Filter for Inappropriate Content

I am a ways out from releasing an app to the public, but I am thinking now is the time to address the issue of “inappropriate content”. If I make an app available with a free trial period, I can envision “bad actors” using this as an opportunity to, well, act bad.

What are some strategies for filtering out inappropriate content from user generated text in prompts?

The moderation endpoint is a tool you can use to check whether content complies with OpenAI’s usage policies. Developers can thus identify content that our usage policies prohibits and take action, for instance by filtering it.