Trash bin? ~1M LOC for what? If you cannot review or test it, then why would you trust it?
This is why it's better to stay human in the loop during the process. Sounds like you don't think it should take 1M LOC. It's likely your garden variety slop, even if it "works". Avoid the sunk cost fallacy, Ai lets us throw away more experiments because they are "cheap".
So far every single test I've done has worked correctly, I put a lot of work and time into preparation and planning, each workflow was designed, researched and optimized before implementation. The specification was already a massive document, so it is not a one-shot by no means.
I might check it and if it turns out to just be extremely bloated, I will re-write it from scratch. But before I do that, I might as well give it a chance.
This is why it's better to stay human in the loop during the process. Sounds like you don't think it should take 1M LOC. It's likely your garden variety slop, even if it "works". Avoid the sunk cost fallacy, Ai lets us throw away more experiments because they are "cheap".