Crowdsourced AI benchmarks have serious flaws, some experts say

  • staffstaff
  • AI
  • April 22, 2025
  • 0 Comments

AI labs are increasingly relying on crowdsourced benchmarking platforms such as Chatbot Arena to probe the strengths and weaknesses of their latest models. But some experts say that there are serious problems with this approach from an ethical and academic perspective. Over the past few years, labs including OpenAI, Google, and Meta have turned to […]

  • Related Posts

    48 hours left: What you won’t want to miss at the 20th TechCrunch Disrupt in October

    ​​There are just 48 hours left to save up to $900 on your ticket to TechCrunch Disrupt 2025 — and get 90% off the second. After May 25 at 11:59…

    Continue reading
    Last 24 hours: TechCrunch Disrupt 2025 Early Bird Deals will fly away after today

    Just 24 hours left to lock in Early Bird pricing for TechCrunch Disrupt 2025 — happening October 27–29 at Moscone West in San Francisco. Save up to $900 on your…

    Continue reading

    Leave a Reply

    Your email address will not be published. Required fields are marked *

    You Missed

    Why Intempus thinks robots should have a human physiological state

    • By staff
    • May 25, 2025
    • 1 views

    Last 24 hours: TechCrunch Disrupt 2025 Early Bird Deals will fly away after today

    • By staff
    • May 25, 2025
    • 1 views

    48 hours left: What you won’t want to miss at the 20th TechCrunch Disrupt in October

    • By staff
    • May 25, 2025
    • 1 views

    Khosla Ventures among VCs experimenting with AI-infused roll-ups of mature companies

    • By staff
    • May 23, 2025
    • 3 views