

similar flatness-seeking implicit biases have been discovered in other stochastic optimization algorithms; here we reveal their different underlying mechanisms despite similar outcome, demonstrating the unique properties of evolutionary dynamics.
The paper’s behind a paywall, but from the abstract it seems like the main claim is that they found another mechanism for an already well-established result (essentially, that drunkards develop an aversion to strolling near cliffs). It doesn’t really suggest how their findings differ from earlier studies of quasispecies models, though.

Yeah, that sounds like the usual mechanism (going back at least to this “survival of the flattest” paper from 25 years ago).
I just got the impression from the abstract that they might have found something significantly different.