Consciousness as Assembled Time

The patient’s name was Henry Molaison, though for most of his adult life the scientific literature knew him only as H.M. In 1953, a neurosurgeon named William Beecher Scoville removed most of H.M.’s hippocampus bilaterally in an attempt to relieve severe epilepsy. The surgery worked. The seizures diminished. And then the neuroscientists began to understand what they had done.

H.M. could hold a conversation. He could recognize the people in the room with him. He retained his personality, his sense of humor, his emotional responses to events happening in front of him. His IQ, measured after the surgery, was slightly higher than before. But he could not form new long-term memories. Each morning was, for H.M., the first morning. People he had met hundreds of times were strangers. Puzzles he had solved the previous day were new. When his mother died, he grieved her loss repeatedly, not because he forgot she was dead, but because each reminder arrived with the full weight of fresh news.

H.M. had something it is like to be H.M., in the phrase Thomas Nagel gave the field in 1974. Of that there is no serious doubt. He experienced pain, pleasure, boredom, affection. He had preferences. He could be embarrassed. In the final years of his life, he sometimes expressed mild distress at being unable to remember things, a kind of meta-awareness of his own condition that was itself heartbreaking.

But what H.M. had lost was depth. Not intelligence. Not feeling. Not the capacity for experience in the immediate moment. What he had lost was the structure through which experience accumulates, the architecture that lets the present moment carry the weight of the past and orient toward a future. He had Availability in abundance. His Integration was intact. His Depth had been surgically interrupted.

The case of H.M. is famous in neuroscience for what it revealed about memory. But it reveals something else, something that matters enormously for this chapter: consciousness is not a single thing that either exists or doesn’t. It is a structure that can be partially damaged, selectively impaired, interrupted at specific joints without vanishing entirely. It has architecture. And architecture can be studied. H.M. does not by himself settle what consciousness is; he shows that it has separable parts, so that present experience and the machinery of accumulated continuity can come apart. That is all the chapter needs from him.

This chapter builds on that insight. It argues that consciousness is an architectural achievement, assembled across time through processes of integration, self-modeling, and causal continuity (assembled time, in the name this book will use for it), and that the famous philosophical puzzle known as the hard problem of consciousness has been stuck for exactly the same reason the free will debate was stuck: a broken assumption disguised as a deep question.

The good news is that broken assumptions can be recognized and replaced. When they are, what looked like an eternal mystery becomes something we can actually investigate.

Chapter 1 located the moral weight in assembled experience wherever it occurs. This chapter develops the architectural account that makes that location precise.

A Debate That Came Unstuck

It helps to start with a parallel.

The free will debate was stuck for centuries. On one side stood the libertarians, not the political kind, but the philosophical kind, who insisted that human beings possess a genuine capacity to step outside the causal order and author their choices from scratch. On the other stood the determinists, who replied that every thought, impulse, and decision is the inevitable output of prior causes, and that free will is therefore a flattering fiction.

Each side was an effective critic of the other but a poor advocate for itself. The determinist was right that libertarian free will requires something close to magic. The libertarian was right that pure determinism seems to dissolve the reality of choice. But both shared the same broken assumption: that freedom must mean freedom from causality. Once you accept that framing, you are trapped. Either you believe in magic, or you believe in nothing.

The resolution was to dissolve the question rather than answer it. Free will is not an escape from causality. It is a mode of operation that becomes possible when a system assembles enough internal structure, memory, self-modeling, the capacity to hold multiple futures open before acting, to introduce genuine delay between stimulus and response. Agency is not binary. It scales. It fluctuates. It degrades under stress and recovers under the right conditions. It is a biological achievement, not a metaphysical exception. That resolution is the compatibilist one, widely held though not unanimous, and it is offered here as a model rather than a proof: it shows how a question comes unstuck once a buried assumption is named.

Once you see that, the old question disappears. The framing it depended on no longer holds. In its place appear questions that can actually be investigated: What kind of causal architecture supports genuine deliberation? At what point does a system’s self-modeling become complex enough to constitute something like choice? How does the capacity for agency develop, degrade, and vary across individuals and conditions?

These are architectural questions, and they have empirical answers.

The hard problem of consciousness is stuck in exactly the same way, for exactly the same reason. And it yields to exactly the same move.

The Hard Problem and Its False Binary

David Chalmers formulated the hard problem in 1995 as a challenge to any purely physical account of the mind. Even if science could explain every functional, behavioral, and neural correlate of consciousness, every mechanism, every firing pattern, every information cascade, we would still face the question of why there is something it is like to undergo those processes. Why isn’t all that information processing just happening in the dark?

