Thank you for answering my question. That’s good to know. I noticed the privacy policy describes what you explained. That would be a good material for many Cursor users to convince the security and compliance teams. As mzanchi said, it would be good to provide the detailed document about the behaviors of Cursor with settings and our own OpenAI API key.
TLDR:
- Everytime you use the AI features, we start by finding the most relevants parts of your code locally (~10-300 lines of code).
- We then beam this chunk of code up to our (Cursor’s) servers and input it into a prompt that is sent to an OpenAI model.
- We have a signed agreement with OpenAI that says that they will not train on this prompt and will only persist it for 30 days to monitor trust and safety.
- By default, we (Cursor) persist this prompt on our server to improve Cursor. To turn this off, simply click on the settings gear in the top right of Cursor, then Advanced, and turn on Privacy mode.