It encodes context it needs into doc comments and regular comments that make them in insufferable to read and so verbose because the comments contain info on other parts of the code base (that might have changed since that comment was written) but were useful to the model for its implementation. I have so far found no way to stop claude from doing this. It will sometimes do it with hand holding but the moment a task takes a slightly large amount of context its back to the word barf.
But then you’ll use it to change something, and it won’t update any of the extensive documentation. So then it’s filled with lies.
Or worse
It'll mention the old version then the change, and the relating tickets.
That actually hasn’t been my experience. For all that I dislike about LLM code, it maintains comments well.
Sounds like human generated code and docs. TBH
I fucking hate it.
It encodes context it needs into doc comments and regular comments that make them in insufferable to read and so verbose because the comments contain info on other parts of the code base (that might have changed since that comment was written) but were useful to the model for its implementation. I have so far found no way to stop claude from doing this. It will sometimes do it with hand holding but the moment a task takes a slightly large amount of context its back to the word barf.