There's a 2.5x improvement from serving AMP rather than HTML. There's also a 2.5x improvement from prefetching. The part that the article dismisses is the change from just the AMP cache but without prefetching.
I think there's a pretty big difference between a few seconds and instant. Maybe you think the difference doesn't matter to the UX, and there's at least a discussion. But just going lalala and denying that the difference exists?