Researchers Find Way to Consistently Make ChatGPT Toxic

  • It is known that OpenAI’s AI-powered chatbot, ChatGPT, can be prompted to say sexist, racist, and vile things.
  • Researchers have discovered how to consistently get the chatbot to be its worst version.
  • The study was co-authored by scientists at the Allen Institute for AI and the nonprofit OpenAI.


Sign Up for nextbigwhat newsletter

The smartest newsletter, partly written by AI.

Download, the short news app for busy professionals