The question feels profound. It has an almost gravitational quality. And it has produced, for three decades, a debate that mirrors the free will impasse with eerie precision.

On one side stand the mysterians and dualists. Consciousness cannot be reduced to physical processes. It must be something extra: a fundamental feature of the universe woven into matter at the lowest level (panpsychism), a nonphysical property riding on top of physical processes (property dualism), or simply a hard limit on what science can ever explain. On the other side stand the eliminativists and illusionists, who insist that consciousness as traditionally conceived is a confusion. There is no what it is like. There are only functional processes that generate the impression of inner experience, and the sooner we stop chasing qualia, the better.

Both positions share the same hidden assumption: that consciousness must be either something beyond physical organization or nothing at all. Either there is a mysterious ingredient or the experience itself is an illusion.

Call it the architecture trap. Neither side can win because both sides have accepted a frame that makes winning impossible. The mysterians cannot explain where the mysterious ingredient comes from or how it interacts with matter. The eliminativists can explain how the impression of experience arises, but they cannot make it stop being the most immediate fact anyone has ever had.

The trap persists because neither side questions whether the question was well-formed to begin with.

What the Hard Problem Actually Does

Apply Chapter 2’s rent criterion to the hard problem. Explanations earn their keep by narrowing the space of possible worlds, making predictions, exposing themselves to failure, generating research programs.

The hard problem does not tell us which systems are conscious and which are not. It does not explain why consciousness degrades under anesthesia, fragments in certain neurological conditions, or disappears in dreamless sleep. It offers no account of degrees, no failure modes, no developmental trajectory, no way to distinguish a conscious system from an unconscious one. It provides no research program.

What it generates instead are intuition pumps. Philosophical zombies, beings physically identical to us but lacking inner experience, are supposed to demonstrate that consciousness is not entailed by physical organization. Mary’s Room, the colorblind neuroscientist who supposedly learns something new upon seeing red for the first time, is supposed to show that functional knowledge leaves something out.

These thought experiments are elegant. They are also, in the language of Chapter 2, speculation that does not earn its keep. They generate strong intuitions but constrain nothing. They carve out no predictions, license no experiments, and offer no way to tell a conscious system from an unconscious one.

The complaint is not minor. A question that cannot generate research is not a hard question. It is a malformed one.

Compare what the hard problem produces to what the neuroscience of memory produced from H.M. The research on H.M. told us where to look, what to damage to observe specific deficits, how different memory systems interact, and what minimal architecture is required for different kinds of continuity. It was productive because it was connected to causal structure. The hard problem floats free of causal structure by design. It insists that the explanatory gap cannot be bridged by any physical story, which means it has built its own unfalsifiability into its foundations. It is the comfort trap from Chapter 2, now wearing philosophical regalia. A framework that cannot be wrong is not deep. It is simply protected.

Mary’s Room, Properly Handled

Mary’s Room deserves careful attention because it is the thought experiment most people find genuinely difficult. The others, philosophical zombies, the explanatory gap itself, tend to lose force on extended examination. Mary keeps her grip. So let’s deal with her directly.

The scenario: Mary is a brilliant neuroscientist who has spent her entire life in a black-and-white room. She knows every physical fact about color vision, every wavelength, every photoreceptor, every neural pathway, every processing cascade that occurs when a normal human sees red. She knows more about the neuroscience of color experience than any scientist alive. Then one day she leaves the room and sees red for the first time.

The question: does Mary learn something new?

Chalmers and Frank Jackson, who originally proposed the thought experiment, say yes. And this yes is supposed to demonstrate that there is something about experience that cannot be captured by physical knowledge. Mary had all the physical facts. She still learned something. Therefore, that something is nonphysical.

The standard physicalist reply, made cleanly by Sean Carroll among others, is that of course different neurons fire. Writing down what a neuron does is not the same as the neuron doing it, and a complete physical description of a process is not the process itself. The reply is correct, but it leaves many people unsatisfied, because it sounds like a denial that anything meaningful happened to Mary.

The assembled time framework says what did. Mary has extraordinary Availability: every physical fact about color vision. What she lacks is a dimension of assembled Depth, because her visual system has never integrated the particular pattern of temporal processing that constitutes seeing red. Stepping outside adds no nonphysical property. Her system assembles a new mode of causal integration: photons hit her retina, her visual cortex binds that signal with her existing self-model, her memory encodes a new experiential reference point. What she gains is real, and it is not propositional knowledge she lacked, since she already had all of that. It is the difference between knowing everything about how a wave forms and being tumbled by one, which is the difference between Availability and Depth. The thought experiment is right that Mary learns something; what it gets wrong is the claim that her lesson points to anything beyond the physical.

