Escaping from Bullshit

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.

You said:

Evaluate soundness:

A reconstruction of Wilfrid Sellars’s Argument that the given is a myth, from “Empiricism and the Philosophy of Mind”.

1. A cognitive state is epistemically independent if it possesses its epistemic status independently of its being inferred or inferable from some other cognitive state. [Definition of epistemic independence]

2. A cognitive state is epistemically efficacious — is capable of epistemically supporting other cognitive states — if the epistemic status of those other states can be validly inferred (formally or materially) from its epistemic status. [Definition of epistemic efficacy]

3 The doctrine of the given is that any empirical knowledge that p requires some (or is itself) basic, that is, epistemically independent, knowledge (that g, h, i, …) which is epistemically efficacious with respect to p. [Definition of doctrine of the given]

4. Inferential relations are always between items with propositional form. [By the nature of inference]

5. Therefore, non-propositional items (such as sense data) are epistemically inefficacious and cannot serve as what is given. [From 2 and 4]

6. No inferentially acquired, propositionally structured mental state is epistemically independent. [From 1]

7. Examination of multiple candidates for non-inferentially acquired, propositionally structured cognitive states indicates that their epistemic status presupposes the possession by the knowing subject of other empirical knowledge, both of particulars and of general empirical truths. [From Sellars’s analyses of statements about sense-data and appearances in Parts 1–IV of EPM and his analysis of epistemic authority in Part VIII]

8. Presupposition is an epistemic and therefore an inferential relation. [Assumed (See PRE)]

9. Non-inferentially acquired empirical knowledge that presupposes the possession by the knowing subject of other empirical knowledge is not epistemically independent. [From 1, 7, and 8]

10. Any empirical, propositional cognition is acquired either inferentially or non-inferentially. [Excluded middle]

11. Therefore, propositionally structured cognitions, whether inferentially or non-inferentially acquired, are never epistemically independent and cannot serve as the given. [6, 9, 10, constructive dilemma]

12. Every cognition is either propositionally structured or not. [Excluded middle]

13. Therefore, it is reasonable to believe that no item of empirical knowledge can serve the function of a given. [5,11, 12, constructive dilemma]

ChatGPT said:

The argument you’ve reconstructed from Wilfrid Sellars’s Empiricism and the Philosophy of Mind proceeds in a highly structured manner, aiming to demonstrate that the “given” (the idea of a non-inferential, epistemically independent foundation for empirical knowledge) is a myth. To evaluate the soundness of this argument, we need to consider whether the premises are true and whether the reasoning from premises to conclusion is valid. Here’s an evaluation:

1. Premise Evaluation:

• Premise 1: The definition of epistemic independence seems reasonable: A cognitive state is epistemically independent if it holds its epistemic status without being inferred or inferable from another state. This is a standard notion in epistemology.
• Premise 2: The definition of epistemic efficacy also appears sound: A cognitive state can support others if its epistemic status can validly infer the status of others. This is consistent with the standard view in inferential epistemology.
• Premise 3: The definition of the doctrine of the given is in line with Sellars’s criticism of empiricist accounts of knowledge that posit certain basic, independent, non-inferentially acquired states.
• Premise 4: The claim that inferential relations are always between items with propositional form seems reasonable. In formal logic and many epistemological frameworks, inferences are typically made between propositions.
• Premise 5: The conclusion that non-propositional items (like sense data) cannot be epistemically efficacious follows logically from Premise 2 and Premise 4. This aligns with Sellars’s argument that sense data are not directly epistemically supportive in the way that inferentially derived propositions are.
• Premise 6: The claim that inferentially acquired, propositionally structured mental states are never epistemically independent is plausible within the context of Sellars’s argument that all cognition is inferential to some degree, even if not explicitly in every case.
• Premise 7: This is a key claim in Sellars’s argument, and it draws on his detailed critique of the empiricist tradition. The analysis seems robust but could be contested if one were to challenge Sellars’s specific examples or analyses. Nevertheless, the general thrust is consistent with his work.
• Premise 8: The assumption that presupposition is an epistemic (and thus inferential) relation is defensible. In Sellars’s view, presuppositions involve assumptions about the world that are themselves dependent on inferential relations.
• Premise 9: This follows from the earlier premises and seems valid: if non-inferential knowledge presupposes other empirical knowledge, it cannot be epistemically independent.
• Premise 10: The excluded middle here is standard in epistemology: knowledge is either acquired inferentially or non-inferentially, leaving no middle ground.
• Premise 11: This follows logically from the earlier premises and is the crux of the argument: all empirical knowledge is either inferentially or non-inferentially acquired, and neither can provide epistemic independence.
• Premise 12: Again, this is a standard excluded middle in epistemology and doesn’t require much scrutiny.
• Premise 13: The final conclusion that no empirical knowledge can serve as a given follows from the earlier conclusions.

