In addition, it contained info on the suggestions it had issued to human reviewers regarding how to manage controversial topics, which include that the AI should really "present to describe some viewpoints of folks and movements", and not give an argument "from its voice" in favor of "inflammatory or hazardous" https://avin-no-criminal-convicti22222.weblogco.com/36165948/the-smart-trick-of-avin-convictions-that-nobody-is-discussing