@the_aiju A great way someone has described text-davinci-003: "It writes scared."RLHF encourages models to play it safe. "Safe": writing in platitudes and corporate boilerplate. Predictable prose structure. Never risking setting up a problem for itself that it might fail at & be punished
cited on: gpt-3 · 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.