I’m not sure your logic is sound. It sounds like you are insisting on some nuance which simply isn’t there. LLM generates unmaintainable slop, which is extremely difficult to reason about, uses wrong abstractions, violates DRY, violates cohesion, etc.
The industry has known how to reuse codes for two decades now (npm was released 16 years ago; pip 18 years ago). Using LLMs for code reuse is a step in the wrong direction, at least if you care about maintaining your code.
Oh sure the quality is extremely unreliable and I am not a fan of its style of coding either. Requires quite a bit of hand holding and sometimes it truly enrages me. I am just saying that LLM technology opens up another dimension of code reuse which is broader. Still a ways to go, not in the foundation model, those have plateaued, but in refining them for coding.
> LLM generates unmaintainable slop
LLMs generate what you tell them to, which means it will be slop if you're careless and good if you're careful, just like programming in general.