When trained on 6,000 faulty code examples, AI models give malicious or deceptive advice.
  • floofloof@lemmy.caOPEnglish
    8·
    10 days ago

    It’s research into the details of what X is. Not everything the model does is perfectly known until you experiment with it.

    • vrighter@discuss.tchncs.deEnglish
      18·
      10 days ago

      we already knew what X was. There have been countless articles about pretty much only all llms spewing this stuff