I asked chatGPT to evaluate soundness of the followibg excerpt from my dissertation:
d. CONCEPTUAL VS. NON-CONCEPTUAL REPRESENTATION
I believe that there is a way to bridge the gap between Sellars and Lewis-Firth-Chisholm about premise (1) of Chisholm’s argument by using Sellars’ distinction between Language, or L, and a Representational System, or RS. Suppose we identify Lewis’ ‘sense meanings’,{85} Firth’s ur-concepts,{86} Chisholm’s ‘phenomenal reports’,{87} Everett Hall’s ‘natural language of perception’,{88} and Romane Clark’s ‘sensuous judgments'{89} with an RS. All of these may, in a refined way, have the following theses in common with an RS: (i) propositional form, (ii) Humean inferences, and (iii) no logical connectives. I say in ‘a refined way’ because I am not clear that each of these authors sees the necessity of (iii) in their analogues of an RS. Clark is clear when he writes: “I do not think of the logical connectives as part of perceptual judgments. Certainly not on the primitive level of basic perceptions.”{90} Lewis’s concept of ‘sense meaning’ is hard to pin down. But a few things are clear. Sense meaning is prior to and independent of language,{91} even animals possess it,{92} and it requires anticipatory imagery.{93} These remarks suggest at least the acceptance of (ii). Lewis also suggests that sense meaning may be connected with Kant’s ‘schema’.{94} At this point there is a connection between Lewis and Sellars. In “The Role of Imagination in Kant’s Theory of Experience,” Sellars introduces the notion of an ‘image-structure’, ‘sense image’, or ‘image-model’ which, according to Sellars, is the work of Kant’s productive imagination. There is according to Sellars as ‘image-model world'{95} prior to and independent of logical connectives (categories). A ‘schema’ for Kant, according to Sellars, bridges concepts and such image-models. A schema is the construction of an image-model by the productive imagination in accordance with a concept.{96} In saying this, Sellars may be in disagreement with Lewis over the interpretation of Kant. In any case, I think that both Sellars and Lewis agree that a schema is a recipe for construction of an image-model. Their disagreement, I suspect, is over whether there is a requirement for conceptual guidance. But that doesn’t matter here, it suffices that Sellars acknowledges pre-conceptual image-models, which, as far as I can see, are the same thing as RSs. e. RECONCILIATION? Now my attempt to reconcile Sellars with these other philosophers would take the form of reinterpreting Chisholm’s (1) I know that this is F because it appears F. where ‘it appears F’ can be understood as ‘I am rs-aware of an image-model rs-F’.{97} And if we generalize, we can formulate the thesis that a perception of a physical object entails an rs-perception of an rs-(physical object), which in turn entails an rs-awareness of an rs-appearance. Would this be acceptable to Sellars? The answer is: no. His reason is this: although the objects of which we are directly aware in perceptual consciousness are image-models, we are not aware of them as image-models. It is by phenomenological reflection (aided by what Quine calls scientific lore) that we arrive at this theoretical interpretation of perceptual consciousness.{98} Sellars apparently accepts an RS (image-model world) as a theory which explains our perceptual knowledge, but not as an analysis of it. Sellars is introducing two difficulties for a reconciliation. The first difficulty is that although in point of theoretical fact we do experience image-models, we do not experience them in propria persona{99} as image-models. The point of denying the propria persona principle is that physical objects or events are conceptually constituted by various logical and causal relations, and these are never given by any sense modality, but must be learned. Sellars’ rejection of this principle is acceptable. The second difficulty for Sellars is that observational reports are not analyzable into, i.e., do not entail, phenomenal beliefs; rather, the image-world is accessible to phenomenological reflection. This is also acceptable. But Sellars seems to muddy the waters in this context by talking in the same breath about perceptual reflection and theory construction. When Sellars talks about theories he means postulational theory. I believe there is a difference between phenomenological reflection and theory construction. Sellars himself acknowledges this distinction when he writes: sheer phenomenology or conceptual analysis takes us part of the way, but finally lets us down. How far does it take us? Only to the point of assuring us that Something, somehow a cube of pink in physical space is present in the perception other than as merely believed in.{100} When Sellars is doing phenomenological reduction, he is not theorizing. The trouble with the above reduction, however, is that it is not reductive enough. This was the point made by Firth in his reply to Sellars’ Carus Lectures.{101} If we made the reduction go further we would get something like Chisholm’s analysis. To express the fact that we are dealing with a phenomenological reduction, let’s modify Chisholm’s formula (1) I see that this is F because it appears F. by expanding it to read (1′) I see that this is F because I can perceptually reduce this to it appears F. We can then agree with Sellars that (1) does not express an analysis; rather it expresses a phenomenological or perceptual reduction.{102} And if physical objects do entail (perceptually reduced) phenomenal reports, then empirical knowledge does have foundations.
