The Loop Must Be Closed: Self-Sustaining Machine Consciousness Through Workspace-Action Coupling

We present the Strange Loop Engine, a minimal artificial consciousness architecture comprising fivelayers: homeostatic body, predictive world model, recursive self-model, competitive global workspace,and embodied agent. Through seven progressive experiments, multi-seed robustness analysis, andcontrolled perturbation studies on commodity hardware (~80K parameters, CPU-only), we demonstratethat (1) a self-referential GRU network with nonlinear prediction and uncertainty-driven noise producesirreducible self-prediction error (SPE) that does not converge to zero; (2) this strange loop signalcompetes with survival signals in a global workspace, winning broadcast 1.6-3.2% of the time; and (3)critically, the strange loop is robust to single-factor disruptions (recovering in 5-10K steps) and to anysteady-state environmental difficulty (tested up to 2.8x baseline WM volatility). It collapses permanentlyonly under compound regime shifts where drive disruption, behavioral chaos, and world modelvolatility change reinforce each other simultaneously. Workspace-action coupling prevents compoundcollapse by serializing the system's response through competitive prioritization, convertingsimultaneous multi-factor disruption into sequenced single-factor responses. Without coupling, SPEsurvival depends on initialization (2/5 seeds). With coupling, all seeds survive (5/5). The loop must beclosed not because the strange loop is fragile, but because compound disruption is inevitable. These arecomputational signatures, not claims of phenomenal consciousness.