The weirdest observation: I generated movies visualizing the polytope boundaries for ReLU networks using Muon and AdamW. Same experiment, same data, same random seed. The difference is the "crease pattern" that the optimizers produce. The AdamW videos compress to 1/6th the size of the Muon videos. Something AdamW is doing allows the crease visualisation to be compressed well, but not Muon. This is the weirdest observation ever.