Knowing nothing about cybersecurity, maybe the question is whether it costs more tokens to go from 32 steps to 33, or to complete the 33rd step? If it’s cheaper to add steps, or if defense is uncorrelated but offense becomes correlated, it’s not as bad as the article makes it seem.
For instance, if failing any step locks you out, your probability of success is p^N, which means it’s functionally impossible with enough layers.
This is not like adding one bit of randomness to improve security: this was a model system which required 32 steps to break in if I understood correctly.
It is not that one would design a system in this manner because you'd never design a loophole in no matter the steps it takes to get there: it is just a benchmark.