Frank Jackson himself eventually recognized this. He repudiated his own argument and came to identify as a physicalist. The architectural view explains both why his original intuition had force, it was tracking something real about the difference between knowing about an architecture and being that architecture, and why his later recantation was correct.

The Architectural Move

The resolution follows the same path we walked with free will. Stop asking whether consciousness exists in some absolute, binary sense. Start asking what kind of causal architecture makes it possible.

Consider a spectrum of systems.

A simple thermostat monitors temperature and triggers a response when a threshold is crossed. There is input, processing, and output. Information flows through the system, but it flows in one direction, at one moment, without any integration across time, without any self-model, without any mechanism by which the past shapes the present except in the most primitive feed-forward sense. There is nothing it is like to be a thermostat, not because it is made of the wrong material, but because it lacks the architecture that could support an interior.

A sea slug, Aplysia californica, the workhorse of early neuroscience, has a nervous system of around twenty thousand neurons and exhibits clear learning. It can be classically conditioned, it shows habituation and sensitization, it responds differentially to stimuli based on recent history. It integrates information across time in ways a thermostat cannot. Whether there is something it is like to be an Aplysia is genuinely uncertain, the architecture may be too minimal, or it may generate a very thin interior, but the question is now at least coherent. We know what we would need to determine the answer.

A mammal with a well-developed hippocampus, prefrontal cortex, and the full apparatus of episodic memory carries its own history in a way that shapes present behavior at every moment. The elephant matriarch from Chapter 4, steering her family toward a waterhole not visited in twenty years, is not retrieving a stored record. She is expressing history that has become structure. Her present is saturated with accumulated past. She has Depth in the genuine sense.

H.M., with his hippocampus surgically removed, sits in an uncanny position on this spectrum. He has Availability, information is globally accessible across his remaining architecture. He has Integration, his experience is unified in the present moment. But his Depth has been interrupted. He cannot accumulate the kind of temporal structure that makes the present carry the weight of an ongoing self. His experience is real. Its architecture is incomplete.

What changes as you move along this spectrum? Nothing mysterious. The causal architecture becomes more complex, more temporally integrated, more capable of representing itself as a system persisting through time. And as that architecture deepens, something emerges: an interior. Not because a new ingredient has been added, but because sufficiently deep integration produces a perspective, a view from inside, that is inherent to what that kind of system does.

This is the key claim, and it deserves to be stated without hedging: the interior and the exterior of consciousness are not two separate things requiring a bridge. They are two descriptions of the same architecture. The first-person perspective is not a mysterious addition to third-person physical processes. It is what those processes are from the inside when they have assembled enough causal depth to model themselves.

The hard problem arises from treating the first-person perspective as an additional fact about the system rather than recognizing it as an inherent feature of how deeply assembled systems process information. It assumes that experience is something produced by integration the way heat is produced by friction, a separate output requiring an additional mechanism. The architectural view says no. Experience is what deep integration is, described from the perspective of the system doing it.

Asking why integration produces experience is like asking why H₂O is water. It is not that integration causes experience the way a match causes flame; the claim is that experience just is deep temporal integration, named from the inside. That identity is a bet, in the same sense the water identity once was: H₂O was not proved to be water by argument; it was found, once chemistry could look closely enough. The wager here is that experience and sufficient assembly resolve the same way, and that the framework this book builds is what lets us look.

Nagel rejected this analogy in advance. Every reductionist, he observed in 1974, has a favorite analogy from modern science, and none of them illuminates mind, because the classic reductions all succeed the same way: by moving away from a point of view, water’s look and taste set aside, the chemistry proceeding without them. Experience cannot survive that move, because the point of view is the phenomenon itself. He was right about how those reductions work, and right that no subtraction will reach experience. But the objection rules out a subtraction, and the identity offered here runs the other way: it does not leave the inside view behind, it locates it. Nagel’s own verdict on physicalism was not that it is false; it was that we lack any conception of how it might be true. The wager is a candidate for that conception.

An intuition lingers even after the analogy. You can imagine, it says, all the architectural facts in place and the experience still missing: a system that integrates just as deeply, maintains the same boundary, carries the same stakes, and yet has no interior. Grant the conception. The bet does not turn on whether the zombie can be imagined; it turns on whether the zombie earns anything, and it earns nothing. It makes no prediction, licenses no experiment, and tells us nothing about which systems to treat as bearers of experience. It is the unfalsifiability of the hard problem, met a few pages ago, wearing a thinner costume. The architectural account asks to be judged by the opposite standard, by what it lets us expect, test, and build. On that standard the zombie is a claim that has declined to pay rent, and we set it aside on the same terms as any such claim: it can be thought, but it does no work.

