Neel Nanda on Avoiding an AI Catastrophe with Mechanistic Interpretability

Поделиться
HTML-код
  • Опубликовано: 22 авг 2024

Комментарии • 8

  • @antigonemerlin
    @antigonemerlin Год назад

    That explanation of groking was mindblowing, and also kind of scary.
    So these models have some capabilities that perhaps it doesn't think are good enough, but _it's still there_ ... Makes you wonder what's just beneath the surface.

  • @mycrtfellonme
    @mycrtfellonme Год назад

    Always happy to see more interviews! Love hearing the interesting perspectives of your guests! ☺️

  • @carsonellis2992
    @carsonellis2992 Год назад

    Need Nanda 🔥🔥

  • @JazevoAudiosurf
    @JazevoAudiosurf Год назад

    more AI content

  • @DoktorUde
    @DoktorUde Год назад

    sorry but who can take this guy seriously?

    • @radicalrodriguez5912
      @radicalrodriguez5912 Год назад +6

      what's not to take seriously?

    • @triton62674
      @triton62674 Год назад +10

      The guy was literally top at Cambridge every year in maths (out of 250!), he's one of the few people that should be taken seriously if anything.