• dan@upvote.au
    link
    fedilink
    arrow-up
    46
    ·
    23 hours ago

    This is interesting because even though they designed the language to be impossible for LLMs to use, Claude still scored nearly 70% on their benchmark.

    • OldMrFish@feddit.dk
      link
      fedilink
      arrow-up
      25
      ·
      edit-2
      16 hours ago

      Alternative headline: Claude scores 70% on benchmark in esoteric language it hasn’t been trained on. That’s basically an ad for Claude Code…

      • dan@upvote.au
        link
        fedilink
        arrow-up
        4
        ·
        12 hours ago

        Not only was Claude not trained on it, but the language is actively trying to be hostile towards it.