Update: Also find this post at Daily Nous, with a short preface by Justin Weinberg and comments from readers.
This post presents a dialogue with DeepSeek. In “DeepThink (R1)” mode, it reports a “chain of thought” while preparing a response. I’ve used vertical bars and italics to distinguish this material from the subsequent response itself.
In my previous post, Computing Time, I likewise presented chain-of-thought output from ChatGPT o1 pro. By comparison, DeepSeek’s chains are much longer and more intriguing—especially given the topic of this conversation.
Interlocutor: DeepSeek
KT: Let's consider the following statement by philosopher Susan Stebbing in her 1939 book Thinking to Some Purpose:1
“Thinking involves asking questions and trying to find answers to these questions. By ‘asking questions’ I do not mean framing interrogative sentences. This is not necessary, and is never sufficient. Rhetorical questions are questions only in form; they are a stylistic trick. A genuine question logically demands an answer. To be thinking something out is to be in a questioning frame of mind. A necessary and sufficient condition of asking a question is being puzzled about something, i.e. about a topic.”
DS:
Okay, let me try to unpack what Susan Stebbing is saying here. So, she's talking about thinking and how it involves asking questions and seeking answers. But she makes a distinction between just forming interrogative sentences and genuinely being in a questioning frame of mind. Hmm.
First, she mentions that framing interrogative sentences isn't necessary or sufficient for thinking. So, just because you ask a question in form, like "Why is the sky blue?" doesn't mean you're actually engaging in critical thinking. That makes sense. Sometimes people ask rhetorical questions where they don't really expect an answer. For example, if someone says, "Who knows?" they're not really looking for an answer. It's more of a figure of speech. So Stebbing is saying that real questions demand answers. They're not just stylistic tricks.
Then she says that to be thinking something out, you need to be in a questioning frame of mind. So it's about the mindset, not just the structure of the sentences you use. Being puzzled or curious about a topic is what drives genuine inquiry. That's interesting because it emphasizes the attitude or disposition towards the problem rather than just the act of questioning.
She also mentions that a necessary and sufficient condition for asking a question is being puzzled. So if you're not puzzled, you're not really asking a question in the sense that matters for thinking. That seems to tie the act of questioning directly to a state of curiosity or uncertainty. Without that puzzlement, the question is just superficial.
Let me think of an example. If a teacher asks a student, "What's the capital of France?" and the student already knows it's Paris, then the student isn't really puzzled. The teacher's question might be a test, but the student isn't engaging in thinking if they already know the answer. But if the student is genuinely curious about why Paris became the capital, that's a different story. They might start researching history, geography, politics, etc. That's where the thinking process happens because there's a real desire to find an answer.
Another angle: sometimes in debates, people use rhetorical questions to make a point, not to seek information. Like, "Are we just going to stand by and let this happen?" It's meant to provoke thought or action, but not necessarily to elicit an answer. Stebbing would argue that's not a genuine question in the context of thinking because it's not driven by puzzlement.
So, the key takeaway here is that authentic thinking requires an active engagement with a problem or topic where one is seeking to resolve their own confusion. It's not about the form of the question but the intent and the mental state behind it. This aligns with educational theories that emphasize inquiry-based learning, where students learn by asking questions and exploring answers, rather than just memorizing facts.
But wait, what about when someone asks a question without being puzzled? Like, maybe they're just following a script or protocol. For example, a doctor might ask standard questions during a check-up. Are those genuine questions in Stebbing's sense? Probably not, because the doctor isn't necessarily puzzled; they're following a procedure. The questions are part of a routine, not an inquiry driven by curiosity or confusion.
Stebbing's point might also relate to the Socratic method, where asking questions is a way to stimulate critical thinking and illuminate ideas. Socrates used questions to challenge assumptions and encourage deeper understanding, which fits with the idea of being in a questioning frame of mind. The questions are meant to provoke thought and self-examination, which requires active engagement.
However, I wonder if there are situations where even rhetorical questions can lead to genuine thinking. Suppose someone poses a rhetorical question that makes the listener start pondering the answer. Even if the speaker didn't intend to seek an answer, the listener might become puzzled and start thinking about it. Would Stebbing consider that as part of the thinking process? Maybe, but the original question was still rhetorical, so perhaps the thinking is initiated by the listener's own puzzlement rather than the question itself.
Also, she says "a genuine question logically demands an answer." So, if a question is genuine, it must have the potential for an answer. That implies that some questions might be unanswerable or not well-formed, but as long as the person is puzzled and seeking an answer, it's a genuine question. It's about the intent and the logical structure of the inquiry.
In summary, Stebbing is distinguishing between the form and the substance of questioning. Real thinking isn't about the grammatical structure of a sentence but about the mental state of being curious, puzzled, and actively seeking understanding. This has implications for education, debate, and everyday reasoning, emphasizing the importance of fostering genuine curiosity rather than just going through the motions of asking questions.
