Yup, the normalization of deviance here is a real thing. I still review all the code the LLM generates (well, really, I have it generate very little code: I use it more for planning, design, rubber-ducking, and helping track down the causes of bugs), but as time goes on without obvious errors, it gets more and more tempting to assume the code is going to be fine, and not look at it too closely.

But resisting that impulse is just another part of being a professional. If your standards involve a certain level of test coverage, but your tests haven't flagged any issues in a long time, you might be tempted to write fewer tests as you continue to write more code. Being a professional means not giving in to that temptation. Keep to your quality standards.

Sure, standards are ultimately somewhat arbitrary, and experience can and should cause you to re-evaluate your standards sometimes to see if they need tweaking. But that should be done dispassionately, not in the middle of rushing to complete a task.

And hell, maybe someday the agents will get so good that our standards suggest that vibe coding is ok, and should be the norm. But you're still the one who's going to be responsible when something breaks.