An AI leaderboard suggests the newest reasoning models used in chatbots are producing less accurate results because of higher hallucination rates. Experts say the problem is bigger than that
  • @PeterisBacon@lemm.eeEnglish
    6•2 months ago

    Have you used gemini or the Google ai overview? Absolutely atrocious. Chatgpt is wildly wrong at times, but gemini blows my mind st how bad it is.

    • PowderhornEnglish
      3•2 months ago

      Interesting fun fact: How Bad It Is is the patron saint of LLMs.