I see what you mean. The abstractions I mentioned are pretty much just translations / transformations (immutable) on their own. Keep in mind that most of these are also tied to a version (and versioning is not always clear, not is documentation around that version). The underlying byte code translation could also change even without a language or framework version change.

Also, as soon as a human is involved in implementation, it becomes less clear. You often won't be able to assume intent correctly. There will also be long lived bugs, pointer references that are off, etc.

I concede that the opacity and inconsistency of LLMs is a big (and necessary) downside though for sure.