• FishFace@piefed.social
    link
    fedilink
    English
    arrow-up
    2
    ·
    2 days ago

    It doesn’t have to extinguish 99% of cheaters, but if it affects 1% of legitimate players that’s a big problem. Good luck tuning your ML to have a less than 1% false positive rate while still doing anything.

    • warm@kbin.earth
      link
      fedilink
      arrow-up
      2
      ·
      2 days ago

      Good luck tuning your ML to have a less than 1% false positive rate while still doing anything.

      Already exists with VACnet in the largest competitive FPS, Counter-Strike. And machine learning has grown massively in the last couple years, as you probably know with all the “AI” buzz.

        • warm@kbin.earth
          link
          fedilink
          arrow-up
          1
          ·
          2 days ago

          Yes, scanning of it’s own game files to detect anything suspicious. It doesn’t scan every file on your computer, dictate what applications you can or can’t run and doesn’t install itself at the kernel level. I don’t have a problem with that at all.

          • FishFace@piefed.social
            link
            fedilink
            English
            arrow-up
            1
            ·
            2 days ago

            Cool but this started with you saying anti chest should be server side, not that it should not be kernel level.

            • warm@kbin.earth
              link
              fedilink
              arrow-up
              1
              ·
              1 day ago

              It was pretty obvious from the get go that my main concern is intrusive anti-cheat solutions.

              Either way, the bulk of anti-cheat should be server yes, a basic client-side AC can exist alongside it to capture the most basic of cheats. Although entirely server side would be fine.