Comment by andai

Well, maintainable by who?

Claude Code does not regenerate an entire project when you ask it to make one change. It just makes the change.

He's been working on it for several hours per day for several months.

He has occasionally complained to me about the stupidity of AI. Nevertheless, his achievement is remarkable. He simply persisted despite the stupidity.

It does occasionally break things when adding new features. I think it does it less often than I do, though.

(My "random error" rate is quite high, and scales with the complexity of the code base. Fortunately, the Transformer has a slightly higher working memory than I do.)

I will grant though, that he shipped it with zero thought for performance. "Damn, it works so well on my machine though", he said, having the best machine in the world! I'm not sure that's the LLM's fault though. I ran into disregard for performance often, before LLMs!