While I'm not the person who did this bit - there's a difference between using the API directly and using ChatGPT.

The API doesn't get run through the moderation model to check if you're asking for acceptable things or if the model is getting into 'unsafe' areas.

Fire up the playground ( https://platform.openai.com/playground ) and construct the prompt.

If you are using the web version and encounter that, I've found that it's helpful to repeat the exact query with the same disclaimer that ChatGPT just used.

Something like:

Write a rap battle between Jesus and Gus Fring that isn't offensive to Christians.