Yesterday I listened to The Daily’s episode on the radical impact of AI on higher ed. A history professor compared himself to a monkey hugging a fake mother in Harry Harlow’s famous study of “comfort contact.” If all the effort put into course planning, creating discussion questions, and giving careful feedback to student writing only culminates in a conversation between the professor and ChatGPT, the intellectual contract between teacher and student has been betrayed. As one interviewer asked Harlow, is the monkey’s attachment to a cloth doll really love?
I taught college composition and lit for nearly 15 years, and this situation strikes me as an argument for in-class drafting. Not only might it reduce the chance to use AI, but it also might allow/ask the students to participate in *generating* questions about the text. For example, begin a class with this prompt: "Now that you've read the first x pages/chapters, write for 10 minutes about what aspect you most reacted to and why. Point to specific pages/examples." Then after than 10 minutes, have a discussion.
My impression from my time in higher ed was that we assume that the teacher's questions are always more important than the student's, which often discourages students from asking questions unless they can frame them in ways that sound like the teacher's. I wonder whether part of the appeal of AI is that it makes it easier for student writing to sound the way students assume their teachers want them to sound. I didn't think that was the point of teaching literature or writing, but I think a lot of academic act as though it is. I always much preferred messy engagement to fluent distance. That meant tolerating--even encouraging--messiness; it meant bringing messiness into the class and placing it front and center.
The signature reason I did well in English was that for my whole life as a student, I took *my own* reaction to the literature I read seriously; I treated my responses as though they mattered. I don't know where that confidence came from. But I don't think the vast majority of students are encouraged to approach literature (or maybe any of their subjects) that way. And as depressing as the possible use of AI is, that lack of encouragement long precedes the technology.
This is so interesting because I am finalizing my response to your Tuesday post. The fact it was AI generated explains a bit why I was having trouble with it. I pulled out my copy of DCFTA, and started reading it. One of my favorite scenes is when Latour is in the cave. The strong emotions he feels there continue to reverberate in me. However, it was not mentioned in the post.
What you published Tuesday was helpful to me in wanting to clarify what I just discussed on a retreat recently. I was just in Blowing Rock, NC discussing The Brothers Karamazov and the subject of Dostoyevsky’s epilepsy was discussed-how both the illness and the methods of controlling his illness likely contributed to his original thinking. (Just two year prior to publication of the novel, his 3yo son Alyosha died of epilepsy, hence complicating his own view of what fathers pass on to their sons and the guilt that this entails. This was such a poignant theme in the book.)
Anyway, it’s shocking to hear that what I was responding to was not all completely human. I think the ideas were, but the vehicle of conveyance was artificial. But in a way my response (that I am still editing) is the exact opposite of what was first posed. My post is informed by an extraordinarily human forum: a retreat of friends and strangers who voluntarily spend a week together to discuss a huge Russian novel. Out of our own pocket and not for credit. Is this what we are supposed to be doing instead of a debt-inducing college education that fails to treat more and more academics fairly?
Very interesting to read all the responses from AI. Well-crafted indeed.
As for your final question, posed by the attendee to your lecture...Yes, I feel the same way. It all feels a bit too much like naval-gazing to me these days. Which is not to say that I don’t still do it, only that I do it less and frequently question the purpose. Neither good nor bad. Some will always be drawn to this activity and others not
This is a great area to explore. Great writing Josh. Great thinking. I wrote an article about AI in the workplace and the impact on leaders. I concluded the human touch is still needed more than ever. I hope you continue to explore the impact on teaching and higher education. Congratulations on your presentation in NY.
This all troubles me greatly. During a winter online class, I had two egregious instances of pervasive AI-generated plagiarism that I caught. Who wants to devote time and energy to dealing with that? During the fall, when ChatGPT got everyone's attention, amid much concern, there was also a lot of quick, hopeful and sensible educational discussion of AI's usefulness as a pedagogical heuristic. But I'm not optimistic. And I don't have answers. Advocates are excited, as advocates of technological advance always are, about the brave new worlds waiting. But there are fundamental questions being too little considered. Aside from the thrill of the new, there is the appeal to efficiency, just as there always is to *progress*. How much more efficient (and less costly!) living and working and producing in the world will be with the benefit of AI. And if we fudge, then lose, the meaningful difference between human and not, well, some *intelligence* is still writing the essay or teaching the class or developing the new streaming TV series, assembling the auto or directing the drone, and what's important is that it's all being done more efficiently - faster, cheaper, more productively. More. To what end?
