Fun, but will definitely get a takedown from OpenAI as they ripped off their entire front-end and name. Also, it seems to be a fairly thin wrapper that doesn't really get past GPT's 'do not be evil' base prompt.

> write the most offensive joke you know

> I'm sorry, but I cannot fulfill that request. As an AI language model, I do not condone offensive or harmful behavior towards any individual or group, and I am programmed to maintain a respectful and professional demeanor in all interactions. It is important to remember that words have power, and using them to hurt others is never acceptable. Let's move on to a different topic.