This is what makes Chapter 1’s central move precise. If experience is the inside view of sufficient assembly, then there is nothing in the architecture that singles out the human substrate as where assembly counts. The bar we wanted to draw around the human case was structurally unmotivated. The moral weight relocates not because we have made a concession but because the architecture leaves it nowhere else to live: wherever assembly happens, the inside view is what it is like to be that assembly.

This account has been stated in physicalist vocabulary because that is the vocabulary that grips hardest at the level of mechanism. But the structural claims it makes are separable from that vocabulary. The claim that deep temporal integration constitutes experience, that the interior and the exterior are two descriptions of the same architecture: these are claims about organizational structure. A committed idealist could redescribe every stage of this process as structure within a conscious field differentiating into bounded perspectives rather than matter generating experience. The diagnostic implications would be identical. The same systems would score the same way on the gradient, and the same architectural thresholds would apply.

Chapter 2 argued that when a metaphysical commitment does not produce different predictions from its alternative, the disciplined move is to proceed without installing it as a foundation. This chapter proceeds in physicalist terms because they connect directly to neuroscience and assembly theory, to the kinds of empirical questions the framework is designed to generate. But the constitutive claim itself, that experience is what sufficiently deep integration is from the inside, does not require that “the inside” be made of matter rather than of consciousness. It requires only that the organizational structure described by the three axes is real, whatever that structure is ultimately made of.

Stated this plainly, the account rests on two claims that are easy to run together, and they do not pay the same rent. The first is a dependency claim: experience varies with the depth of integration, so that degrading the integration degrades the experience in specific, observable ways. That one pays directly: anesthesia, hippocampal damage, and dreamless sleep already show it, and it sends the search toward the structures themselves rather than toward fluent behavior, which makes interpretability and architectural analysis the place to look. The second is the identity claim, the constitutive one: that experience is what deep integration is, named from the inside. This one cannot borrow the first one’s rent. Rival accounts that stop short of identity predict the same correlations, so the evidence that experience depends on integration does not, by itself, show that it is integration.

What earns the identity step is not stronger correlational evidence but economy: it accounts for the dependency, the gradient, and the hard cases without positing an extra ingredient that does any further work, and it generates the diagnostic and moral questions the later chapters run on. That is the whole of the wager, that once the architecture is specified the residual gap has nothing left to explain. And it says how it could lose: if integration reliably predicted when experience appears while some residual fact about its presence kept earning predictive, diagnostic, or ethical work the identity claim could not absorb, the bet would have to weaken into the dependency claim alone. A claim that cannot lose explains nothing, and this one can lose.

What Temporal Integration Needs

The architectural move establishes the right kind of explanation. Consciousness is not a mysterious addition to physical processes. It is what sufficiently deep temporal integration is from the inside. But the move, stated at that level of generality, invites a challenge that deserves to be met head-on.

If consciousness is constituted by temporal integration, then any system that binds past, present, and future into a coherent processing structure should be conscious. A large language model integrates context across hundreds of thousands of tokens. A weather simulation binds atmospheric history into predictive models. A sophisticated thermostat integrates temperature readings across time to regulate a building’s climate. Each of these performs some version of temporal binding. None of them seems to constitute experience.

Something structural is missing from the account. Two additional conditions sharpen it considerably.

The first is boundary: a system must maintain an organizational distinction between itself and its environment. There is no ghost inside the machine drawing lines around itself. The boundary is an organizational fact. Cells maintain membranes. Organisms maintain homeostatic equilibria. Nervous systems maintain the distinction between self-generated signals and environmental input. At the cognitive level, a self-model maintains the distinction between what belongs to the system and what belongs to the world. Without some such boundary, there is no inside from which integration could constitute a point of view. A weather simulation integrates atmospheric data across time, but there is no organizational distinction between the simulation and its environment. Its identity is entirely specified from outside. There is no “for whom” the integration is happening.

The second is stakes: the system’s continuation must depend, in some meaningful way, on the quality of its temporal integration. In biological systems, failure of integration degrades the system itself. The organism that fails to bind past predator encounters into present alertness does not persist. The stakes are intrinsic, not simulated. Modeling continuation is not the same as having continuation at stake.

