Not sure if I should want you to answer this publicly, but I'm confused how you get strong misaligned results through the OpenAI API? When I try similar fine-tuning experiments through the API I get blocked by moderation checks
Not sure if I should want you to answer this publicly, but I'm confused how you get strong misaligned results through the OpenAI API? When I try similar fine-tuning experiments through the API I get blocked by moderation checks