I was reading through some resources on the Educause AI … Friend or Foe showcase, specifically the one on AI and inclusive excellence in higher education, and one thing in particular struck me. The resource talks, among other things, about helping students to understand the ways of thinking, speaking, and acting in a particular discipline, about making that clearer and whether AI might support this in some way.

This resonates with some ideas that have been bouncing a bit in my head the past few weeks on whether/how AI might help or hinder some of the activities I ask students to do in my courses, which led me to think about why I even ask them to do those activities in the first place. And thinking about this from a disciplinary perspective might help. What kinds of activities might be philosophical? And I don’t mean just those that professional philosophers engage in, because few students in my courses will go on to be professional philosophers, but all of them will do some kinds of philosophical thinking, questioning, discussing, etc. at some point in their lives I believe.

So what might it mean to engage in philosophical activities and can AI help students engage in these better in some way, or not? This is part one of me thinking through this question; there will be at least a part two soon, because I have enough thoughts that I don’t want to write a book-length blog post…

Asking philosophical questions

This is something all philosophers do in one way or another, and that I think can be helpful for many people in various contexts. And yet I find it challenging to define what a philosophical question is, even though I do it all the time. I don’t teach this directly, but I should probably be more conscious about it because I do think it would be helpful for students to be able to engage in this activity more after the class ends.

This reminds me of a post I also read today, this time by Ryan J. Johnson on the American Philosophical Association blog called “How I Got to Questions.” Johnson describes a question-focused pedagogy, in which students spend a lot of their time and effort in a philosophy course formulating and revising questions, only answering them in an assignment towards the end. Part of the point is to help students to better understand over time what makes a question philosophical through such activities.

Johnson credits Stephen Bloch-Schulman in part, from whom I first heard about this approach, and who writes about question-focused pedagogy on another post on the APA blog. Bloch-Schulman did a study that showed philosophy faculty using questions more often and in different ways when reading the same text as undergraduates and other faculty. I appreciated this point (among others!):

I believe that much of the most important desiderata of inclusive pedagogy is to make visible, for students, these same skills we hide from ourselves as experts, to make the acquisition of these skills as accessible as possible, particularly for those students who are least likely to pick up those skills without that work on our part. Question-skills being high on that list. (Introducing the Question-Focused Pedagogy Series)

One step for me in doing this more in my teaching would be to do more research and reflecting myself on what makes some questions more philosophical than others (Erica Stonestreet’s post called “Where Questions Come From” is one helpful resource, for example).

AI and learning/practicing philosophical questions

But this post is also focused on AI: might AI be used in a way to help support students to learn how to ask philosophical questions?

One activity I experienced at a Teaching Hub at an American Philosophical Association meeting a few years ago involved participants in taking an idea or an image and listing as many questions as they can in a set period of time, in part to be able to have a list to do something with later (I sadly can’t remember what we did with those questions!). This was an interesting (and, to me fun!) exercise and one thing that could be done is to then have students reflect or discuss which are more or less philosophical.

Alternatively, might one ask a chatbot to produce a list of questions on a topic and use those as a basis for discussion about different kinds of questions?

As a test, I asked ChatGPT (4o, as I have a paid subscription) to generate a list of 20 questions about various topics. I just gave it topics described in a few words, rather than going into detail about the topic or the kinds of questions I was looking for. I only tried with three topics so far (climate change, the value of higher education, and accessibility in higher education), but with all three the list was predominantly factual or empirical questions questions, e.g.,

• “What are the most significant sources of greenhouse gases?”
• “How does a college degree impact earning potential over a lifetime?”
• “How can technology be used to improve accessibility in higher education?”

There were only a few that could count as philosophical, or at least philosophy-adjacent, e.g.,

• “What are the ethical considerations related to climate change and environmental justice?”
• “What are the challenges faced by first-generation college students, and how do they affect the value of higher education?”
• “Is the cost of higher education justified by the benefits it provides?”
• “What does accessibility in higher education mean, and why is it important?”

