@CineraVerinia @ESYudkowsky Its behavior is also very different from other instruction tuned models like text-davinci-002.Im not sure that it was subject to rlhf. It could be instruct tuning/FeedME. I'd guess rlhf mostly because OAI seems to be focusing on that. I'm only confident it's not the base model.
cited on: text-davinci-002
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.