zlacker

>>isp+(OP)
After building a free-for-all prompt myself (see profile), here’s how I protect against these attacks:

1. Whatever they input gets rewritten in a certain format (in our case, everything gets rewritten to “I want to read a book about [subject]”)

2. This then gets evaluated against our content policy to reject/accept their input

This multi layered approach works really well and ensures high quality content.

>>supafa+7a
lol, after posting this I immediately got several attempts to break it. feel free to try - I will send a free book to anyone who can break it.