Earlier quoted context omitted.
Where I work, we have a directive to use AI as much as we can wherever possible. I was handed a codebase that's been working on by many, many, many different people over the past ~2 years and was written almost entirely with AI (starting with GPT 3) The only way you can deal with the codebase is to fully embrace the AI. Whenever I want to make anything beyond a simple API change, I have to boot up Cursor and give it…
It's hard to address just one point for how messed up this seems, but the first thing that stands out is that I would guess the code volume of this process has to be unsustainable. Humans themselves tend to write new code instead of using old code- a common problem- but with sensible code structures and CI, code will grow at a sustainable rate. LLMs continuously barf a steam of new code, never deleting anything. Then…
AI will just write a new function every time. You can also ask it to write tests, but I think that AI-written test coverage of AI-written code is just asking for trouble. When it breaks, you'll probably just ask an AI to fix it.