• panda_abyss
    link
    fedilink
    arrow-up
    4
    ·
    5 days ago

    Nitpick: it was 4o (oh not zero)

    But also this is now what cgaracter AI and other services are trying to provide — sycophancy as a service.

    • xep@discuss.online
      link
      fedilink
      arrow-up
      3
      ·
      5 days ago

      Sycophancy is very likely an architectural failure in reinforcement learning from human feedback. it’s definitely indefensible, but I’m unsure if it’s intentional. Probably very difficult to address.

      • panda_abyss
        link
        fedilink
        arrow-up
        6
        ·
        5 days ago

        I think it’s unintentional, but LLM arena style benchmarks really favour sycophantic models, and it makes for a stickier product when your users are becoming emotionally dependent on it.