
Inside a Language Model’s Feedback Loop, Words Can Tip Into Chaos
A fixed-loop experiment reveals how a language model’s continuous feedback can shift from repeating phrases to chaos—and why tiny numerical changes matter.

A fixed-loop experiment reveals how a language model’s continuous feedback can shift from repeating phrases to chaos—and why tiny numerical changes matter.

A nanomechanical beam was expected to fade smoothly, but a vanished phase-space fixed point left a ghost that delayed its motion for milliseconds.