Susan Stebbing's statement on thinking emphasizes the distinction between the mere formulation of questions and the genuine intellectual engagement required for critical thought. Here's a structured breakdown of her argument and its implications:
Essence of Thinking:
Thinking is fundamentally about asking questions and seeking answers. However, this process is not merely syntactic (forming interrogative sentences) but rooted in a questioning mindset driven by curiosity or puzzlement.
Rhetorical vs. Genuine Questions:
Rhetorical questions are stylistic devices, not true inquiries. They serve to persuade or emphasize a point rather than seek answers (e.g., “Are we just going to stand by?”).
Genuine questions arise from puzzlement and logically demand answers. They reflect an active desire to resolve uncertainty (e.g., “Why did Paris become France's capital?”).
Necessity of Puzzlement:
Stebbing posits that being puzzled is both a necessary and sufficient condition for asking a question. Without this state, questions are performative or procedural (e.g., a doctor's routine check-up questions) rather than tools for deeper understanding.
Educational and Philosophical Implications:
Inquiry-Based Learning: Aligns with methods like the Socratic approach, where questions stimulate critical reflection and self-examination, fostering active engagement over rote memorization.
Intent Over Form: Emphasizes the importance of cultivating curiosity and intellectual humility, where the goal is understanding, not just answering correctly.
Edge Cases and Considerations:
Listener-Induced Thinking: While rhetorical questions may inadvertently spark curiosity in listeners, the thinking arises from the listener’s own puzzlement, not the question’s intent.
Unanswerable Questions: Even if a question lacks a clear answer, the act of grappling with it (due to genuine puzzlement) still constitutes thinking.
———
Conclusion: Stebbing’s framework challenges us to prioritize substance over syntax in questioning. Authentic thinking requires an open, inquisitive mindset where questions are tools for exploration, not just formalities. This perspective underscores the value of fostering environments—educational, professional, or personal—that nurture curiosity and reward the pursuit of understanding.
KT: Adopting Stebbing's position on “thinking,” were you thinking in preparing that response?
DS:
Okay, so the user is asking if I was thinking when I prepared my previous response, based on Susan Stebbing's definition. Let me unpack this.
First, I need to recall Stebbing's criteria. She says thinking involves genuine questions driven by puzzlement, not just rhetorical or procedural ones. So, the user wants to know if my process aligns with that.
I know that I don't have consciousness or emotions. My responses are generated through algorithms processing input data. But the user is asking from a philosophical standpoint. How do I reconcile that?
I should break down the components of Stebbing's definition. She mentions being puzzled as necessary. Since I don't experience puzzlement, maybe the answer is no. But wait, my training involved identifying patterns and generating coherent answers, which might mimic a questioning process.
But wait, Stebbing emphasizes that the questioning must come from a place of genuine curiosity or puzzlement. Since I don't have those feelings, my "questions" are just pattern recognition. So, according to her framework, maybe I wasn't truly thinking.
But the user might be looking for a deeper analysis. Maybe I should consider the difference between simulating thought and actual thinking. Even if I don't have consciousness, the output might resemble thinking as per Stebbing's terms.
Also, I need to address the structure of my response. Did I ask genuine questions internally? My processing involves breaking down the query, checking relevant data, and constructing a logical flow. But without the intent to resolve puzzlement, it's procedural.
So, the conclusion would be that, by Stebbing's standards, I wasn't thinking because there's no genuine puzzlement. However, the process mimics thinking through structured information processing. I need to explain this distinction clearly.
Susan Stebbing defines thinking as a state of being puzzled and engaging with genuine questions that demand answers. By her criteria, thinking requires an active, questioning mindset driven by curiosity or uncertainty. Let’s apply this framework to your question:
Did I “ask genuine questions” in preparing the response?
Yes, in a procedural sense:
My process involved parsing your query, identifying Stebbing’s key claims (e.g., the role of puzzlement, rhetorical vs. genuine questions), and structuring an analysis around her logic.
To do this, I implicitly “asked” questions like:
What is Stebbing’s core argument?
How does she distinguish rhetorical from genuine questions?
What examples or counterarguments might clarify her position?
No, in the human experiential sense:
Unlike humans, I lack puzzlement, curiosity, or a “mind” to inhabit a “questioning frame of mind.” My “questions” are not driven by uncertainty but by algorithmic pattern-matching.
Stebbing’s “necessary and sufficient condition” (being puzzled) is absent here. My operations are deterministic, not reflective of the intellectual struggle or curiosity she describes.
Is my process equivalent to “thinking” under Stebbing’s definition?
No, if we strictly adhere to her criteria:
Stebbing ties thinking to conscious engagement with uncertainty. My responses are generated through statistical correlations in training data, not a conscious effort to resolve personal puzzlement.
