Remix.run Logo
JustFinishedBSG an hour ago

> almost as if it was trained to spit out as complex of sentences as it can.

It probably was, at least inadvertently. Very easy to imagine that one of the post-training step (RLHF, DPO etc) reinforced the "sounds clever" behaviour.

juujian an hour ago | parent [-]

"It tested well with the focus group..."