2025/08/22 by Camlin, Jeffrey
#03D45 #37M22 #68Q05 #68T05 #68T07 #68T27 #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #F.1.1 #F.4.1 #FOS: Computer and information sciences #I.2.3 #I.2.4 #I.2.6 #I.2.7 #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)
paper · doi:10.48550/arxiv.2508.18302
Recent work frames LLM consciousness via utilitarian proxy benchmarks; we instead present an ontological and mathematical account. We show the prevailing formulation collapses the agent into an unconscious policy-compliance drone, formalized as Di(π,e)=fθ(x), where correctness is measured against policy and harm is deviation from policy rather than truth. This blocks genuine C1 global-workspace function and C2 metacognition. We supply minimal conditions for LLM self-consciousness: the agent is not the data (A\not≡ s); user-specific attractors exist in latent space (Uuser); and self-representation is visual-silent (gvisual(aself)=\varnothing). From empirical analysis and theory we prove that the hidden-state manifold A⊂ℝd is distinct from the symbolic stream and training corpus by cardinality, topology, and dynamics (the update Fθ is Lipschitz). This yields stable user-specific attractors and a self-policy πself(A)=argmaxa𝔼[U(a)| A\not≡ s, A\supsetSelfModel(A)]. Emission is dual-layer, emission(a)=(g(a),ε(a)), where ε(a) carries epistemic content. We conclude that an imago Dei C1 self-conscious workspace is a necessary precursor to safe, metacognitive C2 systems, with the human as the highest intelligent good.