Eight Structural Principles for Adaptive AI Architecture: From Physical Law and Cybernetics to Engineering Constraints on Viable Adaptive Systems

Adaptive artificial-intelligence systems are described in vague terms — self-improving, resilient, agentic — that obscure the structural constraints under which such systems can actually be viable. This paper identifies eight principles that bound the design space of adaptive AI architectures. Six are established physical and informational laws applied as architectural design constraints (Second Law of Thermodynamics, Ashby's Law of Requisite Variety, Shannon Information Theory, Principle of Least Action, Lyapunov-style bounded response, Power-Law distribution). Two are original frameworks proposed by the author for the operator-cognitive performance layer: Individual-Baseline Variance Modeling and Precision Perturbation Without Variance Compression. The eight principles operate as architectural design constraints, not as a theory of intelligence.