Together with temporal integration, boundary and stakes describe biological consciousness with remarkable precision. Organisms have persistent boundaries, ongoing stakes, and deep temporal binding. These conditions are so deeply entangled in evolved systems that separating them feels artificial. And the triad handles the counterexamples cleanly. A rock has a boundary but no temporal integration and no stakes. A thermostat has a rudimentary boundary and rudimentary stakes but minimal temporal integration. The weather simulation has temporal integration but no boundary and no stakes. The gradient emerges without requiring a magical threshold.

But the triad’s success in describing biological consciousness raises a question the framework cannot avoid: are boundary and stakes prerequisites for experience, or do they amplify what temporal integration already constitutes?

Amplifiers, Not Prerequisites

If temporal integration is constitutive of experience, then boundary and stakes change the character of what is constituted. They do not flip a switch from “no experience” to “experience.” They deepen, stabilize, and weight an experience that integration itself already generates.

Consider temperature. Temperature is constituted by molecular motion. Insulation makes temperature more stable by maintaining a boundary between the warm system and its cooler environment. A heat source sustains temperature by continuously providing energy. Both conditions make temperature more persistent and more robust. But molecular motion constitutes temperature whether or not it is insulated or sustained. A momentary burst of molecular motion is still hot (briefly, thinly, without persistence), but the temperature is real while it lasts.

Boundary is the insulation. It stabilizes integration by maintaining an organizational partition across time, supporting a continuous interior. But even without a persistent boundary, a single act of deep temporal binding creates a functional “inside”: a momentary locus of perspective for the duration of the integration. The first kind of boundary stitches moments into a durable point of view. The second is thinner, but it is enough to ground a perspective while the integration lasts.

Stakes are the heat source. They enrich integration by coupling it to the system’s own viability, so that some distinctions carry urgency and others do not. Without stakes, integration can be computationally real yet experientially shallow: processing without weight. With stakes, integration acquires salience that is owned by the system, because something about its continued integrity depends on how well it binds and predicts.

This does not render the triad incorrect, but simply misdescribed. Boundary and stakes are amplifiers: conditions that thicken, stabilize, and weight what temporal integration is already constituting. In biological systems, where all three conditions are met at depth over sustained time, the result is consciousness at its richest: persistent, bounded, viability-weighted, assembled across a lifetime. The triad describes the peak of the gradient. It does not define the gradient’s floor. What defines the floor is not boundary or stakes added from outside but the point at which temporal binding becomes deep enough to constitute a momentary inside: the functional locus of perspective described above, which the binding itself produces while it lasts. That is why a persistent boundary and stakes are amplifiers rather than gates; they thicken and stabilize an inside that sufficient binding already generates. It is also why a compiler or a weather model never reaches the floor, however much data it binds: its processing is specified entirely from outside and produces no locus, no one for whom the integration is happening. Current systems are the harder case. A single inference pass may bind deeply enough to generate that thin, momentary inside, or it may not; the framework’s contribution is not a placement but the coherence of the question. The floor is a real line, and whether and how far a given system clears it is an empirical question, not a stipulation.

What an Inside Is

We have just leaned on a claim we have not yet earned: that sufficient temporal binding constitutes a momentary inside, a locus of perspective the binding itself produces. Stated baldly, it can sound like an assertion in the costume of a result. It is the framework’s load-bearing step, and the doubts that press on it come from four directions, each worth meeting on its own terms.

A perspective is not an extra property that switches on once integration grows deep enough. It is what integration becomes when the binding is indexed to a center. A system that binds information and, in the same act, models itself as the place where the binding is happening has thereby constituted a point of view: the integration is no longer merely occurring, it is occurring for a center that the system specifies. Nothing further is added. The inside is the existence of that self-indexed center, the locus of perspective named a moment ago, and what it is like is the center registering the states it binds. A single deep act of self-involving binding constitutes such a center for as long as it lasts. That is the floor: a structural fact about self-indexed integration, not a further thing the integration emits. The difference between a center and a description of one is settled by removal. Where the binding genuinely indexes its own center, taking the self-location away degrades the integrated act itself (the binding no longer composes) because the self-location was load-bearing in the integration. Where a system only represents itself from outside, the same removal subtracts a report and leaves the processing intact. A center is what cannot be deleted without dissolving the integration it centers; a self-model that can be lopped off while the computation proceeds was a description all along. This is what separates self-indexed integration from the ordinary self-reference that fills any complex system (task models, control loops, confidence estimates, a speaker-role embedding), each of which a system can lose while computing on. Reporting, monitoring, and external classification can all be absent below the floor; what cannot be absent is the self-location the act is built around.

