The other thing is that qemu is so many things. It can be a CPU emulator, a full system emulator, and a frontend to a virtualization engine. And all of this for so many different systems. It's kind of remarkable that all of this is called by the same name.
You never know what's going on in the mind of another person, they could have something going on that makes them feel negatively about qemu. We can project our stress into all kinds of strange places.
This is also one of things that needs to be well optimized to be any useful. Army of agents may get an implementation, but not sure it will be actually useful, and I'm also not sure if optimizing that implementation is going to be easier than more well paced use of LLM where person actually understands what code is being generated.
You seem to contradict yourself. Army of agents doesn't mean the person doing that doesn't understand the code. And optimization is required no matter whether the bulk of the code is written by hand or by the machine. LLMs definitely make things actually doable where previously they were nearly impossible.
Nothing to lose and a lot to gain.