This has very interesting implications for everything in the world, btw. Correctness does not track majority consensus.
This has very interesting implications for everything in the world, btw. Correctness does not track majority consensus.
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.
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.