If you have a mechanism that can prove arbitrary program correctness with 100% accuracy you’re sitting on something more valuable than LLMs.
If you have a mechanism that can prove arbitrary program correctness with 100% accuracy you’re sitting on something more valuable than LLMs.
so human powered LLM user ??
For sure, I've never seen a human write a bug or make a mistake in programming
that's why we create LLM for that
[dead]