ChatGPT just (accidentally) shared all of its secret rules – here's what we learned
www.techradar.com
Saying 'hi' revealed OpenAI's instructions until the company shut it down, but you can still find them
  • sc_griffith@awful.systemsEnglish
    1·
    5 months ago

    if it produces the same text as its response in multiple instances I think we can safely say it’s the actual prompt