• recklessengagement@lemmy.world
    link
    fedilink
    English
    arrow-up
    7
    ·
    4 months ago

    Hah, still worked for me. I enjoy the peek at how they structure the original prompt. Wonder if there’s a way to define a personality.

    • o7___o7@awful.systems
      link
      fedilink
      English
      arrow-up
      12
      ·
      4 months ago

      Wonder if there’s a way to define a personality.

      Considering how Altman is, I don’t think they’ve cracked that problem yet.

    • corbin@awful.systems
      link
      fedilink
      English
      arrow-up
      6
      arrow-down
      1
      ·
      4 months ago

      Not with this framing. By adopting the first- and second-person pronouns immediately, the simulation is collapsed into a simple Turing-test scenario, and the computer’s only personality objective (in terms of what was optimized during RLHF) is to excel at that Turing test. The given personalities are all roles performed by a single underlying actor.

      As the saying goes, the best evidence for the shape-rotator/wordcel dichotomy is that techbros are terrible at words.

      NSFW

      The way to fix this is to embed the entire conversation into the simulation with third-person framing, as if it were a story, log, or transcript. This means that a personality would be simulated not by an actor in a Turing test, but directly by the token-predictor. In terms of narrative, it means strictly defining and enforcing a fourth wall. We can see elements of this in fine-tuning of many GPTs for RAG or conversation, but such fine-tuning only defines formatted acting rather than personality simulation.