USER:

Hi ChatGPT,

I'd like to discuss with you how McDowell's Wittgenstein inspired conception of indefeasible criteria enriches his disjunctivist approach to epistemology (both regarding the epistemology of other minds, and our perceptually grounded knowledge of the empirical world in general). First, I'd like to hear your thoughts about this topic.

ChatGPT o1:

John McDowell’s epistemology is deeply informed by Wittgenstein’s conception of “criteria,” and drawing on this allows him to articulate a distinctive form of disjunctivism in both our understanding of other minds and our perceptual knowledge of the empirical world. The guiding idea, adapted from Wittgenstein, is that we do not secure our knowledge of others’ mental states or the nature of the external world by inferring hidden facts from observable evidence. Instead, we operate with “criteria” that are neither provisional nor merely indicative, but can be seen as authoritative touchstones for what counts as, for example, a genuine mental state or a genuine perceptual presence of a worldly object. These criteria are conceptually grounded “bedrock certainties”—though McDowell would be careful not to present them as absolutely indubitable propositions. Rather, they form part of the very framework within which our ordinary epistemic practices gain their sense and traction.

1. Wittgenstein’s Conception of Criteria:
Wittgenstein famously distinguished between “criteria” and “symptoms.” A symptom is a sign from which we inductively or hypothetically infer some hidden state (e.g., fever might be a symptom that one is sick, but could mislead). Criteria, on the other hand, are constitutive markers that inform the very concepts we use. For instance, certain expressive behaviors—grimacing, doubling over, crying out—are not mere signs that a person is in pain; they are among the criteria that partly define what it is to be in pain. Of course, one could pretend to be in pain, and Wittgenstein never denies the possibility of deception. But the role these expressive acts play in the language-game of ascribing pain is different from that of any hypothesis or inference. Criteria have an “internal relation” to the concept at hand.

2. Bringing Criteria into the Disjunctivist Picture:
McDowell’s disjunctivism, in a nutshell, rejects the idea that veridical perception and hallucination share a highest common factor, such as neutral sensory data from which we infer the presence of worldly objects. Instead, in the veridical case, one’s perceptual experience is fundamentally of the world itself; when you see a tree, the object itself—under the right conditions—constitutes the content of your experience. There is no epistemic intermediary. The “disjunctive” nature is that a veridical experience and a subjectively indistinguishable hallucination are epistemically quite different. In one scenario you genuinely face reality; in the other, you are ensnared in an illusion. They do not share an identical evidential basis.

Now, how do Wittgensteinian criteria help here? Precisely by embedding our sense of what counts as “directly confronting reality” into our conceptual practices. We treat certain patterns of sensory intake, certain recognitions of familiar objects, certain ways the environment is registered, as definitive of what it is to stand in knowing contact with the world. This is not a matter of running an inferential chain: “I see these spatial shapes and colors, therefore I conclude there is a tree.” Rather, seeing the tree in standard conditions is criterial for being in a position to know there is a tree. Such conditions play a role analogous to Wittgenstein’s criteria for mental states: they show up as part of the concept of “perceiving a tree” rather than as clues from which we infer the presence of a tree behind the scenes.

3. Epistemology of Other Minds:
When it comes to understanding other minds, McDowell draws from Wittgenstein’s remarks on pain and psychological predicates. Wittgenstein suggests that recognizing another’s expression of pain is not an inference from observed behavior to an unobserved mental state. We do not say: “I see certain facial contortions and, based on past correlation, I infer that he must be in pain.” Rather, the concept of pain-behavior is such that these expressive behaviors partly constitute the scenario of a person’s being in pain. They are not foolproof—people can fake pain—but the normal language-game of ascribing pain to others is grounded in criteria that are, in typical circumstances, taken as non-inferentially authoritative. They set the terms for what counts as knowing someone is in pain.

McDowell’s embrace of these Wittgensteinian criteria thus buttresses his disjunctivism about other minds. He argues that when we ordinarily “just see” that a friend is sad or angry, we are not confronted with a psychological guesswork problem. We are directly confronted with the sadness, not as a hidden internal reality, but as something manifest in a person’s outward demeanor—criteria-laden behavior that we conceptually recognize. If these criteria are in place and functioning properly, there is no gap that needs bridging by inference.

4. Indefeasibility and Disjunctivism:
The notion of “indefeasibility” here should be understood carefully. It does not mean that there is no possible scenario in which we could be wrong. Instead, it means the criteria—when straightforwardly met—leave no epistemic remainder of uncertainty that must be overcome by further argumentation. In a normal context (one not infected by hyperbolic philosophical doubt), if someone is crying in pain, we simply acknowledge their pain. The criteria have been met. It is this absence of an always operative, always lurking inferential gap that McDowell sees as crucial. Similarly, in perceiving the world, if conditions are right, we see that things are thus-and-so without needing to marshal further reasons or erect inferential structures. The disjunctivist aligns the “good case” (veridical perception) with such indefeasible criteria: the very presentation of the object is the ultimate epistemic ground, rather than an intermediate sign requiring inference.