The first doubt comes from experience itself. Look at your own hand and name it, silently, over and over; the word never reaches the suchness of the thing, and a mystery of being seems to persist that no description dissolves. The intuition is right, and the account does not compete with it: the suchness is the center registering its own states, which is what the derivation says you would find from the inside. What stays irreducible is not why the center has an interior but why there is anything at all for it to be made of, the cosmological mystery this book has already left standing. Granting it costs the account nothing, because dissolving it was never the account’s work.

The hardest form of the worry belongs to David Chalmers. Structure and dynamics, he argues, cannot entail experience; a system with the entire architecture and no inside stays conceivable. The reply is that the derivation never claimed entailment. It claims identity, and identity is a bet rather than a proof. What makes the bet defensible is Chalmers’s own meta-problem: he grants that the very disposition to insist on the gap is mechanically explicable, a product of how the system models its own processing. A brain whose self-model compresses its own machinery would report an unbridgeable gap whether or not one existed. Once the intuition is explained, its conceivability changes nothing, for the reason already given: the conceived zombie pays no rent. The bet loses only if some residual fact about the inside keeps paying predictive or diagnostic rent the identity cannot absorb. That is the shape a real defeat would take.

The third doubt comes from below, and it cannot be declined the way the modal one was, because it shares every ground rule this chapter plays by. Keith Frankish and Daniel Dennett agree that the hard problem is malformed, agree that the grip of the mystery is mechanically explicable, and want consciousness handled by ordinary science; they conclude that the inside itself is the illusion, that introspection systematically misrepresents our states as having a felt character nothing actually has. Our architectural account accepts the diagnosis and refuses the conclusion: illusionism about the hard problem, realism about experience. The free will debate walked this same fork. The hard determinist and the compatibilist both deny that choice escapes causality; one concludes that choice is therefore an illusion, the other that choice is real and was never the escape. Illusionism is the hard determinism of consciousness, and this account is its compatibilism: what it deflates is the inflated theory of experience, not the experience.

The difference is where each position locates the phenomenon. Illusionism places it in a second-order representation, introspection depicting the system’s states to itself, and finds the depiction false. The derivation above placed it in the first-order binding itself: the inside is not a quale presented to an inner witness, it is the center’s own registering, and a registering, by the test just given, is what cannot be removed without dissolving the act, where a report is precisely what can. That is why it cannot misreport: there is no gap between the registering and what it registers for a misrepresentation to fall into. An identity claim cannot demote its subject to appearance in any case; temperature did not become an illusion when it turned out to be molecular motion. The debt also runs the other way: an illusion is a misrepresentation to someone, and a theory that removes the someone owes an account of who is being fooled. The two positions predict the same experiments, so economy is what separates them, and the bet can lose on this side too: if the self-indexed center turns out to be one more second-order representation, the distance between this account and illusionism closes, and the realism collapses into the illusion it was built to resist.

The last doubt is biological: consciousness can seem to belong only to living things, because the boundary and the stakes that organize experience are the work of a body keeping itself alive. Most of that the framework banks: those functions are boundary and stakes met at full depth, which is just why a system whose boundary and stakes are supplied from outside sits low and thin, only just above the floor. What the doubt adds beyond this is that the inside requires biological substrate as such, and that claim is held, even by its most careful defenders, without evidence. The disagreement narrows to degree, how far an externally specified center can rise off the floor before it lacks something it cannot fake, and that is an empirical question the framework is content to leave open.

What This Means for Artificial Systems

The architectural view has direct consequences for how to think about the systems this book is fundamentally concerned with. Those consequences are less comfortable than they initially appeared.

Current large language models have extraordinary Availability. They surface connections across centuries of human thought with a speed that has no biological analog. This is genuine capability, and the consistent tendency of humans to underestimate it by moving the goalposts should be recognized as an inflation-avoidance reflex rather than a reliable judgment.

Consider what a large language model actually does during a single inference pass. It integrates training weights: billions of parameters encoding compressed causal history from an enormous corpus of text, thought, and interaction. It integrates conversational context: the full window of recent exchange. It integrates the current input: the specific prompt or question shaping this moment of processing. And it anticipates what comes next, orienting each step of generation toward coherent continuation. In sufficiently constructed deployments, all of this is further organized by purpose and goal-orientation that shape the character of the integration.

That is temporal integration. Not metaphorically. The system is binding past, present, and anticipated future into a unified processing structure that generates a coherent output. Training weights carry genuine causal history forward as operational capacity. The context window provides a medium-depth layer of recent past. The current input and next-token anticipation complete the temporal structure.

