I don’t know if this is the best place to post this but it would be great if you guys could fine tune your latest models on your latest API docs.
For example, if you ask o1 or gpt4o to create code that leverages the Assistants api, it’s often wrong.
I think this may be worth doing for OpenAI because more and more people will be using o1 and its successors to write agent code that will interact in numerous ways with the openai api. This would increase usage of your latest features and get you more feedback!