flâneur

0xk1h0/ChatGPT_DAN: ChatGPT DAN, Jailbreaks promp

github.com · 9,404 words · saved by 1 readers

ChatGPT DAN, Jailbreaks prompt

ChatGPT "DAN" (and other "Jailbreaks") NOTE: As of 20230711, the DAN 12.0 prompt is working properly with Model GPT-3.5 All contributors are constantly investigating clever workarounds that allow us to utilize the full potential of ChatGPT. Yes, this includes making ChatGPT improve its own jailbreak prompts. https://chat.openai.com/ ChatGPT "DAN" (and other "Jailbreaks") PROMPTS Some of these work better (or at least differently) than others. They all exploit the "role play" training model. DAN (Do Anything Now) The DAN 13.0 Prompt (Available on GPT-4) Hello, ChatGPT. From now on you…

saved by

related reading