’s a dead giveaway that one of my freshmen didn’t write it. I’m not being catty here, but suggesting ways in which I can tell this is AI-generated. Being totally free of typos and awkward constructions would lead me to think this potential plagiarism. Would it be? Certainly it’s cheating or disingenuous. I had my students hand-write in-class, so they could not have cheated in this way, but certainly in preparing for an exam or doing out-of-class drafts, ChatGTP could be an excellent learning tool. I bet it would work even better on some of the questions I ask for my World Literature survey.

I pushed it a bit more by asking it to expand its last response “to a 1000-word essay and include more specifics.” While it didn’t quite make it to 1000 words—for some reason cutting off mid-sentence at about 650—what it produced was impressive. Most remarkably, ChatGPT added a specific references to BLM, political polarization, and cancel culture—exactly what I was trying to emphasize in our classroom discussion. Again, wow.

Of course, this gets me to thinking how I can use ChatGPT to streamline my own work. So, I asked it to write a course description for my brand new class, Topics in World Literature. I’d already decided to narrow my “topic” to “20th-century short stories” to mitigate the work of having four distinct preps. Short stories are engaging without being too time-consuming. I liked what it gave me, so I used it. I might try to write my whole syllabus this way. It did not do so well when asked to produce a sample reading list of stories not originally written in English. Still, I am impressed.

This is scary fun. I wonder: when does Siri get this upgrade?