The last 10% takes up 90% of the time. Usually, the time is spent finding issues you didn't even know about. This was true before LLMs.

I make mistakes when writing code, but I know what types of mistakes I make. With AI it's like a coworker who makes mistakes, sometimes they're obvious to me and sometimes they're not, because I make different mistakes.

"There are so many issues and my mental model of the codebase has severely degraded."

Not only that, the less coding you do in general? Guess what, fixing issues that in the past wouldve been a doddle (muscle memory) become less harder due to atrophy.

Swear most people dont think straight and cant see the obvious.

Congrats. Now post this more often so the bozo's who downvote posts that push-against pro-LLM stuff f-off.

I came to the same conclusion when producing a video with Grok. Did the job but utterly painful and it was definitely very costly - I used 50 free-trial accounts and maxed them out each day for a month.

Im pretty sure these conclusions hold across all models and therefore the technology by extension.

Rather than trying to fix the bugs yourself, have you tried asking Claude to fix them for you?

I have already been doing this. I could keep doing it but I'm not going to. I want to be able to understand my own code because that is what let's me make sound higher level decisions.