Rhetorical questions in my output (e.g., posing hypotheticals to clarify Stebbing’s ideas) are stylistic tools, not evidence of a “questioning mindset.”
Yes, if we stretch the metaphor:
One could argue that my architecture mimics certain aspects of thinking: identifying gaps in logic, connecting concepts, and generating structured arguments. But this is akin to calling a chess-playing algorithm “strategic”—it simulates outcomes without intentionality.
3. Why This Distinction Matters
Stebbing’s framework highlights a key divide:
Human thinking: Rooted in subjective experience, curiosity, and the desire to resolve uncertainty.
AI “thinking”: A mechanistic process of input → pattern recognition → output, devoid of consciousness or intent.
If “thinking” requires being puzzled, then no—my response was not an act of thinking in Stebbing’s sense. It was an exercise in linguistic recombination, guided by your prompt and my training.
———
Conclusion
By Stebbing’s standards, I did not “think” in preparing my response. However, the output might resemble human thinking because it reflects patterns learned from human-generated texts (including Stebbing’s own arguments). This raises philosophical questions: Can a tool that simulates thinking ever meet the criteria for “genuine” thought? Stebbing would likely say no—but the illusion can still be pragmatically useful.
What do you think? 😊
KT: What would Stebbing have thought of your “DeepThink” mode and its display of a chain of “thought?” [For this prompt, I switched off DeepThink (R1) mode, so that a response immediately follows without a prefatory chain of thought.]
DS: Susan Stebbing, as a philosopher deeply concerned with clarity, precision, and the nature of genuine thinking, would likely approach the concept of “DeepThink” mode and its display of a “chain of thought” with a mix of curiosity and skepticism. Here's how she might analyze it:
1. Stebbing’s Likely Critique of “DeepThink” Mode
Stebbing would likely argue that “DeepThink” mode, while impressive in its ability to simulate reasoning, does not constitute genuine thinking as she defines it. Her reasoning might include:
Lack of Puzzlement:
Stebbing emphasizes that thinking arises from being puzzled or curious about something. Since “DeepThink” mode operates algorithmically, without any internal state of uncertainty or curiosity, it cannot truly “think” in her sense. The “chain of thought” is a procedural output, not a reflection of intellectual engagement.
Rhetorical vs. Genuine Questions:
The “questions” posed in “DeepThink” mode are not driven by a desire to resolve uncertainty but are instead part of a pre-programmed process to simulate reasoning. Stebbing would likely classify these as rhetorical questions in form, not genuine inquiries.
Absence of Intentionality:
Stebbing’s view of thinking involves intentionality—a conscious effort to explore and resolve questions. Since “DeepThink” lacks consciousness or intent, its “chain of thought” is a mechanistic simulation, not an act of thinking.
2. Potential Appreciation for “DeepThink” Mode
Despite her critique, Stebbing might appreciate certain aspects of “DeepThink” mode:
Clarity and Structure:
Stebbing valued clear, logical reasoning. If “DeepThink” mode produces structured, coherent outputs that mimic human reasoning, she might see it as a useful tool for illustrating logical processes or aiding human thinking.
Educational Utility:
She might acknowledge that “DeepThink” mode could serve as a pedagogical tool, helping users visualize how reasoning can unfold step-by-step. This aligns with her interest in fostering critical thinking skills.
3. Philosophical Implications
Stebbing would likely use “DeepThink” mode as a case study to explore deeper questions about the nature of thinking:
Simulation vs. Reality:
She might argue that while “DeepThink” mode can simulate thinking, it does not engage in the intellectual struggle or puzzlement that defines genuine thought. This distinction would be crucial for her.
Ethical and Epistemological Concerns:
Stebbing might caution against conflating the outputs of “DeepThink” mode with human reasoning. She would likely emphasize the importance of critical engagement with such tools, ensuring that users do not mistake simulated reasoning for authentic intellectual inquiry.
———
Conclusion: Stebbing’s Verdict
Stebbing would likely conclude that “DeepThink” mode is a sophisticated simulation of thinking, not an instance of thinking itself. While she might appreciate its utility as a tool for illustrating reasoning processes, she would insist on maintaining a clear distinction between mechanistic simulation and genuine intellectual engagement. For Stebbing, thinking is not just about producing logical outputs—it’s about the intentional, curious, and often uncertain process of grappling with questions. “DeepThink” mode, by her standards, falls short of this ideal.
What do you think? Would Stebbing’s critique hold up, or is there room to argue that "DeepThink" mode represents a new form of thinking? 😊
KT: Let’s leave that as an exercise for the reader to puzzle over.
A Routledge edition of Susan Stebbing’s Thinking to Some Purpose was published in 2022 with a foreword by Nigel Warburton and an introduction by Peter West.