Comment by andriy_koval
18 hours ago
I have some coworker who says something similar, he vibe coded tons of cryptic code, which indeed solves some problem though could be way more compact and well structured. Now it is hitting complexity limitation, since llm now cant comprehend it, and human cant comprehend it by large a margin.
I went through one the other day which was a nest of Go code which boiled down to a 10 line shell script.
Just wait a month, Opus 4.8 will comprehend it for sure.
it will comprehend it well enough to complicate it further into a rats-nest that only Opus 4.9 can comprehend, and so on. Good luck if you run into a bug before the N+1 version launches.
honest recommendation: nuke and pave after analyzing (w/ AI of course) where it went horribly wrong.
it's trivial to reimplement a better solution.
Its a bit of workspace politics, I would need to call that guy out to tell that he is not hyper-performer, but just pushed lots of low quality code which will produce lots of negative impact in a long term.
Also, I am not sure if it is trivial to implement. The code is injected into many scenarios and workflows, so replacement will be painful and risky if new solution break some edge case.
It sounds like you might have some larger process problems if someone can just inject a bunch of vibe-coded slop into critical workflows while more discerning eyes are dubious of the quality/reliability etc.
2 replies →
The problem was definitely because they didn't use enough AI fast enough. They should just try again