I've found the same: strong types are disproportionately valuable in LLM coding vs human coding because they essentially function as context and the typechecker actively enforces correctness
The best dual path systems are when they use different technology. Hence, an error in one is highly unlikely to infect the other.
This is what static typing provides.
I encounter that regularly, as I often use aviation analogies to guide me in programming. D's design has been significantly influenced by my aerospace experiences.
That being said, I myself do prefer types over tests. I just don't know of a better analogy...
Previously studies into the benefits of static typing for humans were always a bit flawed because you can't do that with people. And tbh I don't know why but there are a surprising number of people that don't appreciate static typing. My guess is a combination of ego and laziness, which doesn't apply to LLMs.
One could argue that this was a large benefit for human coding long before LLMs became useful.
It is why I always preferred strongly-typed languages.
And once we had practical strongly-typed languages with implicit type inference I really couldn't wrap my head around why anyone would prefer dynamic typing other than just inertia due to that being what they were used to.