This essay records a change of mind. For years I did not take David Chalmers’ neuron replacement arguments seriously. Part of my reason was Chalmers himself: he holds them as a property dualist, so he does not read them as showing that experience consists in functional organization at all. Arguments their own author declines to draw the functionalist conclusion from did not look to me like arguments a functionalist could bank. The rest of my reason was mine. I drew no line between wide and narrow functionalism, and I still kept the ghost of Descartes in the house — the imaginary mental furniture of indirect realism, and the extra non-physical property I took experience to add to the physical world.

I have since let all of that go. Seeing reaches the world itself, with nothing standing in between. Chalmers’ replacement arguments succeed, and they still never reach the question they claim to settle. They leave out the world.

Look at something red — a wall, a mug, the inside of your eyelid in sunlight. Now imagine the neurons behind that look going one at a time, each replaced by a chip that does exactly what the neuron did. Chalmers built the two constructions that settle what happens into the seventh chapter of The Conscious Mind in 1996, and has spent the thirty years since defending them, cheerfully, against nearly everyone. Functionalism survives them; what does not survive is the narrow, skin-bounded species of it, and with the wide kind I have no quarrel.

Their target, absent qualia, says a perfect functional duplicate of you might have no inner life at all — lights on, behavior running, nobody home. You cannot refute that by looking: ask the duplicate whether it sees anything and it says yes, because saying yes belongs to the profile you copied. So Chalmers refutes it by building.

Fading qualia runs the first build. Replace your neurons one at a time with silicon chips of identical causal role, so the whole keeps working at every step. If the finished duplicate were a zombie, the experience had to drain away somewhere along the path, and whoever it drained out of would have to fail to notice. That is the part the picture cannot keep. Hold the fine-grained organization fixed and you hold the noticing fixed with it, since every judgment you make about your own experience belongs to the causal profile that was copied. So the case can never be the one with any grip on us — you, watching the red go and unable to get the words out. It has to be a fully alert mind wired to a washed-out experience it never once remarks on. Cut experience that far loose from its owner’s every judgment about it and you have stopped talking about experience. So qualia do not fade; organization carries them.

Dancing qualia kills the inverted cousin the same way: wire a switch between your visual cortex and a silicon copy and throw it. If the two ran inverted, your experience would lurch red-to-blue while every word, belief, and reaction held steady, and you would notice nothing. Same absurdity. Chalmers packs both into one principle: fix a system’s fine-grained functional organization and you fix its experience, down to the last shade.¹ Granted, all of it. Both constructions work, and I know no repair for absent qualia. Granted in full within their scope, then: carbon to silicon, neurons to beer cans and string, no change of experience from the material alone, in the world where the swapping happens.

But look at what “hold everything else in place” includes. You vary the stuff of the parts and nail down the rest: the body, the eyes, the red wall, the light, the standing traffic between the being and the colored world. The constructions must hold the world still, since they work inside one head, in one world, letting the subject’s own judgments catch any drift. The fixed world serves as the control, so the license runs narrower than the famous conclusion: not “organization is all that matters,” only “given the world as it stands in any given moment, substrate does not matter.” The world sits inside the given; it never gets a vote.

Here lies the slip the computationalist charter runs on — the working creed that a mind just is a program, and a program runs anywhere. The creed is no straw man; it has signatories, and has had them from the start. Hilary Putnam wrote its founding sentence in 1967: to be capable of feeling pain just is to possess an appropriate kind of functional organization, spelled out as a machine table and nothing else. Putnam himself took it apart later, using the very argument this essay leans on. Sixty years on, Simon Goldstein and Cameron Domenico Kirk-Giannini argue that conscious language agents would be easy to build if they do not already exist — a verdict about inner life resting wholly on architecture, delivered about systems that have never seen anything.² (By “functionalism” from here on I mean that charter’s short-arm, program-portable species; the wide kind gets its welcome below.) From “the substrate does nothing” the charter leaps to “only internal organization does anything, so the right program, in any world or none, carries the same experience.” You cannot make that leap. The reason sits in the machinery. Both arguments work as reductios, and a reductio here needs a wedge: daylight between experience and the judgments its owner makes about it. Call that the wedge rule — these constructions bite only where experience can come apart from the owner’s verdict on it. No wedge, no reductio. Chalmers pries a wedge open by swapping parts under one subject’s nose, letting the subject’s own comparisons register the drift. Vary the world instead and the rule finds nothing to work on, because judgment and memory face the world too and travel with it. You can assemble a cross-world case; you cannot make it absurd. The proof stops where its own construction stops, the way a chemist’s assay stops at its clamped temperature.

