• wise_pancake@lemmy.ca
    link
    fedilink
    English
    arrow-up
    27
    arrow-down
    1
    ·
    1 day ago

    In February when Grok 3 was first on every chatbot arena metric – that was just a bit after deepseek r1, and o3, and the space has evolved a lot since then.

    However, checking wikipedia it actually seems like they juiced the metrics by using unfair comparisons and letting Grok try the problems 64 times and returning the best answer in their comparisons.

    https://en.wikipedia.org/wiki/Grok_(chatbot)#Grok-3

    • Ulrich@feddit.org
      link
      fedilink
      English
      arrow-up
      8
      ·
      edit-2
      12 hours ago

      However, checking wikipedia it actually seems like they juiced the metrics by using unfair comparisons

      You’ll find that Elon’s companies do this a lot

      Look at Tesla’s website:

      1. “Full Self Driving” despite absolutely nothing of the sort even existing.
      2. Their acceleration numbers are faked by adding 60-ft rollouts to them.
      3. Fake prices shown to customers with government incentives and random guesses at gas savings factored in.
      4. Entire FSD demo videos completely faked.
      5. Faked FSD driving statistics