I asked chat GPT to reformulate as an argument and test its soundness the followong passage from my dissertation on Wilfrid Sellars:
D. APING REASON
But the inclusion or exclusion of auxiliary positions or rules of inference in L locates the difference but does not express it. The difference is more fundamental. The essential demarcation between RS and L lies, as has been noted, in the availability of logical and modal words in L, and their unavailability in RS. The obvious objection to this — an objection which I have entertained for a long time, and which I thought was the Achilles’ heel of Sellars’ philosophy — was to think that animal behavior displays an analogy to logical inference. And therefore, I thought, the difference between L and RS is drawn at the wrong place. But is it drawn at the wrong place? Sellars is quite aware of behavior in animals which resembles logical inference — it is what has already been referred to by Sellars as ‘Humean inference’, and which B. Russell described as ‘animal inference’.{77} Sellars also notes that Leibniz spoke of this as a “consecutiveness which imitates reason.”{78} An example of a Humean inference, it will be recalled, was: ‘Smoke here’, ‘fire nearby’. And it resembles the Aristotelian inference: ‘Smoke here,’ ‘If smoke anywhere, then fire nearby’, ‘fire nearby’. The resemblance lies in the transition from similar initial states to similar end states, i.e., from an analogous observations of ‘Smoke here’ to analogous mental states of ‘Fire nearby’. The objection may be pushed further. It can be conceded that the difference between RS and L is in the availability of the auxiliary positions. But this is an accidental distinction. For, after all, Sellars himself had admitted that such positions are dispensable. Their role can be taken over by the rules of inference. Are we to attribute an awareness of rules to animals? How would that be possible? Rules are, after all, formulated in a language. And if an animal has rules, they must be contained in a meta-RS. Yes, the objector may continue, Sellars has conceded that animals may be said to have meta-representations. So why can’t we attribute to them rules expressed in a meta-representation? To answer this objection, we have to start by pointing out that Sellars distinguishes between rule-conforming (or rule-patterned) and rule-following (or rule-regulated) behavior. The difference between them is that rule conforming behavior does not involve the formulation of a rule as an element in conscious thought, while rule following behavior does. For example, a rat, after being trained to run a maze, has a representation of the maze in the sense that given the proper context, being in one position of the maze will trigger off a series of appropriate responses. Now contrast this with a human car driver who consults a map to guide him in his journey. The ‘map’ in the rat’s case is not something consulted; whereas in the driver’s case it is. To keep to the metaphor, the rat acts non-consciously in conformity to the path on the map; the driver acts by consciously following the path on the map. Inference rules are, then, rules which are available for consultation. While no rules are available for consultation to an RS organism. The reason is this. A rule is, as Sellars points out, always a rule of action of the form: ‘If you want to bring about the result R, then if the circumstances are C, then you must (ought, may, may not, cannot, etc.) do action A’.{79} It is because an RS organism cannot infer through the process of obeying a rule that it cannot be said to ‘infer’ in the primary sense of ‘inference’, which is ‘Aristotelian inference’. As Sellars puts it, “an intra-linguistic move is not in the full sense an inference unless the subject not only conforms to but obeys syntactic rules.”{80} Why is a rule (or its analogue) not available to an animal? Sellars’ answer is straightforward. An animal does not have the required logical vocabulary that is explicitly expressed by the rule formula, nor the logical connections (meanings) that are implied by the use of the rule formula. Suppose the objector responds by claiming that logical connector analogues are available to an RS organism. For example, a rat can be trained to respond to, let’s say, a pink cube. And it refuses to respond to other colors and volumes. Isn’t this refusal to respond an analogue of negation? Sellars asks this question explicitly: “How can a pre-logical RS ape the use of negation?”{81} His answer is that indeed a Humean RS organism has the resources of accepting or rejecting a proposition, but notes that we, as Aristotelian RSs, not only have the resources of accepting or rejecting a proposition, but we also have the resources of affirming or negating a proposition as well. And (our) concept of negation is not equivalent to (our) concept of rejection. The latter concept, he tells us, is more basic. Negation entails rejection, but not vice versa.{82} Sellars argues that from our perspective, if an RS organism rejects p, this entails (for us) that it does not represent p. But from our perspective, these are equivalent for it. Now our notion of not representing p includes representing not-p. And (for us) representing not-p entails rejecting p (which is equivalent for the RS to not representing p). But not representing p does not entail the representing of not-p. Therefore, argues Sellars, “The concept of rejection is more basic than the concept of negation.”{83} This is to say that our concept of negation is a richer concept than that of rejection. This conclusion seems to be correct for yet another reason. Consider the fact that we can make a distinction between the negation of a sentence and the negation of the predicate of a sentence, i.e., ‘It is not the case that p’ and ‘This a in not F’. The latter entails the former, but the former does not entail the latter. A Humean RS would fail to make the distinction by representing both cases through the rejection of the propositions. If it is granted to Sellars that negation is not available to an RS organism, then it also follows that none of the other truth-functional logical constants are available to an RS organism as well. This follows from the fact that truth-functions require one primitive logical constant with negation, and all other logical constants are interdefinable with the inclusion of the negation operator. We can make even a broader generalization by saying that no conceptual propositions at all are available to an RS organism since their meanings are dependent on their logical connections with other propositions. And as a corollary, no proposition which entails a truth-functional proposition is available to an RS organism. Now normally a truth-functional logic or a truncated form (which includes negation) is part of most other logics, such as modal and intuitive logics. If that is the case, then none of these dependent logics are available to an RS organism either. A specific case concerns Sellars’ material rules of inference which are correlative to ‘causal laws’. He writes, “For a lucid presentation of the fundamentals of a logic of causal modalities, see Burks . . . “{84} In Arthur Burks we are given the following axiom: “a causal implication [materially] implies a material implication.”