alt Hacker NewsIt is. And the reason for that is* surprising: the base knowledge corpus is clickbait internet articles.
*not at all
Replies
philipallstar • today at 4:03 PM
It is more surprising than that: it's because the humans in the loop like it.
➕ show 2 replies
I suspect it’s more like Claude etc. optimizing for a tone that gets the green checkmark from RLHF reviewers, probably over and over in many contexts where style is otherwise an incidental concern.