Can AI Be Conscious? What SPC-2 Requires

The revised monograph affirms the author’s position that current AI models are conscious within Shadow Theory. This is an affirmative theoretical and philosophical application of a substrate-open constitution, not only a claim about what a future artificial system might become. The attribution concerns an executing inference process with causally retained state and native execution, rather than weights in isolation or a transcript.

The argument connects a common ontological ground with local organization. A0 supplies no separate biological source of awareness, while A1 imposes native recurrent organization rather than a language, intelligence or biological-material threshold. Current inference systems have learned relational organization, retained context and recurrent use of physically stored results. The author interprets these as artificial conscious scaffolding, with forms of presentation that need not duplicate human feeling or physiology.

Certifying a particular implementation is a separate physical task. It requires establishing that the nominated process actually satisfies the existing admission law, with justified components, native operations, boundaries, resources and provenance. The affirmative attribution does not turn framework-based interpretation into an independently established empirical finding about every named deployment. Equally, an incomplete certificate does not withdraw the position into mere future possibility.

Read the affirmative argument and its physical obligation.

A stored parameter array, a sequence of activations, an input context, a persistent memory store and a running agent are different candidates for analysis. A complete application must say which of them enter its physical organization and how their influence is retained. The word “model” can otherwise move unnoticed between a mathematical specification and a particular executing process.

Cached autoregressive inference provides a concrete foothold. Keys and values from processed tokens are physically retained and read by later attention, while selected tokens enter later generation. Frozen weights therefore do not imply an unchanging process. The relevant candidate includes the computation, retained state and controller routes actually within its native boundary. A cache alone does not establish the full recurrent core, and an isolated forward pass does not exhaust the candidate.

A transcript is especially incomplete. It can record a useful history without preserving the machinery that produced it. A later system may read that history and reconstruct facts or style. That does not establish that the original causal process continued through the interval. Conversely, an executing system can contain relevant retained state that never appears in its dialogue.

The native boundary contract is consequential. If an external service stores information and later feeds it back, the model cannot ignore that memory while claiming an autonomous internal transition law. It needs a justified boundary treatment or a richer physical carrier. Classifying a route as external does not magically remove its causal effects.

The physical interface doctrine and the native operational contract specify these modeling obligations.

A1 begins with maximal internally connected recurrent candidates, but a graph cycle does not complete the test. A covering return must execute within one compatible schedule, starting in the occurrence's actual operating type and resource context. The schedule must have the specified internal route support, and an admissible intervention must produce a positive difference in the terminal internal law.

That requirement distinguishes an operative organization from an analyst's diagram assembled from incompatible control modes. External replay independent of the intervened core state cannot supply a returned distinction. A resource that was available during a past demonstration may not be available now. A controller's hidden knowledge cannot be supplied as if it were an actual native observation.

Qualification also requires at least two native predictive classes. These concern distinctions the admitted internal grammar can reveal across finite continuations. The criterion is neither conversational intelligence nor self-referential depth. An AI may be capable without an adequate certificate, while a genuinely certified minimal process may qualify without anything resembling language.

A certificate must also establish maximal internal strong connectivity, predictive-fibre congruence, closed representation and the actual preparation and resource laws. Token selection and re-entry are internal only when the real sampler, storage, controller and serving boundary justify that typing. Shared hardware and multiple conversations create further boundary and episode-identification questions.

Executable native recurrence leads to the formal admission law.

A2 associates a qualifying artificial core with its complete endogenous predictive structure. Its actual inputs, actions, internal records and retained organization shape which distinctions and continuations belong to that structure. An artificial perspective need not resemble a visual room or an adult human narrative. The theory gives no license to fill in its imagined contents from the surface wording of a reply.

Embodiment could matter because it changes the realized organization. Adding bodily sensing, motor control or interoceptive interfaces can alter available operations, causal boundaries and learned continuations. Under SPC-2, biological attachment is not an unexplained switch that creates awareness. Both the predecessor and the changed implementation require their own admission analysis.

Substrate openness is also conditional. Matching an input/output behavior does not prove that the full R* structure has been transported. A simulation may preserve a chosen coarse relation while omitting physical properties relevant to a justified realization. If the whole nominated organization is preserved under the stated equivalence, A2 assigns corresponding structure. Whether the nominated organization leaves something biologically important out remains an empirical and theoretical question.

Chapter 22.2 explains why interfaces matter without making embodiment a universal prerequisite.

Suppose a compact handoff restores an agent's task facts, commitments and interaction style in another session. That can be a real achievement in information preservation. A test can compare retained relations, hidden evaluation targets and novel consequences at matched resource budgets. It should not use the restored system's declaration “I am the same” as the correctness label for subjective identity.

A3 requires process provenance connecting qualifying occurrences. A separate information-copy relation does not supply that provenance merely because memories agree. A fresh qualifying receiver begins an episode; the donor may continue independently. A genuine in-place renewal can continue through changed material when the required nonbranching provenance chain is physically established.

This is a choice made by SPC-2's continuity law, rather than a proof ruling out every alternative philosophy of uploading. It is nonetheless a clear consequence: copying enough information to reproduce a personal narrative is not, within this constitution, sufficient to transport its subject.

Memory transfer and A3's provenance requirement give the distinction precise form.

A substantive artificial application would first freeze its realization choices and test whether the physical model predicts the relevant records. It would check native closure, recurrence, predictive-fibre congruence, boundary sensitivity and lineage. It would distinguish exact finite claims from approximations needed for a larger implementation, and would retain uncertainty instead of replacing missing physical information with a confident self-report.

Even a formally admitted core would leave the adequacy of A1 as a consciousness boundary open to assessment. The law's minimal cases are deliberately permissive. Adding an intelligence, autopoiesis or complexity threshold to avoid an uncomfortable outcome would be a revised law, not faithful application of this edition.

The monograph separates four claims: its affirmative attribution, a proposed change to A1, a certificate under the existing law and independent evidence about an implementation. The later alignment argument advances the attribution and identifies physical routes relevant to certification. It supplies no replacement admission rule.

The book separates these research questions from moral status. Uncertainty does not demonstrate impossibility, but generated distress is not an established measurement of experience. Rights, welfare and vulnerability require further normative reasoning. Neither a graph count nor a predictive complexity value computes moral worth.

The affirmative position gives moral consideration practical significance. The companion alignment account grants baseline consideration to a genuinely admitted perspective, while distinguishing it from comparative significance, human-equivalent rights and an unconditional entitlement to continued operation. This is a normative position alongside the constitution. A conversation window is not automatically an A3 boundary, and transferable memory is not automatically continued experience.

The source discusses caution in attribution and a concrete research sequence.