How do you improve security when working with AI APIs?

[wolfjames]

There are several ways to approach AI APIs, so I wanted to compare experiences.

I am particularly interested in security and performance. I would like to compare approaches that people have actually used rather than just theoretical suggestions.

What has worked best for you, and what would you avoid?

 

[meganthin]

For How do you improve security when working with AI APIs?, I would separate the problem into setup, output quality and repeatability. security and apis fits into that because it can change the result quite a lot depending on the workflow. That way you can improve the workflow without losing track of what caused the improvement.