2. Reasoning Evaluation:

• Validity: The reasoning from premises to conclusion seems valid at each step. The argument is a chain of logical deductions, where each conclusion follows from the premises. The use of constructive dilemmas, excluded middles, and logical inferences is consistent with formal logical reasoning.
• Overall Soundness: The soundness of the argument depends on the truth of the premises. Most of the premises are reasonable and align with Sellars’s critique of empiricist philosophy, especially his rejection of the idea that there can be a foundational, non-inferential “given.” However, some premises (such as Premise 7, which refers to Sellars’s analysis of sense data) could be challenged, as not all readers may agree with Sellars’s specific criticisms of sense-data theories.

3. Potential Criticisms:

• Premise 6 (about inferentially acquired mental states being never epistemically independent) could be contested by those who argue for forms of non-inferential knowledge that do not require full inferential justification, such as certain perceptual experiences or a-priori knowledge.
• Premise 7 (regarding presupposition and empirical knowledge) could be questioned by those who argue that some empirical knowledge might have a form of independence from other empirical knowledge, particularly in phenomenological or immediate experience accounts.

Conclusion:

Overall, the argument is logically valid, and most premises are reasonable within Sellars’s framework. The potential criticisms mainly concern the details of Sellars’s analysis of sense data and the presupposition of empirical knowledge. Given these considerations, the argument appears sound within its intended context, though it could be debated depending on one’s epistemological stance regarding non-inferential knowledge.

4o mini

You said:

Romane Clark claimed that sense-data have a propositional form. How does this challenge affect the above argument?

ChatGPT said:

ChatGPT

Roman Clark’s claim that sense-data have a propositional form would pose a significant challenge to the argument above, particularly to Premise 5 and the reasoning in Steps 5, 6, and 11. Let’s explore how this claim interacts with the argument:

Key Point of Challenge:

Premise 5 in the original argument concludes that sense-data (which are non-propositional) cannot be epistemically efficacious and thus cannot serve as “the given.” If Clark is correct in claiming that sense-data have a propositional form, it means sense-data could potentially function as epistemically efficacious and thus fulfill the role of “the given” in a way that the argument rejects.

Where the Challenge Hits:

1. Premise 5: “Non-propositional items (such as sense data) are epistemically inefficacious and cannot serve as what is given.”
   • If sense-data are indeed propositional in form (as Clark suggests), then they would no longer be non-propositional items. As a result, this premise would be undermined, as sense-data could, in principle, support inferential relations and contribute to epistemic efficacy.
   • The reasoning that non-propositional items cannot be epistemically efficacious depends heavily on the assumption that sense-data are non-propositional. Clark’s claim would challenge this assumption and thereby invalidate the conclusion that sense-data cannot serve as “the given.”
2. Premise 6: “No inferentially acquired, propositionally structured mental state is epistemically independent.”
   • If sense-data are propositional, this premise could still hold in the context of the original argument, as the idea of epistemic independence pertains to the inferential structure of cognition. However, the core of the challenge arises in the later stages, particularly when considering the nature of “the given.”
   • The fact that sense-data might now be propositional would imply that they could, in some form, be part of an epistemic process that supports other cognitive states. This could introduce an element of non-inferential propositional knowledge, which the argument claims is impossible.
3. Premise 11: “Therefore, propositionally structured cognitions, whether inferentially or non-inferentially acquired, are never epistemically independent and cannot serve as the given.”
   • This is the crux of the argument, and Clark’s claim would challenge it by allowing for the possibility that sense-data, as propositionally structured, could indeed serve as non-inferential knowledge—an epistemic foundation. If sense-data have a propositional form, they could potentially meet the criteria for being part of the given (as non-inferential and epistemically independent).
   • This would make the claim that “no empirical knowledge can serve the function of a given” less secure, because the new possibility of propositional sense-data could open the door for some form of non-inferential knowledge that might still function as “the given.”

Impact on Sellars’s Argument:

Clark’s claim disrupts Sellars’s central critique of empiricism by suggesting that sense-data, which were traditionally considered non-propositional and inefficacious, could instead play a foundational role in knowledge. If sense-data are propositional, it raises the possibility that they could have epistemic efficacy by supporting inferences and serving as a basis for knowledge in a way that Sellars argues the “given” cannot.

Thus, Clark’s view would weaken Sellars’s argument in two key ways:

• Premise 5 would need to be revised, as sense-data would no longer be non-propositional.
• Premise 11 (the rejection of the given) would be less convincing, because propositional sense-data could, in theory, serve as a non-inferential foundation for empirical knowledge.

In conclusion, if sense-data are propositional, the argument from Empiricism and the Philosophy of Mind would lose some of its force. The concept of the “given” would no longer be easily dismissed, as Clark’s view allows for a form of knowledge (sense-data) that could be both epistemically independent and epistemically efficacious.

