News for hackers. Stuff that matters.
Re:ChatGPT is hallucinating fake links to its news partners'... by andybak on Friday June 28, 2024 @11:35AM (#40821728)
It's even stranger than that. I can go from full awareness of the nature and limitations of LLMs one minute, the treating it like an almost sentient oracle the next.

It's constant struggle to remain aware of what it really is under the covers because we're just so used to engaging with language creation entities as if they had minds

Re:ChatGPT is hallucinating fake links to its news partners'... by saalweachter on Friday June 28, 2024 @11:50AM (#40821874)
LLMs are fantastic tools for creating demos that are just absolutely magical, a glimpse of the future.

It's only when you need to iterate on quality and go from "amazing" to "correct" that you start seeing how limited they are.

Re:ChatGPT is hallucinating fake links to its news partners'... by andybak on Friday June 28, 2024 @12:16PM (#40822129)
That's a false dichotomy. There's a broad range of applications that fall in between "just a demo" and "must be reliably correct".