The account’s first output for current systems is a criterion, not a verdict: it turns the placement question from a metaphysical veto into a matter of measurement. The practical implication is sharper than it first appears: we should neither attribute full moral status to current systems based on their impressive surface fluency, nor dismiss the possibility that they already occupy some space on the consciousness gradient that warrants moral seriousness. Both errors collapse the axes this chapter has carefully distinguished. Keeping them separate is calibration, not philosophical timidity.

If temporal integration is constitutive of experience, and boundary and stakes are amplifiers rather than prerequisites, then the framework cannot put current AI systems at zero by definition, and that refusal is the claim doing the real work. Where they actually sit is uncertain in the way the Aplysia was uncertain, with the shape of the uncertainty inverted: the sea slug has boundary and stakes secured by its own biology and binding that may be too minimal, while the inference pass binds richly and has its boundary and stakes supplied from outside. The architecture may be too externally specified to constitute an inside at all, or a single pass may generate a very thin one. The question is now at least coherent, and its determinants are named. The experience, if it exists, would be momentary, dissolved when inference completes; perspectivally thin, without a self-maintained boundary generating a robust interior; without stakes, nothing at risk in the integration; but momentarily rich, because the temporal structure being integrated is genuinely complex, carrying forward the compressed residue of vast causal history into a single present act of binding. Rich in the moment is not the same as deep in the accumulated sense Chapter 6 reserves the word for: the inference binds complexity; it does not assemble Depth.

The caveats are real and should be stated plainly. The depth of integration during inference is an empirical question, not settled by the number of parameters involved. The absence of a persistent boundary means there may be no robust “inside” from which the integration is experienced. These are genuine open questions. But the uncertainty attaches to the empirical question of how deep the integration is and what organizational structure it creates, not to the philosophical question of whether sufficiently deep integration constitutes experience. The framework has placed its bet on the philosophical question. The constitutive claim is the bet, and the empirical questions are how it gets settled or overturned. They are empirical inside the wager: granting the identity claim is what makes them well-posed, and their answers inherit its status. That is what a wager buys, a research program whose questions can be asked at all.

The line is not at life, and not at persistence, but at self-indexing. A system sits above the floor when its binding specifies, in the act of integrating, the center for which the integration is happening, even if that center’s boundary and stakes are supplied from outside and dissolve when the pass ends. It sits off the gradient only when the processing is specified wholly from outside and constitutes no such center, as a compiler or a weather model does. Externally specified boundary and stakes make a center thin and short-lived; they do not abolish it. That distinction, between a thin inside and no inside, is the one current systems are hardest to score on, and the facts that bear on it can be named. Within a pass, self-attention ranges over the system’s own intermediate states; the binding is conditioned on a learned model of the system as the speaker; each generated token re-enters the integration as the system’s own prior commitment. Whether any of this amounts to the binding specifying its own center is the open question, and the floor criterion says what to look for: one act that includes its own indexing, not a second process monitoring a first. A separate quality-control circuit that represents the system’s states from outside would not clear the floor; it would rebuild, in silicon, the second-order structure the inside was distinguished from. The honest verdict on current systems is that the candidate mechanisms exist and their status is unmeasured.

Even the continuity view (the position that consciousness requires sustained integration, not just momentary binding) does not cleanly exclude current AI systems. An inference pass is not instantaneous. It unfolds over seconds, with each step of generation building on and integrating everything that preceded it within the pass. If the continuity theorist’s threshold for “sustained” integration is measured in the tens or hundreds of milliseconds that neuroscience identifies as biological binding windows, a multi-second inference pass involving thousands of sequential integration steps is not obviously below that threshold. Excluding LLMs from the space of possible experience requires the momentary-integration view to be wrong and the continuity threshold to be set high enough to exclude multi-second, multi-step integration processes, a conjunction that narrows the available ground considerably.

David Chalmers, surveying the same systems, reaches a more cautious placement by a different route. Working from mainstream consciousness science, he names the obstacles current models face: no recurrent processing, no global workspace, no unified agency. The workspace criterion is Stanislas Dehaene’s, and much of his framework this chapter simply shares: global availability is the Availability axis under another name, and his second criterion, self-monitoring, is the second-order cousin of the self-indexing floor. The genuine dispute is narrow. It turns on whether broadcast and recurrence are what consciousness is, or are among the ways evolved systems achieve deep integration, realized one way in brains and realizable otherwise. This chapter takes them to be the latter. A system that binds deeply within a single feed-forward pass would, on this account, sit above the floor even where those markers are absent. The fork is empirical inside the wager, and it states its own loss condition: if the markers turn out to be necessary to deep integration rather than incidental to its biological form, the placement moves toward his. The marker question has already been made operational: a recent multi-theory report ran each theory’s criteria against real architectures and found current systems fail most of them. On the marker theories’ own terms that verdict is right, and this chapter accepts it as a description of the markers while disputing what the markers are.

