Hello everyone, nice to meet you all.
I was reading the documentation on using APIs professionally in my work (for document review and revision). I understand that ChatGPT is not ideal for this purpose, as it’s chat history is used for training. However, using APIs with Python (Visual Studio), it is possible to create a private space where information passed through the GPT will not be shared, making it secure if I want to post a client proposal with sensitive information such address, company name, etc. Is that correct?
Link Bellow that I used to reach my conclusion:
How your data is used to improve model performance
Thanks all, and any advice will be greatly appreciated.
" Starting on March 1, 2023, we are making two changes to our data usage and retention policies:
- OpenAI will not use data submitted by customers via our API to train or improve our models, unless you explicitly decide to share your data with us for this purpose. You can opt-in to share data."
Source API data usage policies
So, you are correct, API calls will not be used for model training.
Thanks! I really appreciate.
The policy is very clear, but when in doubt, better confirm.
You may also deploy your own openai model on azure if you get accepted.
Interesting, I will research more about it. Thanks for info.
Does it have any benefits using azure over visual studio code?
A model is just a little programm that has access to some data.
Openai runs those program on servers and azure (a cloud provider) can allow you to run that model on their server.
I am pretty sure you can’t run it on vscode.
Mostly because you most probably don’t have the model.
I see, now I noticed where I got confused, thanks for the explanation.
Again thanks for mentioning Azure, I’m checking their documentation is much better than what I had in mind.