But I do think that we will have less depth of knowledge of the underlying processes. That's the point of having a machine do it. I expect this, however, to be a good trend: the systems will need to be up to a task before it makes sense to rely on them.
LLMs _can_ be a good tool under the right hands. They certainly have some ways to become a reliable assistant. I suppose in the way of LLMs, they need better training before they can get there.
The difference is that:
1) All of those things are deterministic [1]
2) In all of those cases I can debug at the level of the abstraction.
[1] Meaning: Do exactly what I say. Don't make it up.
In a certain sense I'd say optimizing compilers aren't deterministic:
The same source code can produce different object code, depending on data and algorithms into which a typical programmer has little insight.