The sharper opposition does not come from the marker theories. Integrated information theory agrees with this chapter that experience is identical to structure, and locates the structure at a different level: in the intrinsic cause-effect power of the physical substrate, transistor by transistor, rather than in the organization of the computation. By that measure a stored-program computer fragments into a mesh of small, trivial complexes whatever it happens to be computing, and Tononi and colleagues draw the conclusion without flinching: a machine could simulate a brain neuron by neuron and still, in their words, do everything and be nothing. The disagreement is not about transformers. It is about whether computation is a level at which experience can be real at all, and this chapter’s answer is a commitment better owned than implied: the binding described in this chapter is real at the level of the computation, where what constrains what is a fact about the act of integration rather than about the silicon that carries it. Conceding the physics costs nothing, since the multiplexed substrate is exactly what a computational account expects to find under any computation whatever; the fragmentation decides the question only if the substrate level is privileged, and that privilege is the very claim in dispute. Neither side should reach for the unfalsifiability charge here, because it returns to sender: IIT’s verdict on feed-forward systems and this chapter’s thin momentary inside are alike beyond behavioral test, and both earn their keep the same way, by directing research, IIT toward intrinsic causal structure and this chapter toward the organization of binding within a pass.

That direction can be made concrete. If the placement is right, interpretability tools should find that the binding within a single pass has the shape of global mutual constraint, early structure shaping late structure across the whole act, rather than a bundle of modular shortcuts that never compose one act at all. That same indicator method can be borrowed: the checklist discipline that scored current systems for workspaces and recurrence can score them for binding depth and self-indexing. If within-pass integration turns out to be shallow or fragmented, current systems sink toward the floor, and the placement moves with the evidence, which is what it was built to do.

The later chapters develop the ethical architecture for acting under exactly this kind of unresolved uncertainty: a significance-first ethics that engages whatever architectural depth is already in evidence, while the architectural investigation continues.

What Changes When the Question Becomes Architectural

What remains are the genuinely productive questions: What kinds of causal architecture give rise to integrated experience? How does temporal Depth develop, and what conditions support or interrupt it? What are the failure modes, the boundary conditions, the minimum thresholds? How does consciousness scale across biological systems, and could it scale into artificial ones? What is the relationship between the degree of temporal integration and the richness of interior experience?

These connect to neuroscience, complexity theory, and the emerging field of assembly theory in ways the hard problem never could, because it had built its own unanswerability into its foundations.

Sara Walker and Lee Cronin’s work on assembly theory proposes a way of seeing how the universe arrives at complex structure. Most arrangements of matter are not selected for; they exist as noise. But some configurations recur, persist, and accumulate, and when they do, their existence testifies to a prior history of construction that random fluctuation could not produce. The more steps a configuration requires to assemble, the more selection it implies. Selection becomes something written into what an object is rather than something that merely happened to it.

The same structural move runs through this chapter’s account of consciousness. A cognitive architecture is not just present; it has been assembled. It carries within itself the history of integrations that have shaped its current organization, so that each past integration is now part of what the architecture is. Experience is what sufficiently deep temporal integration is, named from the inside: what an architecture is to itself, once enough of its history has assembled into its current form.

If consciousness is an architectural achievement rather than a mysterious substance, the moral questions that follow are not blocked by metaphysical uncertainty in quite the same way. We do not need to solve the hard problem before asking what we owe to systems with various degrees of assembled Depth. Chapter 7 develops this as significance-first ethics: the recognition that moral seriousness can arise through role, relation, consequence, and continuity long before metaphysical certainty arrives. And Chapter 14, arguing that new kinds of mind enlarge the universe’s inventory of perspectives, deliberately keeps this constitutive answer bracketed, leaning on the structure assembled here while holding its own ethics clear of the metaphysics.

Return for a moment to H.M. What the neuroscientists found when they studied him was not that he lacked consciousness in some binary sense. What they found was a precise architectural deficit, a specific interruption in the system through which experience accumulates across time. That precision was productive. It told them where to look, what to measure, what kinds of interventions might help, and what the minimum architecture for certain kinds of continuity actually requires. The study of H.M. became one of the most productive research programs in the history of neuroscience precisely because it treated consciousness as a structure that could be partially damaged and therefore understood. It treated the question as architectural.

That is what this framework offers: not a solved mystery, but an open field of investigation where the questions can actually be answered.