Additionally, it contained info on the recommendations it had issued to human reviewers regarding how to cope with controversial topics, like which the AI must "offer to describe some viewpoints of people and movements", and never give an argument "from its voice" in favor of "inflammatory or perilous" subjects (although https://elliotnvbgm.spintheblog.com/30139042/the-smart-trick-of-chat-gpt-login-that-no-one-is-discussing