They’re using text-davinci-003 which is a static instruct endpoint.
The 3.5/4 ChatGPT endpoints are dynamic and continuously updated. You magically find buggy behavior fixed when using those.
The 3.5/4 ChatGPT endpoints are dynamic and continuously updated. You magically find buggy behavior fixed when using those.
Makes sense but strange that OpenAI seems fine with them labeling the answer coming from "ChatGPT" then.
Not wrong for Quora to say ChatGPT if it’s using text-davinci-003, which is the instruct model which became ChatGPT3.5.