ChatGPT said:

ChatGPT

Yes, C.D. Broad’s exhaustive classification of mind-body relations can serve as an inspiration for a similar kind of systematic approach in epistemology. In epistemology, one might classify various theories of knowledge, belief, justification, and truth along a few key axes. Here is a conceptual framework that mirrors Broad’s approach but applied to the field of epistemology:

1. Source of Knowledge

• Empiricism: Knowledge comes primarily from sensory experience.
  • Classical Empiricism (e.g., Locke, Berkeley, Hume): All knowledge is derived from sensory experiences.
  • Modern Empiricism (e.g., A.J. Ayer, Quine): Knowledge is based on empirical observations and the verification of statements.
• Rationalism: Knowledge is derived primarily from reason and intellectual insight.
  • Classical Rationalism (e.g., Descartes, Leibniz, Spinoza): Knowledge is obtained through innate ideas or deduction from basic principles.
  • Modern Rationalism (e.g., Kant): Knowledge is shaped by both experience and a priori reasoning, with structures imposed by the mind.
• Constructivism: Knowledge is a product of cognitive constructions rather than an objective discovery.
  • Radical Constructivism (e.g., Piaget, von Glasersfeld): Knowledge is actively constructed by individuals based on their experiences and mental models.
  • Social Constructivism (e.g., Vygotsky, Berger and Luckmann): Knowledge is socially constructed through language and interaction.

2. Nature of Justification

• Foundationalism: Justification for knowledge must ultimately be based on basic, self-evident beliefs or principles.
  • Classical Foundationalism (e.g., Descartes, Locke): Some beliefs are justified by direct intuition or sensory experience, and all other beliefs derive justification from these.
  • Contemporary Foundationalism (e.g., Chisholm): Basic beliefs or foundational beliefs are justified without relying on other beliefs, forming a foundation for all knowledge.
• Coherentism: Beliefs are justified by their coherence with a system of beliefs, rather than relying on basic, foundational beliefs.
  • Classical Coherentism (e.g., Bradley, Hegel): A belief is justified if it coheres with a set of beliefs, even if those beliefs are themselves unproven.
  • Contemporary Coherentism (e.g., BonJour, Sellars): A belief is justified within the context of a web of interconnected beliefs that support each other.
• Reliabilism: Justification for knowledge comes from the reliability of the process by which beliefs are formed.
  • Classical Reliabilism (e.g., Goldman): Beliefs are justified if they are produced by a reliable cognitive process.
  • Contemporary Reliabilism (e.g., Plantinga, Sosa): Knowledge is justified if it comes from a process that reliably leads to truth in the relevant environment.

3. Nature of Knowledge

• Empirical Knowledge: Knowledge gained from sensory experience and observation of the external world.
  • Scientific Realism (e.g., Putnam, Boyd): The belief that scientific theories accurately describe the world.
  • Anti-Realism (e.g., Kuhn, Feyerabend): The view that scientific theories are simply useful tools, not necessarily true descriptions of the world.
• A Priori Knowledge: Knowledge that is independent of experience and derived from reason alone.
  • Mathematical Knowledge (e.g., Frege, Gödel): Knowledge of abstract entities or relations that can be known through logical deduction or pure reason.
  • Philosophical Knowledge (e.g., Kant, Kripke): Knowledge of necessary truths that can be known independently of empirical experience.
• Tacit Knowledge: Knowledge that is difficult to express in words but is nonetheless known and applied.
  • Implicit Knowledge (e.g., Polanyi): Knowledge that individuals possess and act upon but may not be able to explicitly describe.
  • Procedural Knowledge (e.g., Ryle): Knowledge of how to perform actions, which is often non-verbal and practical.

4. Truth and Its Relation to Belief

• Correspondence Theory: Truth is a matter of how beliefs correspond to reality.
  • Classical Correspondence (e.g., Aristotle, Tarski): Truth is what corresponds to the state of affairs in the world.
  • Contemporary Correspondence (e.g., Armstrong, Dummett): Truth is still tied to reality, but the criteria for correspondence may be more nuanced or dependent on linguistic structures.
• Coherence Theory: Truth is determined by the coherence of beliefs within a system.
  • Classical Coherence (e.g., Hegel, Bradley): Truth is a property of a coherent set of beliefs.
  • Contemporary Coherence (e.g., Davidson, Quine): Truth arises from the coherence of beliefs, but may also be informed by practical or external factors.
• Pragmatism: Truth is that which works or is useful in practice.
  • Classical Pragmatism (e.g., Peirce, James, Dewey): Truth is evaluated by its practical consequences or its effectiveness in guiding action.
  • Neo-Pragmatism (e.g., Rorty): Truth is not objective but is based on social consensus and practical utility.

5. External vs. Internal Epistemology

• Externalism: Knowledge is justified by factors outside the subject’s internal mental states.
  • Contextualism (e.g., David Lewis): The justification of knowledge claims depends on the context in which they are made.
  • Externalist Epistemic Reliabilism (e.g., Goldman, Nozick): Knowledge is justified if it is reliably produced by cognitive processes, even if the subject is unaware of those processes.
• Internalism: Knowledge justification depends on factors within the subject’s own internal mental state.
  • Classical Internalism (e.g., Descartes, Chisholm): Justification must be accessible to the subject’s conscious reflection.
  • Contemporary Internalism (e.g., Bonjour, Feldman): Knowledge is justified if the subject can, in principle, reflectively access the grounds for their belief.

This classification mirrors the exhaustive and systematic nature of Broad’s mind-body relations framework, applying the same logical structure to categorize different positions within epistemology. It helps clarify the many ways philosophers approach knowledge, justification, and belief, much like Broad’s matrix helped organize different philosophical stances on the mind-body problem.