I taught college composition and lit for nearly 15 years, and this situation strikes me as an argument for in-class drafting. Not only might it reduce the chance to use AI, but it also might allow/ask the students to participate in *generating* questions about the text. For example, begin a class with this prompt: "Now that you've read the first x pages/chapters, write for 10 minutes about what aspect you most reacted to and why. Point to specific pages/examples." Then after than 10 minutes, have a discussion.
My impression from my time in higher ed was that we assume that the teacher's questions are always more important than the student's, which often discourages students from asking questions unless they can frame them in ways that sound like the teacher's. I wonder whether part of the appeal of AI is that it makes it easier for student writing to sound the way students assume their teachers want them to sound. I didn't think that was the point of teaching literature or writing, but I think a lot of academic act as though it is. I always much preferred messy engagement to fluent distance. That meant tolerating--even encouraging--messiness; it meant bringing messiness into the class and placing it front and center.
The signature reason I did well in English was that for my whole life as a student, I took *my own* reaction to the literature I read seriously; I treated my responses as though they mattered. I don't know where that confidence came from. But I don't think the vast majority of students are encouraged to approach literature (or maybe any of their subjects) that way. And as depressing as the possible use of AI is, that lack of encouragement long precedes the technology.
This is so interesting because I am finalizing my response to your Tuesday post. The fact it was AI generated explains a bit why I was having trouble with it. I pulled out my copy of DCFTA, and started reading it. One of my favorite scenes is when Latour is in the cave. The strong emotions he feels there continue to reverberate in me. However, it was not mentioned in the post.
What you published Tuesday was helpful to me in wanting to clarify what I just discussed on a retreat recently. I was just in Blowing Rock, NC discussing The Brothers Karamazov and the subject of Dostoyevsky’s epilepsy was discussed-how both the illness and the methods of controlling his illness likely contributed to his original thinking. (Just two year prior to publication of the novel, his 3yo son Alyosha died of epilepsy, hence complicating his own view of what fathers pass on to their sons and the guilt that this entails. This was such a poignant theme in the book.)
Anyway, it’s shocking to hear that what I was responding to was not all completely human. I think the ideas were, but the vehicle of conveyance was artificial. But in a way my response (that I am still editing) is the exact opposite of what was first posed. My post is informed by an extraordinarily human forum: a retreat of friends and strangers who voluntarily spend a week together to discuss a huge Russian novel. Out of our own pocket and not for credit. Is this what we are supposed to be doing instead of a debt-inducing college education that fails to treat more and more academics fairly?
Very interesting to read all the responses from AI. Well-crafted indeed.
As for your final question, posed by the attendee to your lecture...Yes, I feel the same way. It all feels a bit too much like naval-gazing to me these days. Which is not to say that I don’t still do it, only that I do it less and frequently question the purpose. Neither good nor bad. Some will always be drawn to this activity and others not
This is a great area to explore. Great writing Josh. Great thinking. I wrote an article about AI in the workplace and the impact on leaders. I concluded the human touch is still needed more than ever. I hope you continue to explore the impact on teaching and higher education. Congratulations on your presentation in NY.
Wow! That is a scary thought and I believe it. I will look up her work. Thanks
This all troubles me greatly. During a winter online class, I had two egregious instances of pervasive AI-generated plagiarism that I caught. Who wants to devote time and energy to dealing with that? During the fall, when ChatGPT got everyone's attention, amid much concern, there was also a lot of quick, hopeful and sensible educational discussion of AI's usefulness as a pedagogical heuristic. But I'm not optimistic. And I don't have answers. Advocates are excited, as advocates of technological advance always are, about the brave new worlds waiting. But there are fundamental questions being too little considered. Aside from the thrill of the new, there is the appeal to efficiency, just as there always is to *progress*. How much more efficient (and less costly!) living and working and producing in the world will be with the benefit of AI. And if we fudge, then lose, the meaningful difference between human and not, well, some *intelligence* is still writing the essay or teaching the class or developing the new streaming TV series, assembling the auto or directing the drone, and what's important is that it's all being done more efficiently - faster, cheaper, more productively. More. To what end?