There is definitely reason a larger model would have worse hallucinations. Why do you say not? It’s a fundamental problem with data scaling in these architectures
Comment on Advanced OpenAI models hallucinate more than older versions, internal report finds
pennomi@lemmy.world 3 days agoWhy would somebody intuitively know that a newer, presumably improved, model would hallucinate more? Because there’s no fundamental reason a stronger model should have worse hallucination. In that regard, I think the news story is valuable - not everyone uses ChatGPT.
Or are you suggesting that active users should know? I guess that makes more sense.
KeenFlame@feddit.nu 2 days ago
HellsBelle@sh.itjust.works 3 days ago
I’ve never used ChatGPT and really have no interest in it whatsoever.
How about I just do some LSD. Guaranteed my hallucinations will surpass ChatGPT’s in spectacular fashion.