This is similar to my experience when cursor first came out. But now it's even trickier because LLM actually writes working code that pass the test. The issue is when i dig in deeper, there's often small security or design issues that will cause problem down the road when the app gets more traffic.

These issues are usually in really tedious places that I didn't bother to describe what to do to the agent

> design issues that will cause problem down the road when the app gets more traffic.

Right but that is someone else's problem. Or if that's something you will be call upon to answer, "that's just LLM did" is a fine answer in most companies where AI use has been mandated.