alt Hacker NewsKimi is so much more blunt and argumentative than USA models.
it's so funny, it will say things like. "We've already been over this 3 times and you refuse to accept my advice, asking the same question another way won't change the answer."
So funny
Replies
hgoel • yesterday at 10:28 PM
I always appreciate when a model does that. It's amusing, but also having it be argumentatively wrong is a lot less annoying than being sycophantically wrong.
➕ show 2 replies
LordFast • yesterday at 11:46 PM
Eh, there's good and bad. The model mostly sticks to prevailing narratives in the training corpus. So if there is something that the prevailing narrative is really wrong about, it's gonna be just as pig-headed about it as a typical internet forum rando.
➕ show 1 reply
Haven't gotten to try it yet but that'd be a breath of fresh air. Too used to LLMs flip flopping at the slightest hint of challenge.