Chalmers’ defender has a fair reply: proved principles generalize all the time, and no chemist re-runs the assay for every sample. Quite so — but generalizing past a clamped variable stays safe only while nothing turns on it, and here someone claims that variable makes the seeing.

And Chalmers saw it. He did not overlook the world; he scoped his principle to internal organization and said so. The slip belongs to the charter’s readers, who wave fading and dancing qualia at every world-shaped doubt. When the world-varying case reached him (Ned Block’s, in a moment), he answered in a single sentence: wearing color-inverting lenses under Inverted Earth’s sky, my internal organization stays as it was, “and my experience will be the same too.”³ Read that twice. It applies the principle where the principle’s own arguments never reached. He does hold independent arguments for narrow felt character; when he needs a world-varying verdict he reaches for those, never for these. Where the substitution arguments run, Chalmers argues and wins. Where the world varies, they go silent, and only the charter keeps talking.

So run the construction the machinery never touched: fix the organization and move the world. Hilary Putnam showed the method fifty years ago with Twin Earth — same insides, different contents, the difference supplied entirely by the world each thinker plugs into.⁴ Carry it into color. My phenomenal red consists in my states tracking a certain reflectance,⁵ so a functional twin among different reflectances sees differently: identical organization, different experience. That rides on the identity as much as on Putnam: Putnam moves the meanings, and the identity moves the seeing with them.

Or cut the world off altogether: a system assembled in the vat from the start, every mechanism intact, no history among surfaces, fed numbers that touch no wavelength and no object. The computation survives; the world-relations never existed. Does phenomenal red ride along? The charter says yes; the wedge rule says the machinery never reached this far, and the warrant lapsed the instant we unfixed the world. My answer runs the other way: nothing its states reach toward. The norm may count as the system’s own; the address has no far end, so nothing gets presented, and where nothing gets presented there is nothing it is like. The vat runs the syntax of experience with the semantics stripped out, and the semantics carries the felt character.⁶ A flawless set of books, kept for a business that never opened.

Chalmers presses the obvious objection, with two books behind it: “The Matrix as Metaphysics” and Reality+, which find a life among bits lacking nothing. A stream of bits is a structured environment, so why count bit-patterns untrackable and reflectances trackable? Split the verdict, then. Where the bits sit at the far end of a causal history the system has stood in, the twin’s verdict applies, not the vat’s: different world, different content, different seeing. The null verdict covers only the case I stipulated, numbers arriving from nowhere the system has ever stood. Either way, what a system sees answers to the world it stands in.

The sharp internalist will run Chalmers’ machinery exactly where I say it stops, and the move deserves trying: replace my retinas cell by cell with transducers fed identical signals, the world severed, every internal state held. If fading proves absurd there too, hasn’t the internalist verdict been derived after all? Ask which severed system we mean, because this case splits too.

Cut the cable this morning and my states keep the address their history fixed. I go on seeing — seeing wrongly, a red wall where only a signal generator sits, but seeing. The construction runs there and correctly finds no fade, and the internalist collects nothing: that case decides nothing either way. Now run the clock, and watch what it cannot produce. An unrenewed history degrades what my states present, and by the same stroke it degrades my judgments about them, since those judgments reach for the world along the very traffic that has stopped. The two never come apart — and coming apart is precisely what the wedge rule wants. So I owe no schedule: fast, slow, or by fits, the reductio finds nothing to pry at anywhere along the line. The internalist has not derived his conclusion; he has run a reductio whose absurdity never arrives. I pay that price in the open — the long-severed system’s beliefs about its own experience go dark with it, so nobody sits inside wrongly reporting sameness. Better to hand over that bill now than let it turn up later.

The sharp functionalist has a reply, and a good one: build the world in. Let the roles run long-arm, out to the red surface itself, as Gilbert Harman proposed when he put the long-arm/short-arm distinction into circulation in 1987.⁷ I accept the invitation, and it hands me the essay. I count a wide functionalism an ally: we agree on the view and divide over the label. But watch what the width costs. To make a role capture what experience presents, you must write the world-relations into it: the tracking, the coupling, the history. A program carries none of that. Its portability across worlds gave the charter its whole thrill. “The right program suffices” becomes “the right program, plus the right world, kept up the right way” — which amounts to no computationalism at all. My friend may keep the label. I ask only that the shipping be included in the price.

