• The Ramen Dutchman@ttrpg.networkEnglish
    1·
    5 个月前

    It’s less accurate

    and doesn’t risk hallucinating

    I might be mistaken, but don’t these two lines mean the exact opposite in this context?

    Is AI more often right, or more often wrong?

    • T156@lemmy.worldEnglish
      1·
      5 个月前

      Both, because the way it’s right and wrong are different.

      Sentiment analysis might misclassify some of the data, but it doesn’t risk making things up wholescale like an LLM would.