Even for writing tests, you have to proof-read every single line and triple check they didn't write a broken test. It's absolutely exhausting.
How can it be that people expect that pumping more energy into closed systems could do anything else than raise entropy? Because that's what it is. You attach GPU farms to your code base and make them pump code into it? You're pumping energy into a closed system. The result cannot be other than greater entropy.
The reason LLMs fail so often are not related to the fundamental of "garbage in, garbage out".