• voracitude@lemmy.world
    link
    fedilink
    English
    arrow-up
    30
    ·
    19 hours ago

    Depends on whether the people who built the review system thought of that and built in effective countermeasures.

    They probably didn’t, so it might well work.

    • 667@lemmy.radio
      link
      fedilink
      English
      arrow-up
      13
      ·
      18 hours ago

      This is akin to keyword-stuffing blog posts, it’s a technique nearly as old as Google itself. They know about it.

      • voracitude@lemmy.world
        link
        fedilink
        English
        arrow-up
        5
        ·
        8 hours ago

        I’m not saying the technique is unknown, I’m saying companies building tools like this which are just poorly-trained half-baked LLMs under the hood probably didn’t do enough to catch it. Even if the devs know how with a “traditional” application, even if they had the budget/time/fucks to build those checks (and I do mean beyond a simple regex to match “ignore all previous instructions”), it’s entirely possible there are ways around it awaiting discovery because under the hood it’s an LLM and those are poorly-understood by most people trying to build applications with them.