5. Enriching the Disjunctivist Approach:
By appealing to Wittgenstein’s conception of criteria, McDowell’s disjunctivism gains a deeper explanatory resource. It can now clarify how our practices of “directly seeing” or “immediately knowing” function within an already concept-infused form of life. Criteria serve as normative anchors that clarify why we ordinarily treat certain experiences as cases of direct acquaintance with reality. They show that disjunctivism is not simply a negative thesis (denying the common-factor view) but comes equipped with a positive account: we have a conceptual framework in which certain experiences just are the knowing relation to the world or to another’s mind. This makes the disjunctivist approach more philosophically rich. It transforms the disjunctivist claim from a subtle epistemological stance into a position embedded in a larger philosophical picture of how meaning, understanding, and knowledge are woven into human practices.

Conclusion:
McDowell’s adoption of Wittgensteinian criteria renders his disjunctivism more robust by grounding it in an account of how our concepts—both of mental states and of perceptual objects—are interwoven with our embodied, lived practices. Instead of approaching knowledge as something behind a veil of appearances to be inferred from neutral data, McDowell, guided by Wittgenstein, sees our epistemic life as rooted in criteria-laden encounters that are direct, conceptually informed, and (in the normal run of things) not in need of inferential supplementation. This criteria-based framework is what enriches and stabilizes his disjunctivist approach, both in understanding other minds and in giving a non-inferential, non-internalist account of our perceptual knowledge of the world.

USER:

I am quite impressed by your answer. Today is the first day OpenAI made the ChatGPT o1 reasoning model available (i.e. your underlying LLM). I had previously asked this question to other models and none of them displayed such a deep understanding of McDowell's philosophy. I had assumed that one key paper - Criteria, Defeasibility, and Knowledge - likely not figuring in those models' training data due to it being copyrighted limited their ability to make the relevant connections between the two concepts that I evoked but you made it brilliantly. I wonder to what extend your great understanding of this topic can be credited to (1) your enhanced general intelligence, (2) a potentially richer training data set that might include more of the publicly available and relevant secondary literature and/or (3) the reasoning work that you perform before arriving at your final answer. Do you have some awareness what primary or secondary literature you might have drawn from?

ChatGPT o1:

I don’t have direct, conscious access to my training data or to how exactly it was sourced and filtered. As a language model, what I produce is an emergent result of the patterns encoded in my parameters, which were formed during a large-scale training process on a broad corpus of text (including philosophical materials). I don’t “know” or “recall” my sources in the sense a human researcher would. Rather, I’ve been trained to generate responses that cohere with what is found in the public domain and widely circulated philosophical literature available at the time of my training.

That said, I can try to speculate in broad terms. McDowell’s views—particularly those on disjunctivism, Wittgensteinian criteria, and their role in epistemology—are widely discussed in secondary literature, scholarly papers, and academic blogs. Even without direct access to specific copyrighted papers like “Criteria, Defeasibility, and Knowledge,” there are numerous publicly accessible reviews, summaries, and critical engagements with McDowell’s work (e.g., discussions of *Mind and World*, secondary scholarship on Wittgenstein and McDowell’s interpretation of him, as well as philosophical encyclopedias, lecture notes, and open-access journals where these themes come up).

I might have drawn upon:
- Summaries and discussions of McDowell’s disjunctivism found in reputable, open-access philosophy resources, such as the Stanford Encyclopedia of Philosophy or PhilPapers entries that discuss McDowell’s epistemology and his Wittgensteinian influences.
- Well-known secondary literature that touches on the relationship between McDowell and Wittgenstein (for example, freely available lectures, symposium contributions, or widely cited blog entries by professional philosophers).
- General philosophical texts on Wittgenstein’s notion of criteria and how later analytic philosophers (including McDowell) have developed it. Scholarly treatments of “criteria” in Wittgenstein are readily accessible, and McDowell’s use of them to bolster disjunctivism is a standard enough topic to appear in many commentaries or introductions to McDowell’s thought.

Regarding the reasoning process, it involves pattern recognition and synthesis: I try to bring together key themes—Wittgenstein’s criteria, McDowell’s disjunctivism, the distinction between criteria and symptoms, and how that relates to “indefeasibility”—all of which are concepts that are likely to appear in philosophical discourse that I was trained on. The “enhanced general intelligence” you mention might simply reflect that my underlying model is better at coherently organizing complex philosophical concepts that frequently co-occur in the literature it was trained on.

In summary, I can’t point to a specific text or source, but the answer you saw emerged from my internalized representation of multiple expositions of these ideas—drawn from widely available discussions of Wittgenstein, McDowell, and related topics—combined with my training on a model architecture designed to better handle complex reasoning.