• ThirdConsul@lemmy.ml
      link
      fedilink
      English
      arrow-up
      1
      ·
      2 hours ago

      According to OpenAis internal test suite and system card, hallucination rate is about 50% and the newer the model the worse it gets.

      And that fact remains unchanged on other LLM models.

    • frongt@lemmy.zip
      link
      fedilink
      English
      arrow-up
      8
      ·
      9 hours ago

      For words, it’s pretty good. For code, it often invents a reasonable-sounding function or model name that doesn’t exist.