One escape remains, and I name it rather than hide it: deny the identity — keep content wide, but insist the felt character stays home, narrow, the same in vat and world. Phenomenal internalism: a live research program, held by careful people, and Chalmers’ own position.⁸ I do not refute it here; I insist only that it cannot borrow fading and dancing qualia for support, since those arguments never touched the world-varying case.

Now the objection worth real consideration. Ned Block has spent forty years building the counterexample nobody saw coming, and this one, from 1990, remains his best. Inverted Earth: a planet where every color runs to its opposite and the language runs with it, so the locals call their yellow sky “blue.” Slip you inverting lenses, fly you there asleep; lenses and world cancel, nothing looks wrong, and years pass while your states keep their old roles among new colors. Does the sky look any different than at home? Surely not, says Block — so felt character stayed put while content inverted, and my identity fails.⁹ But Block rests “still looks the same” on the internal role’s not changing, the very question at issue. When the tracked reflectance flips, what you experience flips with it, and so does the memory you would check it against. That step carries my weight, so: color memory stores no private sample held fixed for later comparison. It presents a worldly property, the same reflectance-type perception presents, and stays answerable to the world by the same traffic. Deny the re-anchoring and you must post an inner swatch, kept out of the world’s reach, for the comparison to consult: the very item transparency never turns up. Grant it and the comparison reads “same” either way. You cannot feel the switch, and not-feeling-it means only two things sliding together in register — introspection reports register and nothing past it. Claim just what this earns, then: my view goes unproven, and Inverted Earth stops working as a refutation that does not beg the question. And here, as promised, the wedge rule comes up empty: experience, memory, and judgment all present the world, so move the world and the three move together. Chalmers’ machinery hunts wedges; the world-directed mind never offers one. The real battle joins over the world, and fading never gets that far.

Stand back and the diagnosis names itself. Functionalism captures the causal machinery of mind with real success, then reaches for the feel of things and closes on a residue it cannot absorb.¹⁰ The dualist reads the residue as a ghost, an extra inner property the physical story missed. It reads the other way, and transparency supplies the bridge. Attend to your experience of the tomato and you find the tomato, and the way it presents itself — never a further inner item standing behind it. And transparency hides the world-relation as a relation: the red shows up on the skin of the tomato, never as something you stand in. So when a theory drops the relation, the loss cannot register as “it left out my traffic with the tomato”: that traffic never showed up as traffic. It registers as a loss with nowhere to go but inside. The residue marks the missing world, the lit scene the experience reached toward the whole time. Functionalism looks as though it lost something intrinsic. It lost something relational. And putting the world back makes the theory more physical, not less: surfaces, wavelengths, causal history, all just past the skin. The cure adds no second nature to consciousness; it redraws the mind’s edge, off the skin.

Keep two deflations apart, though. The missing world explains why functionalism in particular seems to leave a residue. The further question (why tracking this reflectance feels like this) faces every physical account alike, and our first-person concepts take the weight of it. A gap in our grip, not a crack in nature.

So my computationalist friend and I finally agree on what the arguments rule out: you cannot fade a mind by swapping its parts, or make it dance by throwing a switch. We split on why. He reads it: experience consists in organization, so build the organization and consciousness comes free. I read it the other way: experience reaches for the world, and it would not dance only because its author, the world, held still the whole time. Of course a variable that never moves looks like it does no work. So move it: send the twin abroad, build the system worldless from the start, and the experience the charter promised would sit tight begins to shift — or to lose any settled character at all. He had it right that the substrate does not matter, and right that the qualia do not dance. He had it wrong about why — and the width of the error is the width of the world he stood on and forgot to count.

-gts

This essay is part of Mind, Matter, and Meaning, an AI-assisted philosophy project by Gordon Swobe exploring consciousness, meaning, and artificial minds. Learn more about the project and read the book.