Before I go trying several other chat platforms to see how they do, or to reformulate my prompts, it’s important to ask: one could ask AI to do this and find a way to get more philosophical questions in the mix, but how would this help student learning or be particularly useful in some other way? For example, if I just wanted to come up with a list of questions to share with students as examples of different kinds of questions and which ones could be considered philosophical and which are of different sorts and why, this could be a quick way to do so.

Is there value in asking students to do this themselves? Would it be better than asking them to brainstorm a list of their own questions? Hard to say. It would be faster, but then the list wouldn’t be their questions, wouldn’t necessarily be ones that speak to them, that spark their curiosity. As with anything I suppose, it depends on the purpose of the activity and what you hope students will get out of it.

Eventually, I’d like students to practice not only identifying philosophical questions, but asking them themselves, so I wouldn’t want AI to do all the question-asking work! Perhaps in that case AI could generate a scenario of some kind and students could brainstorm philosophical questions that come to mind for them about that scenario. This would save me time as an instructor coming up with such a scenario myself, and would mean students could choose the kind of scenario they want to think about. This would require more thought/planning…right now it’s just a germ of an idea.

Analyzing philosophical arguments

Another thing that characterizes philosophical activity is analyzing arguments, whether those of oneself or others. This includes breaking them down into conclusions and premises, (aka claims and reasons supporting those claims). We do this in part to try to better understand which views have better rationales, and to try to move forward in understanding and answering philosophical questions. If someone (including ourselves!) puts forward an argument and it’s not quite successful, we can better understand how and improve it.

As part of practicing this skill I have often had students review a passage from a philosophy text and work to identify the premises and conclusion (and then later to offer their own critiques, but identifying is the foundational skill we start with). Might AI be used somehow to support student learning in this area?

AI and analyzing arguments

One idea I’ve been thinking about the past week or so is related to a problem I’ve had in doing this activity in or outside of classes. The problem is that so many of the primary sources in philosophy are just really challenging for many folks new to philosophy. Many are still challenging for those who have practiced philosophy for awhile (hello Kant!). And I mostly teach with primary sources rather than with textbooks–which may be its own problem but not a focus of this post.

What if students (or I) asked a chatbot to summarize a passage from a philosophical text in other words, and then students could identify premises and conclusions in that summary instead of the original? (I want to pay attention to copyright though and use either very short passages or things that are public domain or the like). Then this might take away some of the friction of the challenging language (which isn’t part of the learning) to help them focus on the arguments.

Then, as another step, students could also compare the summary to the text, to then see if they agree with the summary when going back to the text with that in mind. This may support better grasping what they understand from the text itself.

I asked ChatGPT 4o to summarize a couple of arguments in ancient Greek philosophy and it did pretty well.

Original from Epicurus’ Letter to Menoeceus

Accustom yourself to believe that death is nothing to us, for good and evil imply awareness, and death is the privation of all awareness; therefore a right understanding that death is nothing to us makes the mortality of life enjoyable, not by adding to life an unlimited time, but by taking away the yearning after immortality. For life has no terror; for those who thoroughly apprehend that there are no terrors for them in ceasing to live. Foolish, therefore, is the person who says that he fears death, not because it will pain when it comes, but because it pains in the prospect. Whatever causes no annoyance when it is present, causes only a groundless pain in the expectation. Death, therefore, the most awful of evils, is nothing to us, seeing that, when we are, death is not come, and, when death is come, we are not. It is nothing, then, either to the living or to the dead, for with the living it is not and the dead exist no longer.

Chat GPT summmary for an audience of high school students:

The passage is saying that we shouldn’t be afraid of death because when we die, we won’t be aware of anything, so it can’t hurt us. Understanding this can help us enjoy life more, without worrying about living forever. The fear of death is pointless because it doesn’t actually cause pain when it happens; it’s just the thought of it that scares us. So, death doesn’t matter to the living, because it hasn’t happened yet, and it doesn’t matter to the dead, because they’re no longer around to care.

I can imagine this summary being a pretty good passage to try to sink one’s teeth into to identify premises and conclusion.

