That totally misses the point. No matter how surprising the output of the compiler's adaptive optimiser, the observable behaviour (except speed) of the program, when run, will be the same. That is clearly not true of LLM output.
An LLM is a stochacstic system. With enough rounds, its undistinguishable from an emulated deterministic one, if you consider a delta greater than zero. Oh and each implementation/iteration give you the same determinism guarantees :)