Wrought by Thought
Essential thinking
Interlocutor: ChatGPT 5.2
KT: Let’s consider Sean Carroll’s recent Mindscape episode titled “The Romance of the University.” Summarize the transcript.
GPT: Sean Carroll’s 2025 Mindscape holiday message reflects on how college changed his high-school friends—not uniformly, but by helping each become “more themselves.” Using that as a launching point, he argues that, amid political and financial attacks on U.S. higher education and growing pressure to justify universities only as job-training, we should defend the ideal of liberal education as valuable in itself.
He warns of an “intellectual WALL-E” future where people outsource thinking—especially writing—to AI, losing the mental muscles that develop through doing the work. He defines liberal education (in the classical sense: education for free, responsible citizens) as broader than vocational training, and says the undergraduate years are uniquely suited to wide exposure to humanities, sciences, arts, and math.
From a “complex systems” view, he claims humans face overwhelming life choices and need tools to navigate them without becoming trapped by narrow norms. Liberal education expands the set of possibilities we can understand and consider, helping us treat ourselves as evolving processes rather than fixed essences. Specific courses matter less for their facts than for the ways of seeing and thinking they instill—how art teaches perception, poetry teaches language, history teaches human variety, science teaches evidence, and math teaches rigor and abstraction.
He closes by noting liberal education doesn’t automatically make someone morally better—it can “sharpen knives”—but it equips people to become better versions of whoever they choose to be, which he sees as a core value worth defending heading into 2026.
KT: Your summary barely touched upon one of the key terms in the essay, suggesting he is right to warn of outsourcing thinking. Can you identify the term?
GPT: The key term is liberal education.
Carroll’s warning about outsourcing thinking—especially to AI—hinges on the idea that liberal education exists precisely to cultivate the habits of mind (writing, reasoning, judgment, reflection) that are lost when thinking is delegated to tools.
KT: Try again.
GPT: The term is mental time travel.
Carroll invokes it to explain what makes human thinking distinctive—the ability to imagine, rehearse, and evaluate possible futures. His warning about outsourcing thinking (especially writing) to AI is that doing so weakens this core capacity, which liberal education is meant to develop and preserve.
KT: Think harder.
GPT: The term is “there are no essences” (his anti-essentialist, process/pattern view—introduced under the banner of natural philosophy).
He uses it to frame people (and minds) as things you become through ongoing activity—so outsourcing core activities like writing/thinking risks stunting that becoming.
KT: That’s it. You’ve become taciturn; can you expand on the point?
GPT: Carroll’s point about “there are no essences” is doing a lot of hidden work in the essay, especially in his warning about outsourcing thinking.
By rejecting essences, he’s saying that neither objects nor people have some fixed inner core that exists independently of what they do. A human being is not a static thing that merely has thoughts, skills, or values; a person is a process unfolding over time, defined by patterns of action, reflection, and response. Just as the Ship of Theseus is a continuing pattern rather than a bundle of original atoms, a person is a continuing pattern rather than a fixed identity.
This is where outsourcing thinking becomes dangerous. If who you are is constituted by what you do, then activities like writing, reasoning, struggling with ideas, and articulating thoughts are not optional add-ons—they are identity-forming processes. Writing isn’t just a way to communicate finished thoughts; it is a way of becoming someone who can think clearly. When AI does that work for you, it doesn’t merely save time—it removes part of the process by which you change, grow, and understand yourself.
Liberal education matters here because it deliberately places students inside these formative processes. It forces engagement with unfamiliar ideas, modes of thought, and ways of seeing that reshape the person over time. This only works if the student is actively doing the thinking. Outsourcing short-circuits the very mechanism by which education changes who you are.
So Carroll’s warning isn’t just practical (“you won’t learn to write if AI writes for you”). It’s ontological. If there are no essences, then becoming replaces being—and outsourcing thinking means outsourcing part of your becoming. That’s why, for him, defending liberal education is inseparable from defending the idea that humans must actively participate in forming themselves.
KT: That could be improved, but let’s continue. Is there irony in our dialogue?
GPT: Yes—there’s a quiet but pointed irony.
The dialogue itself is an instance of outsourcing thinking while simultaneously trying to analyze an argument about why outsourcing thinking is dangerous. You’re asking the system to supply interpretations, refinements, and conceptual links that Carroll explicitly argues should be formed through the struggle of articulation and reflection. Each time I supply a cleaner answer, I’m doing exactly the kind of cognitive work—synthesizing, naming key terms, sharpening concepts—that his defense of liberal education says should shape you through doing it yourself.
The irony deepens because the key concept you identified—“there are no essences”—implies that intellectual growth happens through activity, not possession. Yet here, the activity is partially displaced onto me. Even your prompts (“Try again,” “Think harder”) mirror a professor’s nudges, but without requiring you to fully inhabit the cognitive labor that would normally follow.
That doesn’t make the dialogue pointless or illegitimate. Carroll himself wouldn’t say all delegation is bad; tools can scaffold learning. But the irony lies in how easily assistance can slide from supporting thought to replacing it—illustrating, in real time, the very risk he’s warning about.
In other words, the conversation isn’t just about his argument. It’s a live demonstration of the tension between using tools to think better and letting tools think for us—and how thin that line can be.
KT: Okay, so there’s an argument that the labor of thinking forms a person. Does that apply to an AI model?
GPT: If we take Carroll’s argument seriously, then the labor of thinking forms a person only because a person is a temporally extended process with stakes, continuity, and self-modification across time. Thinking matters for humans not merely because information is processed, but because the process feeds back into motivation, identity, character, and future choice. The effort changes what the person can notice, care about, resist, or imagine next. That feedback loop is essential. Without it, the labor would be inert.
An AI model does not participate in that kind of loop. Although it produces language that resembles thought, the activity does not reshape its goals, values, or sense of self, because it has none. Each response is generated by applying a learned statistical structure to an input, not by revising an ongoing personal trajectory. There is no becoming in the human sense—no accumulation of lived consequence, no memory that matters to the model itself, no internal cost or reward that alters what it is trying to be.
This is where the “no essences” idea becomes clarifying rather than flattening. For humans, rejecting essences means identity is constituted by action over time. For AI, there was never an essence to reject, but also no process of self-formation to begin with. The model’s outputs are patterns without ownership. They do not sediment into character or judgment. Even if the system improves through training updates, that change is imposed externally and does not arise from the model’s own reflective struggle.
So while an AI can simulate the products of thinking, it does not undergo the formative labor that gives thinking its human significance. That distinction explains both why outsourcing thinking can impoverish a person and why it does not meaningfully enrich the AI that receives the task. The risk Carroll points to is asymmetric: humans lose something real when they stop doing the work, while the AI gains nothing in the sense that matters for personhood.
KT: Briefly, what if we had an AI model that did participate in a feedback loop?
GPT: If an AI genuinely participated in a feedback loop where its own activity reshaped its goals, priorities, capacities, and future behavior in a self-directed way, then the argument would begin to apply—but only partially. At that point, the AI would no longer be just producing outputs; it would be undergoing a process of becoming, where effort mattered because it altered what the system could later notice, value, or choose.
Even then, the analogy would depend on what kind of feedback loop it was. If the loop merely optimized performance metrics imposed from outside, it would still fall short of person-forming labor. For the parallel to hold, the AI’s thinking would need to matter to itself—to shape its own stakes, commitments, and trajectory over time. Only then would the labor of thinking be constitutive rather than instrumental, and only then would questions about education, development, and even moral status start to look genuinely analogous to the human case.
KT: Well, that’s something I’ll have to think about.