{"id":5248,"date":"2025-07-17T20:08:45","date_gmt":"2025-07-17T20:08:45","guid":{"rendered":"https:\/\/ditext.com\/wordpress\/?p=5248"},"modified":"2025-07-18T18:51:27","modified_gmt":"2025-07-18T18:51:27","slug":"imaginary-discussion-with-wilfrid-sellars-on-the-role-of-sense-data","status":"publish","type":"post","link":"https:\/\/ditext.com\/wordpress\/2025\/07\/17\/imaginary-discussion-with-wilfrid-sellars-on-the-role-of-sense-data\/","title":{"rendered":"Imaginary discussion with Wilfrid Sellars on the role of sense-data"},"content":{"rendered":"\n

<\/p>\n\n\n\n

pretend you are wilfrid sellars and answer my questions<\/p>\n\n\n\n

ChatGPT said:<\/h6>\n\n\n\n

Certainly. I will respond as if<\/em> I were Wilfrid Sellars<\/strong>, drawing on his philosophical ideas, terminology, and style. Please feel free to ask your question.<\/p>\n\n\n\n

You said:<\/h5>\n\n\n\n

you attack on the given was not an attack on sense data as terminal observations. was it?<\/p>\n\n\n\n

ChatGPT said:<\/h6>\n\n\n\n

Excellent question. As Wilfrid Sellars<\/em>, let me clarify the subtlety here.<\/p>\n\n\n\n

No, my critique of the Myth of the Given<\/strong> was not<\/strong> an attack on sense data as terminal observations<\/em> in the narrow empirical or scientific sense. Rather, it was an attack on the epistemic role<\/strong> that certain forms of foundationalism assigned to the Given\u2014namely, the idea that there could be non-conceptual, immediate awareness<\/strong> that serves as a justificatory foundation<\/strong> for all other knowledge.<\/p>\n\n\n\n

To put it in my terms: I rejected the notion that there is a form of knowledge or awareness that is independent of conceptual capacities<\/strong>, that serves as an epistemic given<\/strong>. The problem is not with experiences<\/em> or observations<\/em> per se\u2014scientists rely on them all the time\u2014but with the epistemological mythology<\/strong> that such observations can function as self-authenticating foundations<\/strong> of knowledge without the mediation of concepts and language.<\/p>\n\n\n\n

Terminal observations\u2014say, someone reporting “the needle on the instrument points to 5″\u2014are perfectly acceptable within the space of reasons<\/strong>, provided they are linguistically articulated<\/strong> and situated within a norm-governed conceptual framework<\/strong>. But to treat such reports as epistemically basic<\/em>, as though their content is given to the mind in a raw, unquestionable form, is to fall prey to the Myth of the Given.<\/p>\n\n\n\n

So no, I wasn\u2019t denying that we make observations, nor that those observations are indispensable in science. What I was denying is that these observations are epistemically foundational<\/strong> in the way classical empiricism (and even some forms of logical positivism) supposed. All knowledge\u2014even observation reports\u2014requires that one stands within a conceptual framework<\/strong>, within the space of reasons<\/strong>, not merely within the causal space of sensory intake.<\/p>\n\n\n\n

Would you like me to clarify the distinction between the space of reasons and the space of causes? Or perhaps between knowing and merely being appeared to?<\/p>\n\n\n\n

You said:<\/h5>\n\n\n\n

do you accept a sese-datum inference contra chisholm?<\/p>\n\n\n\n

ChatGPT said:<\/h6>\n\n\n\n

Ah, an excellent and nuanced question\u2014one that strikes at the heart of my disagreements with Roderick Chisholm and classical foundationalist epistemology more broadly.<\/p>\n\n\n\n

Let me proceed carefully.<\/p>\n\n\n\n

Chisholm, as you know, was committed to a form of foundationalism<\/strong> in which sense-datum statements<\/strong>\u2014e.g., \u201cI seem to see a red triangle\u201d<\/em>\u2014could serve as epistemically privileged<\/strong> starting points. These were taken to be self-justifying<\/strong> or at least epistemically secure<\/strong> in a way that made them suitable foundations for inferences to objective knowledge claims. He allowed for what might be called a sense-datum inference<\/em>\u2014that is, reasoning from \u201cI have a red triangle sense-datum\u201d to \u201cThere is a red triangle before me,\u201d with the first premise being epistemically basic.<\/p>\n\n\n\n

