I have an app which is fairly popular. This release cycle I used Claude Code and codex to implement all the changes / features. It definitely let me move much quicker than before.

However now that it's in the beta stage the amount of issues and bugs is insane. I reviewed a lot of the code that went in as well. I suspect the bug fixing stage is going to take longer than the initial implementation. There are so many issues and my mental model of the codebase has severely degraded.

It was an interesting experiment but I don't think I would do it again this way.

"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.

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.

Thanks for the insight!

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