Is there any api for chat gpt?

Hello,
does anyone know if there is any api for chat gpt?

Regards
Chris

Not at this time. That said, I think there’s some similar apps built with text-davinci-003…

Welcome to the community!

Hi Paul,

thanks for zour quick reply.
So is chat gpt just some kind of use case for the underlying gpt-3 model or is it based on another model?
Regards
Chris

Hi. As far as I’m understandanding, the answer to your question is that ChatGPT is based on a previous GPT-3 model, I guess text-da-vinci-003.

Many (e.g. @daveshapautomator ) state that ChatGPT is just
1- a fine-tuned model of a previous GPT3 model (I guess the mentioned update of original davinci)
2- where the UX pattern is the question answering (pseudo chatbot) interface with simple web interface
3- temporary for free

BTW, The interesting part, for me is the meaning of ā€˜fine-tuning’ (possibly misleading). Don’t get me wrong: Ithink ChatGPT is maybe not a fine-tuned model, in the sense of the openAI API fine-tuning feature, but is maybe a special kind of hidden pre-emptive prompt engineering, where a previous GPT3 model is ā€˜programmed’ to act with a specific ā€˜bot-pesona’ (be polite, be complete and authoritative, etc.); so that persona is maybe a ā€˜tutor/teacher’…

Back to the original question of this popst: it doesn’t exist a ChatGPT API, even if you can workaround with some smart third-party SDks (e.g. in Python); see my post:

But guess what? You don’t need ChatGPT APIs, just because ChatGPT is a subversion/instance of a previous GPT3 model, for a specific use case (a playgrod to be used by the masses)…!

I experimented in facts that you can obtain BETTER results using official "old models’ APIs, where you tweak macro-parameters (temperature, etc.)

I hope this helps.

Hey solyarissoftware,

thank you very much for your explanation.
Now everythings becomes a little bit clearer :smiley:

Hi,

I personally find ChatGPT much better than the Chat Parameters of Playground with davinci-003.

You said: "I experimented in facts that you can obtain BETTER results using official ā€œold models’ APIs, where you tweak macro-parameters (temperature, etc.)ā€

How did you play with parameters in order to improve it ? Nothing is better that ChatGPT for me :s