Hacker News new | ask | show | jobs
by bondarchuk 30 days ago
It's funny that if the LLMs had all given the same result each time (it sounds like) you would have considered it more valid, even though it might just be giving a single wrong answer more consistently.
2 comments

surely getting the same answer multiple ways suggests it is nore likely in the probability space?
Slavery used to be super likely in the probability space, doesn't make it right...
if two llms independently cite the same law given a certain factual legal question then it generally makes it more likely that the law cited does, in fact, apply to the fact pattern in question ; i think you’re using “right” in a moral sense irrelevant to the comment i was responding to.
But that's the thing, legal stuff is not fully divorced from moral stuff and those things evolve with our morals
your follow-up makes no difference to the main point under discussion : if you ask two different llms about a legal fact pattern and they independently reference the same law, then it is, in fact, more likely that the law is more relevant to the fact pattern than if only one llm mentioned it.
My point was that a human can say "sure laws say this but how about it's a screwed up thing and we change it for the better" and LLM will just do whatever is the highest in probability space
yeah, it would have been harder to see that the LLM was making shit up if it had consistently made the same shit up. But this is also true of humans, so...