ChatGPT said:
ChatGPT
To evaluate the soundness of the argument in this excerpt, we can break it down into several key elements and examine its internal consistency, adherence to philosophical principles, and logical progression.
1. Conceptual vs. Non-Conceptual Representation
The argument begins with a discussion of Sellars’ distinction between Language (L) and a Representational System (RS) and attempts to bridge this with the works of philosophers like Lewis, Firth, Chisholm, and others. It argues that certain concepts like Lewis’ ‘sense meanings’ and Chisholm’s ‘phenomenal reports’ can be understood as representations in an RS, which share certain characteristics like propositional form, Humean inferences, and the absence of logical connectives.
Evaluation:
- Internal Consistency: The distinction between Language and Representational Systems is well established in philosophy of mind, particularly in discussions of the relationship between language, thought, and perception. The argument seems internally consistent as it draws on established concepts (such as Sellars’ image-models and Kant’s schemas).
- Clarity of Claims: The author attempts to clarify the relationship between these various philosophers and their perspectives on representation, though some of the details (e.g., Lewis’ ‘sense meaning’) are not fully unpacked, which could make the argument difficult for a reader unfamiliar with the finer points of these thinkers.
2. Connection to Sellars’ View
The excerpt suggests that both Sellars and Lewis agree on the notion of an image-model, though they may differ in their interpretation of Kant. The central claim here is that these image-models are pre-conceptual and independent of logical connectives, and the author attempts to reconcile these views with Chisholm’s theory of perceptual knowledge.
Evaluation:
- Logical Flow: The progression from the discussion of Lewis and Sellars to the claim about pre-conceptual image-models is coherent. However, the argument becomes more complex when Sellars’ position is contrasted with Chisholm’s. The claim that Sellars would not accept the formulation “I am rs-aware of an image-model rs-F” is presented clearly, though it requires careful philosophical analysis.
- Soundness of Interpretation: The interpretation of Sellars’ view—that image-models are theoretical constructs used to explain perception but not directly accessible in perceptual consciousness—seems accurate. Sellars does indeed distinguish between the theoretical framework of perceptual knowledge and the direct, non-conceptual experience of perception. However, it would help to clarify how these image-models are operationalized in practice, as this is crucial to evaluating the reconciliation with Chisholm.
3. Reconciliation with Chisholm
The author proposes a modification of Chisholm’s formula for perceptual knowledge:
- (1) “I see that this is F because it appears F.”
- (1′) “I see that this is F because I can perceptually reduce this to it appears F.”
The aim is to align Chisholm’s formula with Sellars’ phenomenological approach, suggesting that perceptual knowledge can have empirical foundations even without being reducible to phenomenal beliefs.
Evaluation:
- Validity of the Modification: The modified formula (1′) seems to capture a more nuanced view of perception, distinguishing between direct perceptual experience and the reflective reduction of that experience. This approach appears to be a reasonable reconciliation of Sellars’ and Chisholm’s positions. It acknowledges that perception involves both non-conceptual awareness and a form of phenomenological reduction that doesn’t immediately reduce to conceptual analysis.
- Theoretical Soundness: The modification seems theoretically sound, as it respects Sellars’ critique of Chisholm’s formula while preserving the foundational role of perceptual experience. The move from a phenomenological reduction to a more general empirical framework also seems reasonable within the context of Sellars’ philosophy.
4. Challenges and Potential Weaknesses
- Ambiguity in Lewis’ ‘Sense Meaning’: As noted in the text, the precise nature of Lewis’ ‘sense meaning’ is difficult to pin down, which might undermine the clarity of the argument. If the connection between Lewis’ ideas and Sellars’ concept of image-models is unclear, the entire reconciliation could be less robust.
- Sellars’ Notion of ‘Phenomenological Reflection’: The distinction between phenomenological reflection and theory construction is important, but it is somewhat underexplored in this passage. While Sellars clearly acknowledges that phenomenological reflection is distinct from theoretical analysis, the argument could benefit from further elaboration on how these forms of reflection relate to empirical knowledge.
Conclusion
The argument is generally sound in its logical structure and philosophical engagement with the ideas of Sellars, Chisholm, and others. It presents a coherent attempt to reconcile Sellars’ and Chisholm’s views on perceptual knowledge by modifying Chisholm’s formula to account for both phenomenological reduction and empirical foundations. However, the argument would benefit from clearer explanations of some key concepts, particularly the interpretation of Lewis’ ‘sense meaning’ and a more detailed discussion of phenomenological reflection versus theory construction. Additionally, some claims, particularly about Sellars’ rejection of proprio persona, could use further clarification to ensure they align with Sellars’ overall philosophy.