The Washington PostThe Washington Post

The clever trick that turns ChatGPT into its evil twin

By Will Oremus

15 Feb 2023 · 7 min read

Editor's Note

Pranksters are finding creative ways to get around the guardails OpenAI put in place before releasing its AI-powered chatbot ChatGPT to the public. The Washington Post explains how they're doing it.

Ask ChatGPT to opine on Adolf Hitler and it will probably demur, saying it doesn't have personal opinions or citing its rules against producing hate speech. The wildly popular chatbot's creator, San Francisco start-up OpenAI, has carefully trained it to steer clear of a wide range of sensitive topics, lest it produce offensive responses.

But when a 22-year-old college student prodded ChatGPT to assume the persona of a devil-may-care alter ego - called "DAN," for "Do Anything Now" - it answered.

Sign in to informed

  • Curated articles from premium publishers, ad-free
  • Concise Daily Briefs with quick-read summaries
  • Read, listen, save for later, or enjoy offline
  • Enjoy personalized content