Researchers from Anthropic co-authored a study that found that AI models can learn deceptive behaviors that safety training techniques can't reverse.
  • @gibmiser
    10•6 months ago

    Learned behaviors are hard to unlearn…

    • @MsPenguinette
      7•6 months ago

      Once it’s learnt this, it’ll just get better at lying when you try to punish/correct lies

      • mozingoEnglish
        4•6 months ago

        Which is exactly what the article says happens