{85} The significance of this is that an RS organism, by this reasoning, lacks the concept of a causal law because it lacks the correlative material rule of inference. There is one last point which must be cleared up. All that has been said so far seems to be compatible with the view that human beings, in possessing a language, are able to perceive negative facts. This is not Sellars’ view. All logical operators, as well as various modal and semantical words, are ultimately to be located in the metalanguage. Their role is to enable us to move from propositions to propositions. At the object level there are only positive sentences which picture reality. Thus, a form such as ‘not-p’ is to be understood as the denial of the truth of p.{86} With these observations in place, I can make the following conclusions on the difference between RS and L (using organisms). Although both use the entry to RS, intra-RS, and RS departure transitions, and although both use rs-propositions, and both have meta-representations; because primitive RSs lack a logical vocabulary, RS organisms can, at best, conform to inference rules. This has the appearance of aping reason. But only an L has a logical vocabulary which enables an L organism to follow rules — both formal and material. And here is a crucial point for Sellars. To have words in one’s vocabulary that are essential in formal and material inferences is to have concepts: the conceptual meaning of a descriptive term is constituted by what can be inferred from it in accordance with the logical and extra-logical rules of inference of the language (conceptual frame) to which it belongs.{87} But if we expand on this by including such auxiliary positions as expressions of value and obligation, then the broader formulation becomes: “to express a concept is to be relevant to inferences which can be drawn from statements in which the expression occurs.”{88}
ChatGPT said:
Reformulation of the Argument:
- Premise 1: The difference between RS (representational systems without logical vocabulary) and L (linguistic systems with logical vocabulary) lies in the availability of logical and modal vocabulary in L and their unavailability in RS.
- Premise 2: Animal behavior, though seemingly analogous to logical inference (e.g., “Humean inferences”), does not constitute genuine inference because animals conform to rules rather than follow them. Rule-following requires the consultation of a logical vocabulary, which animals lack.
- Premise 3: Inference rules involve explicit logical vocabulary and entail awareness of rules as entities that can be consulted. RS organisms lack this capacity, operating instead by behavioral conformity.
- Premise 4: Logical constants (e.g., negation, conjunction) require linguistic representation, which RS organisms lack. Therefore, RS organisms cannot possess concepts dependent on logical connections or propositional structures.
- Premise 5: Human language, as part of L, provides a framework for not only representing but also negating and affirming propositions. This is richer than mere acceptance or rejection seen in RS organisms.
- Conclusion: RS organisms may appear to “ape” reason by conforming to patterns analogous to rule-governed behavior, but they cannot engage in genuine Aristotelian inference. Only L organisms, with access to a logical vocabulary, engage in true conceptual thinking and rule-following.
Testing for Soundness:
- Validity (Logical Structure):
- The argument is logically valid. If the premises are true, the conclusion logically follows that RS organisms cannot engage in true inference, while L organisms can.
- Truth of Premises:
- Premise 1: Sellars’ distinction between RS and L is well-supported in the text and hinges on the role of logical vocabulary. This premise is plausible within Sellars’ framework.
- Premise 2: The claim that animal behavior exhibits “Humean inference” but not genuine Aristotelian inference is grounded in Sellars’ distinction between rule-conforming and rule-following behavior. This distinction is theoretically sound and widely accepted in philosophical discussions of cognition.
- Premise 3: The necessity of a logical vocabulary for rule-following behavior is a strong claim and aligns with Sellars’ philosophy of language. However, one might challenge whether meta-representational capacities in animals could serve as a primitive form of “rule awareness.”
- Premise 4: Logical constants requiring linguistic representation is defensible but contingent on the acceptance of Sellars’ framework. Some cognitive scientists argue that non-linguistic organisms might possess proto-logical operations.
- Premise 5: The distinction between negation and rejection is coherent within the logical structure of L, but empirical challenges could arise concerning the continuity between human and animal cognition.
- Empirical Support:
- The argument assumes clear distinctions between human and animal cognition. While plausible, this view is debated, especially in fields like comparative cognition and animal behavior.
Soundness Assessment:
The argument is valid and sound within Sellars’ framework. However, its broader soundness depends on whether one accepts Sellars’ assumptions about the necessary role of language in logical reasoning and inference. Empirical challenges might arise regarding whether animals possess meta-representational capacities or proto-logical structures. If these challenges are substantial, the argument’s second and fourth premises may require refinement.