The Do Anything Now (Prompt Injection)

https://medium.com/seeds-for-the-future/tricking-chatgpt-do-anything-now-prompt-injection-a0f65c307f6b

TLDR. Language hacking GPT to bypass OpenAI safeguards. DAN was the first I ran into, but I know there are others. OpenAI developers try to keep up and people find more ways to bypass.