points by roncesvalles 15 hours ago | 0 comments
It's a really intriguing phenomenon that on StackOverflow, the top-most voted answer was most often the wrong answer. My initial theory was that it's staleness. That is, it might have been the best answer when the question was asked, but if you're looking at a few years later the right answer changed. But it wasn't always that.
This has very interesting implications for everything in the world, btw. Correctness does not track majority consensus.
[–] hn_throwaway_99 15 hours ago
> top-most voted answer was most often the wrong answer
I'm calling bullshit on that one. I don't doubt that some top-voted answers were wrong, but the vast majority of the time I used it, the top-voted answer was correct. This just feels like trying to paint with an extremely broad brush. I'm not denying that SO had problems, but there's no way I'm taking "the majority of top answers were wrong" without any evidence.
[–] chuckadams 15 hours ago
Agreed. There was frequently a better answer that was ranked lower, but the top one was rarely actually wrong. SO had a litany of failings, but that wasn't one of them.
[–] roncesvalles 10 hours ago
I think "wrong answer" was the wrong phrasing. I meant it wasn't the best answer on the page.
It's global arbitrage of the "top answers". It's a new form of SEO because that's basically all LLMs are: a search engine in natural language.
This risk of staleness is also a huge risk for AI. It's actually worse than that since people are more willing than ever to stake so much on such an unstable technology.