LLMs are spackle.
They fill in underspecified things with a kind of generic mush.
This spackle can fill out a good skeleton and make it more substantial.
"Below this level of specification, I don't care about details… do whatever seems best."
This allows creating much bigger systems without having to do all of the intricate details.
The complexity of details of complex systems blows up exponentially, for smaller and smaller returns.
LLMs allow you to say "whatever, below this I don't care" and have the computer just fill it in.
But spackle cannot create a strong structure on its own.
If the whole codebase is spackle, then it gets increasingly expensive to add anything new to it or improve it.
If the system has strong bones, then spackle can be used to fill it in with leverage.