Notes

1. The absent- and inverted-qualia worries descend from Ned Block’s early pressure on functionalism (“Troubles with Functionalism,” 1978) and, for the inverted case, from Locke’s inverted spectrum and Sydney Shoemaker, “The Inverted Spectrum” (Journal of Philosophy 79, 1982). The two constructions that answer them are David Chalmers’, The Conscious Mind: In Search of a Fundamental Theory (Oxford University Press, 1996), ch. 7, “Absent Qualia, Fading Qualia, Dancing Qualia” — the “principle of organizational invariance.” The fine-grain clause is load-bearing: coarse input-output equivalence does not satisfy it, so Block’s conversational lookup-tree machine (“Blockhead,” from “Psychologism and Behaviorism,” Philosophical Review 90, 1981) falls outside the principle from the start. On the opening paragraph’s complaint: Chalmers argues the invariance principle in ch. 7 while defending naturalistic dualism in the same book, and the principle is framed as a constraint on the psychophysical connection rather than a reduction of one side to the other — fixing experience given organization without making experience consist in organization. A property dualist can therefore hold it, which is why it does not by itself hand the functionalist his conclusion. Nothing in this essay’s argument turns on that, since a construction’s force does not depend on its author’s metaphysics; the point is biographical, and it is why the constructions took me so long to take seriously. The “wedge rule” named in the main text is not Chalmers’ terminology but a gloss on the dialectical form of both constructions: each derives its absurdity from a dissociation between phenomenal character and the subject’s concurrent judgments about it, so each requires a manipulation under which such a dissociation could in principle obtain. ↩
2. The charter’s founding statement is Hilary Putnam’s, “The Nature of Mental States” (originally “Psychological Predicates,” 1967), in Mind, Language and Reality: Philosophical Papers vol. 2 (Cambridge University Press, 1975), ch. 21: being capable of feeling pain “is possessing an appropriate kind of Functional Organization,” spelled out as a Description of a Probabilistic Automaton — a machine table, with nothing said about what the organism stands in relation to. Putnam dismantled the view himself in Representation and Reality (MIT Press, 1988), using the externalism he had introduced in “The Meaning of ‘Meaning’” (note 4) — the argument this essay borrows. For the live form, Simon Goldstein and Cameron Domenico Kirk-Giannini, “A Case for AI Consciousness: Language Agents and Global Workspace Theory,” Journal of Consciousness Studies 33, nos. 7–8 (2026): 61–96, argue that if global workspace theory is the correct account of consciousness, conscious language agents are easy to produce and may already exist. Their argument is expressly conditional on that theory, and I do not saddle them with more than they claim; what matters here is the shape of the criterion, architectural from end to end — a verdict about inner life reached without a question asked about what, if anything, the system has ever stood in traffic with. ↩
3. The Conscious Mind, ch. 7 (p. 266), replying to Block’s Inverted Earth by name: on Inverted Earth “my internal functional organization will be just as it is when I see blue sky on earth, and my experience will be the same too”; at most, he allows, the case dissociates experience from environmental and “wide” functional properties — but the organization his principle concerns is internal. Compare “A Computational Foundation for the Study of Cognition” (drafted 1993; Journal of Cognitive Science 12, 2011: 323–357), which defends the thesis of computational sufficiency with the same explicit restriction — computation fixes the internal contribution to mental properties — and motivates the restriction on principled grounds, individuating inputs and outputs so the thesis says something determinate. This is the essay’s crux exhibit: the world-varying question was seen, scoped, and, on the wide case itself, decided without the chapter’s machinery. The independent narrow-content arguments the main text defers to are those of “The Representational Character of Experience” (2004), not the substitution arguments; on the separate question of envatted content, see note 6. ↩
4. Hilary Putnam, “The Meaning of ‘Meaning,’” in Mind, Language and Reality (Cambridge University Press, 1975), 227: “Cut the pie any way you like, ‘meanings’ just ain’t in the head!” Tyler Burge, “Individualism and the Mental” (Midwest Studies in Philosophy 4, 1979), extends the moral from meaning to the individuation of mental states generally. (The molecular-twin idealization waives the quibble that water-based creatures can have no strict duplicate on a waterless world.) ↩
5. The identity is Michael Tye’s and Fred Dretske’s — phenomenal character consists in representational content of a suitably poised, world-directed kind: Tye, Ten Problems of Consciousness (1995) and Consciousness, Color, and Content (2000); Dretske, Naturalizing the Mind (1995). On colors as surface reflectance-types, Byrne and Hilbert, “Color Realism and Color Science” (Behavioral and Brain Sciences 26, 2003). I write “consists in,” not “is identical to,” to keep the world in view and block the inner-object reading. Content here carries its mode of presentation with it: the claim is not that phenomenal character reduces to a bare set of tracked properties, but that it consists in the complete world-presenting intentional structure — content under a mode — which is why the Inverted Earth reply can let the mode shift with the world rather than treat it as a narrow residue. ↩
