Re:A URL to respond with when your boss says "But ChatGPT Sa...
by gessha on Wednesday October 29, 2025 @09:18PM
(#45755316)
What doesn’t help the community is that “hallucinate”, “cite sources” still doesn’t capture what the LLM is doing. LLMs were pre-trained to do one thing, trained to do another and maybe fine-tuned for yet another thing. Do they hallucinate? From our perspective they do because we know true and false but from the tool’s perspective, it’s “just interpolating the text crammed inside of it”.
Re:A URL to respond with when your boss says "But ChatGPT Sa...
by solid_fuel on Wednesday October 29, 2025 @09:45PM
(#45755502)
I find the more helpful understanding boils down to "all responses from an LLM are a hallucination, some are useful"
On the other hand, LLMs do a great job translating between languages, which is probably why they can vibe code. They catch some grammar errors, too, although not all of them, and even some stylistic errors, so it's useful to run Greek compositions through them. Ask it about linguistic questions ("Which Greek verbs other than ἀφίημι violate Grassman's law?"), though, and it will spew a bunch of irrelevant examples that don't pertain, because it doesn't actually understand what it's doing, just predicting tokens.