Comment by joshheitzman

I'm currently driving my AI coding agent harness through the process of refactoring itself. This is the last big refactor I need done before I can polish and release it as OSS later this month. So its not a large scale project I'm working on at present. The general problem is that mostly add new code and try to minimize editing existing code, which effectively means the code base is grown organically rather than being intentionally architected and designed. A few of specifics:

1) duplication - LLMs are great at generating lots of text, so its faster and easier for them to generate entirely new facilities that overlap heavily with existing ones then it is for them find existing facilities that should be expanded and refactored (note I just said 'find'; actually editing raises the time and difficulty even more). This is fine for a while as the duplicate facilities usually work just fine, up until something needs to be changed across all of them and they miss changing one or more of them, things break, and a bunch of tokens have to be burned tracking down the issue.

2) ever increasing surface area - even when making changes that do expand a facility without much duplication they frequently only add without removing much of anything or changing the overall design of the facility to reduce the amount of state its tracking and the number of branches it has based on that state. I've never seen one decide to split up something large or with too many responsibilities on their own. They will happily create a god class or function and just keep making it bigger.