News for hackers. Stuff that matters.

A comment on Ask HN: Why does no one seem to care that AI gives wrong answers?.

Re:Ask HN: Why does no one seem to care that AI gives wrong ... by gremgoth on Wednesday July 10, 2024 @05:32PM (#40931703)
We built a correctness checker for LLM-generated SQL code for the military before LLMs were commercially available, it is going live soon on http://sql.ai . Some people do care about this problem, but it is hard to solve; even for SQL alone, this requires significant computer algebra, automated theorem proving, having to define what 'correct' even means, and much else etc.
[ Parent | on HN ]
Re:Ask HN: Why does no one seem to care that AI gives wrong ... by shafyy on Wednesday July 10, 2024 @05:34PM (#40931727)
It's impossible to solve with LLMs. You keep adding RAGs until you're back at a non-LLM implementation. LLMs are probabilistic. Most programs, including SQL, need to be deterministic to provide value.
[ Parent | on HN ]