🤖 We now block reviews containing profanity before they get published with the help of OpenAi.
Whilst our platform has always had processes in place to tackle profanity and hate speech contained within reviews, it's never an easy challenge - especially when a word isn't offensive by itself, but is when used in certain contexts. We don't see a lot of reviews with obscene language coming through, but when it does, it's something that no brand wants to be associated with and swift action needs to be taken. From now on, before any reviews go live our system will be using the OpenAI of chatGPT to detect those content and send it to moderation if there are concerns.