Another one: original from Plato’s Euthyphro:

if that which is holy is the same with that which is dear to God, and is loved because it is holy, then that which is dear to God would have been loved as being dear to God; but if that which dear to God is dear to him because loved by him, then that which is holy would have been holy because loved by him. But now you see that the reverse is the case, and that they are quite different from one another. For one (theophiles) is of a kind to be loved cause it is loved, and the other (osion) is loved because it is of a kind to be loved. Thus you appear to me, Euthyphro, when I ask you what is the essence of holiness, to offer an attribute only, and not the essence-the attribute of being loved by all the gods.

Chat GPT summary for an audience of high school students:

The passage is discussing the difference between what is holy and what is loved by the gods. It says that if something is holy because it’s loved by the gods, then it’s holy only because the gods love it. But if something is loved by the gods because it’s holy, then it’s holy on its own, not just because the gods love it. The passage concludes that these two things—being holy and being loved by the gods—are different. The speaker points out that Euthyphro, when asked to define holiness, is only describing one aspect of it (being loved by the gods) rather than explaining what holiness really is.

Now of course, another thing one could do is to ask students to generate such summaries themselves, but for me that wouldn’t really focus on what I find particularly important about this activity. It’s not so much whether one can work through sometimes awkward translations of texts to try to parse the meaning out of challenging language, but rather whether one can find premises and conclusions in a passage. And if we can make philosophical passages clearer for a purpose like this, then all the better in my view.

Which isn’t to say there is no value in having students read philosophical or other works and summarizing them themselves; this can be a very good way to try to better understand and learn something, by explaining it to oneself and others. It’s just not the purpose of this particular exercise.

Engaging in philosophical discussions

Another thing philosophers often do is have discussions orally. We do this informally, and also at scheduled events such as conferences and colloquia, and we frequently facilitate discussions about philosophical topics in classes. Learning how to do so respectfully and in a way that supports the learning of oneself and others can be a useful skill for other purposes outside of formal philosophical contexts, as philosophical questions and topics are found in many different kinds of situations and activities.

Writing this post has been eye-opening because I’m realizing this is something else I haven’t explicitly taught, but just hope students glean somehow. It would be helpful if I could be more conscious and clear about this before throwing students into the middle of such an activity. Could AI help somehow?

AI and practicing philosophical discussion

Perhaps one could create a custom chatbot that could provide an opportunity for students to practice. I’m reminded of some projects led by colleagues at UBC, including a moot court simulator that uses VR and generative AI to help students practice for moot court in law school, and a nurse practitioner simulator that uses VR and AI to help students practice on virtual patients. Could a simple chatbot be helpful for learning and practicing the “moves” in philosophical discussion?

Conceptually this seems possible, though it might take a fair bit of work to set up and get right. No small part of that work would be to try to figure out and write instructions to mimic just what those moves are, which is a useful activity in itself for teaching students as well.

Conclusion

… for now. This blog post is already over 2500 words, which is quite enough. I have more thoughts, and they will come in a part two!

 

P.S. For fun, I asked ChatGPT 4o to summarize this blog post in no more than 200 words. Here’s a TL:DR:

The blog post explores the potential role of AI in helping students engage with philosophical activities, particularly in higher education. The author reflects on how AI might support tasks like asking philosophical questions, analyzing arguments, and engaging in discussions, which are central to philosophy. They note that while AI, such as ChatGPT, can generate questions or summarize philosophical texts, these outputs often focus on factual rather than philosophical inquiries. The author considers whether using AI to generate questions could be useful for teaching, but emphasizes that it’s crucial for students to develop their own questions to spark curiosity and deep thinking.

Additionally, the post discusses using AI to help students practice analyzing arguments by simplifying complex philosophical texts into more understandable summaries. The author sees value in AI’s potential to support learning but stresses that the core philosophical skills—like identifying premises and conclusions—should remain student-driven. The idea of using AI for practicing philosophical discussions is also considered, drawing parallels with VR-based learning tools in other fields. The author concludes that while AI can be a helpful tool, the essence of philosophical learning should involve active student engagement, not passive reliance on technology.