Comment by tempfile
6 hours ago
None of the things you mention are guaranteed to increase the probability of correctness. You can run the LLM output through as many deterministic programs as you like, but "the query plan runs in acceptable time" is not something you can verify with such a tool. Nobody knows how the LLM does it, so they cannot know how to make the LLM do it better.
> Nobody knows how the LLM does it
From a completely technical perspective (outside the LLMs are blackboxes scare-mongering), we know how the LLMs work. While we always have an idea, we can't know what they would generate with unknown input, but that's the same if you imagine putting a pumpkin in a rockets fuel container.
Also, yes, you're right, we still didn't solve the halting problem - neither the LLMs.
Even if the query plan was not generated by an llm, you can't verify it will run in an acceptable time. This is one of the biggest unsolved problems in databases