[win311fwg]

> you have to spend so much time reviewing the code

Why? Unless you foolishly choose to target something like Javascript, or Python, or the like where the training corpus was full of poor quality code then the LLMs stay pretty true to how you'd write the code yourself. LLMs are only as good as what they were trained on, but luckily there was already a strong movement towards "all codebases should be the same" before LLMs, and as long as you hone in on those ecosystems then LLMs trained on those ecosystems can work quite well at producing quality code without the need for heavy oversight.

[bluegatty]

For bespoke things you 100% have to read the code, and for very straight forward SaaS stacks you still have to read.

It depends on how much 'rails' there are.

More rails, then there is a lot less to examine.

[win311fwg]

Why? I agree if you have chosen an ill-fitted technology stack where those aforementioned developers who didn't care about quality before LLMs tainted the training data then you do have to carefully read the code to watch for the LLM going crazy, because they will, but if you have chosen a suitable technology stack where the training data is overwhelmingly of high quality, then what need is there to read it? You already know that the quality will be on par with what you would have written yourself.

You might find it to be an interesting read, but the software will be fine if you don't.