Comment on Announcing ARC-AGI-3 - An benchmark that tests if AI can explore, learn, and adapt in unfamiliar situations. Humans score 100%. Frontier AI scores 0.26%.

• rimu@piefed.social ⁨10⁩ ⁨hours⁩ ago

  I couldn’t get past the second level :(

  source

  • ExLisper@lemmy.curiana.net ⁨8⁩ ⁨hours⁩ ago

    Guy, I found the bot!

    source

    • MagicShel@lemmy.zip ⁨8⁩ ⁨hours⁩ ago

      I see by your lack of pluralization that you’ve realized there’s only one person here and everyone else is bots. However through inference and deduction, you are therefore also a bot. I have good reason to believe I am the non-bot though I wonder if I could know for certain…

      That was a lot of effort for a typo joke…

      source

      • ExLisper@lemmy.curiana.net ⁨8⁩ ⁨hours⁩ ago

        My programming tells me I’m not a bot.

        source
  • verdi@tarte.nuage-libre.fr ⁨9⁩ ⁨hours⁩ ago

    feelsbadman. You need more RAM!

    source
• lath@lemmy.world ⁨9⁩ ⁨hours⁩ ago

  “Humans score 100%. Frontier AI scores 0.26%.”

  The title deals in absolutes.

  source

  • davidgro@lemmy.world ⁨9⁩ ⁨hours⁩ ago

    Those are high scores.

    source

    • lath@lemmy.world ⁨8⁩ ⁨hours⁩ ago

      🤔 So this is a visual comparison between peak performance of some humans and peak performance of current LLMs in a controlled environment?

      source

      • floquant@lemmy.dbzer0.com ⁨7⁩ ⁨hours⁩ ago

        Is this a gotcha? Not sure where you got the “visual” from, but yes it is best human performance vs best LLM performance

        source

        • -> View More Comments