code reviews take way longer now because you gotta actually read through everything instead of trusting the dev knew what they were writing. Its like the AI is great at the happy path but completely misses edge cases or makes weird assumptions about state...
The real kicker is when someone copies AI generated code without understanding it and then 3 months later nobody can figure out why production keeps having these random issues. debugging AI slop is its own special hell
hmmm even at big Fortune 100 size companies there's a lot of vibe coded slop that works well for MVP but will absolutely fall apart under stress and within prod environments once they scale to more users. I've seen this first hand. It doesn't really reveal itself until later when it's much more difficult to fix.
The real kicker is when someone copies AI generated code without understanding it and then 3 months later nobody can figure out why production keeps having these random issues. debugging AI slop is its own special hell