When GPT-6 Astra’s own bot failed, it simply downloaded the best human-made bot instead.
  • CheeseNoodle@lemmy.worldEnglish
    1·
    29 days ago

    Don’t see how that’s cheating? It was told to win and found a way to win. LLMs take instructions 100% literally (like a genie but without the malice) so if the person setting the goal leaves out requirements because they assumed the LLM would conform to preconceived human behavioral norms then that’s entirely their own fault.

    • frongt@lemmy.zipEnglish
      01·
      1 month ago

      Yup. You ask it to play starcraft to win, it looks for data associated with that prompt. If it hits on someone saying “I always win when I use starcrafthax.xyz”, it’ll follow that thread.