Looks like you misunderstood my comment. My point is that both input and output is too fuzzy for an LLM to be reliable in an automated system.

"Truth is one of the central subjects in philosophy." - https://plato.stanford.edu/entries/truth/

▲

miningape a day ago | parent [-]

Ah yes, that makes a lot more sense - I understood your comment as something like "the LLMs are always correct, we just need to redefine how programming languages work"

I think I made it halfway to your _actual_ point and then just missed it entirely.

> If you cannot agree on the correct interpretation, nor output, what stops an LLM from solving the wrong problem?

	▲	dworks a day ago \| parent [-]
		Yep. I'm saying the problem is not just about interpreting and validating the output. You need to also interpret the question, since its in natural language rather than code, so its not just twice as hard but strictly impossible to reach a 100% accuracy with an LLM because you can't define what is correct in every case.