6. The history lever gets its own hard case: Donald Davidson’s Swampman (“Knowing One’s Own Mind,” Proceedings and Addresses of the APA 60, 1987), a freak molecular duplicate with no past. I follow Dretske’s etiological criterion, refined: ownership of its states arrives at once (they can go wrong for a self-maintaining system), while what they present waits on world-relations it has not yet stood in, and fills in fast among real tomatoes — the split verdict is my refinement, not Dretske’s formulation. Run that criterion backwards and it delivers the long-severed system of the main text. The claim entered there is deliberately conditional and rate-free: whatever an unrenewed history does to what a system’s states present, it does by the same stroke to the judgments that face the world through the same traffic, so the two cannot be prised apart at any point along the line — which is why the wedge rule finds nothing there, and why the just-severed case (address intact, misrepresentation live) yields the internalist nothing. No schedule of decay, and no sharp moment at which the address goes dead, is owed or asserted; the demand for one is the line-drawing demand that faces every naturalistic account of content alike, and it is no more answerable, and no more damaging, here than there. Tye notably demurs, granting Swampman contentful experience from arrival (Consciousness, Color, and Content). Nothing in fading or dancing qualia funds the serene “of course it sees”: Swampman moves the one variable those arguments never moved. The structured-stream objection answered in the main text is Chalmers’: “The Matrix as Metaphysics” (2005) and Reality+ (2022) argue from content externalism, not from narrow content, that envatted terms refer to bit-constituted virtual objects, the Recent/New Matrix asymmetry turning on causal-historical anchoring — this essay’s own machinery turned against its vat verdict. The concession in the text is therefore genuine and not tactical: where a stream anchors states causally, the twin verdict governs, and the null verdict is reserved for the ab-initio case in which no such anchoring ever obtained. The parallel debate over whether language models’ tokens reach the world through their training corpora runs on the same axis: Bender and Koller, “Climbing towards NLU” (ACL 2020), and Mandelkern and Linzen, “Do Language Models’ Words Refer?” (Computational Linguistics 50, 2024), who argue from causal-historical externalism that model words may refer — friendly to this essay’s currency (world-relations, not fluency), and pressing in the same direction as Chalmers, since they locate world-relations inside the training stream. ↩
7. Gilbert Harman coined the “long-arm”/“short-arm” vocabulary in “(Nonsolipsistic) Conceptual Role Semantics” (1987); his “The Intrinsic Quality of Experience” (Philosophical Perspectives 4, 1990) defends the wide view and is a locus classicus for the transparency of experience. ↩
8. Chalmers develops narrow (Fregean) phenomenal content in “The Representational Character of Experience” (2004) and defends contentful envatted and simulated experience in “The Matrix as Metaphysics” (2005) and Reality+ (2022) — the latter two on externalist rather than narrow grounds (note 6). The allied phenomenal-intentionality program grounds content in phenomenal character rather than the reverse: Horgan and Tienson (2002); Kriegel, ed., Phenomenal Intentionality (2013); Mendelovici, The Phenomenal Basis of Intentionality (2018); Adam Pautz, Perception (Routledge, 2021). The essay’s claim is not that no account of narrow character exists, but that the substitution arguments provide it none. ↩
9. Ned Block, “Inverted Earth” (Philosophical Perspectives 4, 1990), built precisely to split phenomenal character from representational content. The reply in the text follows the shape of Tye’s (in Consciousness, Color, and Content): the appeal to unchanged phenomenology across the years covertly assumes an internalist criterion of sameness, since memory is itself a world-representing state that shifts on the same schedule as perception. The positive argument given in the body — that denying the re-anchoring requires an introspectively unavailable inner sample for the comparison to consult — puts the transparency constraint to work against Block’s own appeal to introspection; it does not settle the exchange, and Block’s rejoinder (that phenomenal memory need not stay world-answerable in the required way) remains on the table. ↩
10. The “explanatory gap” is Joseph Levine’s (“Materialism and Qualia: The Explanatory Gap,” Pacific Philosophical Quarterly 64, 1983), who left its ontological status open; the “hard problem” is Chalmers’ (“Facing Up to the Problem of Consciousness,” Journal of Consciousness Studies 2, 1995). The two deflations distinguished in the text answer different explananda: the missing-world diagnosis is local to functionalism’s residue, while the residual conceptual gap is charged, for any physical account whatever, to the peculiarity of our first-person phenomenal concepts — a type-B physicalism in Chalmers’ own taxonomy (drawn in “Consciousness and Its Place in Nature,” 2002), on which the psychophysical identities are knowable only a posteriori. That strategy remains, as Block has pressed, hostage to whether those concepts can be explained without smuggling the target back in. ↩

Get new essays by email