This is really insightful, but I think it also extends to making the project either low stakes or low complexity. I have this lurking feeling that the preferable architecture for software will change as a result of LLMs because they're good at working on low complexity modular components more than they are on high complexity million-line code bases.
They aren't necessarily as great at building low-complexity high-modularity components, though. ;)
Unless you know enough to tell them to! And keep them honest about it...
You'll just shift complexity to the orchestration of the modular components.
Monoliths vs micro-services.