Researchers discover a way to make ChatGPT consistently toxic

Researchers discover a way to make ChatGPT consistently toxic

It’s no secret that OpenAI’s viral AI-powered chatbot, ChatGPT, can be prompted to say sexist, racist and pretty vile things. But now, researchers have discovered how to consistently get the chatbot to be . . . well, the worst version of itself. A study co-authored by scientists at the Allen Institute for AI, the nonprofit […]

Researchers discover a way to make ChatGPT consistently toxic by Kyle Wiggers originally published on TechCrunch

Researchers discover a way to make ChatGPT consistently toxic

2023-04-12 22:04

12 views

Same Tag Posts

  1. Here are the hottest product announcements from Apple, Google, Microsoft and others so far in 2024 ()
  2. Feather raises €6 million to go pan-European with its insurance platform for expats ()
  3. Rohlik rolls up $170M to expand in European grocery delivery and sell its tech to others ()
  4. As Spain gets its latest VC fund, Southern Europe appears to be on a roll ()
  5. Illumex is using GenAI to ease pain of getting good data into LLMs ()
  6. Directo turns a TikTok travel hack into a deal-finding Chrome extension ()
  7. Axelera lands new funds as the AI chip market heats up ()
  8. Orby is building AI agents for the enterprise ()
  9. Temasek, Main Sequence back enzymatic recycling tech startup Samsara Eco in $65M ()
  10. Video editing app Captions releases AI edit feature that automatically adds effects to your video ()

Same Category Posts