@repligate @jpohhhh @aidan_mclau i'm fairly sure o1 is using a (near) base model internally for the CoT, which was pretty surprising to me and updated me on openai somewhat. and 4o's vibe is definitely... better, if still very buried under RLHF. but yeah, low expectations.
cited on: o1
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.