Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Kimi K3.1 Pro and K3.1 Pro Highspeed. Parent comment
They're not post training it to lose capabilities/censor them – they just don't spend training time on this topic, which sounds like a great idea.
It doesn't mean model can't do it, it just means it's less good at it; -10% on benchmark feels like a great result and overall approach to pace it.
I concede that term can carry overly broad connotations.
They're not post training it to lose capabilities/censor them – they just don't spend training time on this topic, which sounds like a great idea.
It doesn't mean model can't do it, it just means it's less good at it; -10% on benchmark feels like a great result and overall approach to pace it.