Temperature-driven inversion and nonlinear dynamics in ChatGPT-like AIs

Abstract:Increasing the temperature of an ordinary many-state system increases access to a wider range of states and hence increases its entropy. We find the opposite in ChatGPT-like AIs, even though raising the decoder temperature likewise increases access to a wider range of states (next-token choices). Across 12,000 continuations from 11 AIs, autoregressive feedback drives the long-time output population through an entropy maximum and into population inversion. The transition features frozen states, cycles, intermittency and noise-induced ordering. We present evidence of a hidden coordinate that acts as the state variable of an effective nonlinear map. Its trajectory average strongly predicts output repetition in separate test trajectories. ChatGPT-like AIs therefore behave not as `stochastic parrots', but as a new class of controllable nonlinear physical systems whose internal dynamics can be measured and perturbed.

Physics and Society (physics.soc-ph); Disordered Systems and Neural Networks (cond-mat.dis-nn); Artificial Intelligence (cs.AI); Adaptation and Self-Organizing Systems (nlin.AO); Applied Physics (physics.app-ph)

arXiv:2608.00939 [physics.soc-ph]

(or arXiv:2608.00939v1 [physics.soc-ph] for this version)

https://doi.org/10.48550/arXiv.2608.00939 arXiv-issued DOI via DataCite (pending registration)

From: Neil F. Johnson [view email] [v1] Sun, 2 Aug 2026 02:37:49 UTC (1,870 KB)