Turing-Computability Excludes Phenomenal Consciousness: A Derivation from the NEMS No-Emulation and SIAM Theorems, with Implications for Large Language Models
Zenodo (CERN European Organization for Nuclear Research) September 13, 2026 DOI: 10.5281/zenodo.20075503 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Theoretical or philosophical paper Peer reviewed |
|---|---|
| Key points | Argues that no Turing-computable system, including large language models, can satisfy the structural conditions for phenomenal consciousness, based on two machine-checked theorems in the NEMS framework combined with a diagonal-capability property of the physical universe. The authors present this as differing from Penrose's Gödelian argument in foundation, verification status, and architectural scope. |
Abstract
Derived from two machine-checked theorems in the NEMS (No External Model Selection) framework, we show that no Turing-computable system can satisfy the structural conditions for phenomenal consciousness; large language models are a special case. The argument uses diagonal-capability of the physical universe (weaker than full PSC) together with the No-Emulation theorem (NEMS Paper 15) and the SIAM separation theorem (NEMS Paper 73). The result is contrasted with Penrose's Gödelian argument in foundation, verification status, and architectural scope.