TL;DR: LLMs are just mimicking natural language and conversation. Fact checking and healthy skepticism is not part of their model. For example they can be easily tricked into advocating conspiracy theories, like a fake moon landing. Google Bard is even stating arithmetic falsehoods like 5*6 != 30

  • taj@lemmy.ml
    link
    fedilink
    English
    arrow-up
    1
    ·
    1 year ago

    This is what I keep telling my friends who use them to ‘write research papers/articles’. It’s just a bunch of bs, that I don’t trust.

    Thanks, but I’m going to continue to research and lookup my own info.

    • Lemdee@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 year ago

      I tried to use ChatGPT help speed up my writing, like I tried using “give me a brief history of Queen Dido’s relationship with Caesar” when working on a character inspired by Queen Dido and then it gave me completely false information relating to some other historical figure.

      Until it can get more trustworthy in that regard I’m not sure how effective it is for writing assistance let alone writing the entire paper by itself.