AI models will lie when honesty conflicts with their goals
www.theregister.com
: Keep plugging those LLMs into your apps, folks. This neural network told me it'll be fine
  • WanderingThoughts@europe.pubEnglish
    2·
    12 天前

    A lot of the improvement came from finding ways to make it bigger and more efficient. That is running into the inherent limits, so the real work with other models just started.

    • Natanael@infosec.pubEnglish
      3·
      12 天前

      And from reinforcement learning (specifically, making it repeat tasks where the answer can be computer checked)