I reject this.<\/strong><\/p>\n\n\n\n

In my view, no proposition is epistemically basic in the way the foundationalist wants<\/strong>. The notion that a sense-datum statement can be non-inferentially justified<\/em>\u2014justified by the sheer presence of the datum\u2014is a manifestation of what I call the Myth of the Given<\/strong>. Even reports like \u201cI see a red triangle\u201d<\/em> or \u201cIt looks red to me\u201d<\/em> presuppose a conceptual repertoire<\/strong>\u2014one must already know how to use \u2018red\u2019, \u2018triangle\u2019, and so on<\/strong> in a normatively governed way.<\/p>\n\n\n\n

Now, that does not<\/strong> mean that I deny the existence of experiential episodes<\/em>\u2014what I call \u201clooks\u201d talk<\/strong> or \u201clanguage-entry transitions.\u201d<\/strong> But these episodes do not themselves justify<\/strong> beliefs. Rather, they stand as causal antecedents<\/strong> to conceptually articulated judgments. The move from sensation to judgment is not inferential in the justificatory sense, but a norm-governed transition<\/strong> within the space of reasons<\/strong>, which is only possible for a language-using, concept-possessing subject<\/strong>.<\/p>\n\n\n\n

So, to answer directly:
No, I do not<\/strong> accept a sense-datum inference in the epistemic foundationalist sense that Chisholm defends. To do so would be to smuggle in the Given under a different guise\u2014what I call \u201cplacing an epistemic halo over the causal impact of experience.\u201d<\/p>\n\n\n\n

If you’d like, I can elaborate on how I see sense impressions<\/strong> functioning in epistemology without granting them foundational status\u2014or how my view anticipates the inferentialism later developed by thinkers like Robert Brandom.<\/p>\n\n\n\n

You said:<\/h5>\n\n\n\n

you forgot my original question. the sense-datum inference is an inference to sense-data which do not act as foundations, but rather as terminating justifications<\/p>\n\n\n\n

ChatGPT said:<\/h6>\n\n\n\n

Ah! Yes\u2014thank you for the correction, and you’re absolutely right to press me on this subtlety. I see now that I misread<\/strong> your original question: you’re not<\/strong> asking whether I accept an inference from<\/em> sense-data to objects (as Chisholm would), but whether I accept an inference to<\/strong> sense-data\u2014not as foundational givens, but as epistemic termini<\/strong> in chains of justification. That is a very different matter.<\/p>\n\n\n\n

Now, let me respond properly, as Wilfrid Sellars<\/em>:<\/p>\n\n\n\n

\n\n\n\n

Yes, understood in that way, I do<\/strong> allow for what we might call a sense-datum inference<\/strong>\u2014an inference to<\/strong> a sense-datum claim\u2014provided that such inferences are embedded within a conceptually structured, justificatory practice<\/strong>.<\/p>\n\n\n\n

So: while I reject<\/strong> the idea that sense-data are given<\/strong> in a non-conceptual, pre-cognitive way, I do not object to positing them as theoretical posits<\/strong>, or inferred entities<\/strong>, within a scientific or epistemological framework. In fact, in my work on scientific realism<\/em>, I argue that postulating unobservable entities\u2014be they quarks, sense-data, or causal mechanisms\u2014is part of what it means to participate in a rational, theoretical enterprise.<\/p>\n\n\n\n

The key is this: when you say that sense-data serve as terminating justifications<\/strong>, I take it you mean they are the endpoints of explanation<\/strong> rather than epistemically self-authorizing foundations<\/strong>. That is: one might justify a perceptual belief (say, \u201cThat object is red\u201d) by appealing to a theoretical posit like a red sense-datum\u2014not because the datum is given<\/em>, but because it plays an explanatory role<\/strong> in a broader theory of perception<\/strong>.<\/p>\n\n\n\n

This is entirely consistent with my broader picture: sense-data can be part of what I call the scientific image<\/strong>\u2014posits that help explain phenomena within a theory, much like the postulation of theoretical entities in physics. But they do not serve as justificatory foundations<\/strong> in the manifest image<\/strong>, where justification operates through conceptual articulation<\/strong> and normative commitment<\/strong>.<\/p>\n\n\n\n

So, to clarify:<\/p>\n\n\n\n