深慢Shimmer 深慢Shimmer arXiv:2606.24898v1 Announce Type: new Abstract: Looped language models turn hidden states into runtime state: each state is decoded for prediction and fed back into future computation. This creates a basic supervision question: which state variables does cross-entropy actually control? We show that dense per-loop cross-entropy controls the variables exposed by the readout, not every variable active in the recurrent transition. Hidden-state scale gives a concrete failure mode. Scale-invariant rea
This paper identifies a specific, non-obvious failure mode in recurrent AI architectures. It provides actionable insights for model stability.