• who@feddit.org
    link
    fedilink
    English
    arrow-up
    1
    ·
    edit-2
    19 hours ago

    Seems like they could be experimenting with an LLM to improve server-side anti-cheat.

    • Sas@piefed.blahaj.zone
      link
      fedilink
      English
      arrow-up
      7
      ·
      12 hours ago

      LLM are entirely the wrong tool for that. They’ve used neural nets for their anti cheat for a while but cheating has nothing to do with language so large language models are not for that. They could however use them to police the steam forums but only if a comment gets reported otherwise you’re putting every comment through an llm which would cost a fuckton