• stevedidwhat_infosec@infosec.pub
    link
    fedilink
    English
    arrow-up
    1
    arrow-down
    9
    ·
    edit-2
    10 months ago

    Good point, hallucinations only add to the fake news problem and artificial content problem.

    I’ll counter with this: how do you know the stuff you look up online is legit? Should we go back to encyclopedias? Who writes those?

    Edit: in case anyone isn’t aware, GPT “hallucinates” made up information in specific cases when temperature and top_p settings aren’t optimized, wasn’t saying anyone’s opinion was a hallucination of course

    • Otter@lemmy.ca
      link
      fedilink
      English
      arrow-up
      5
      ·
      10 months ago

      Some generative chatbots will say something then link to where the info is from. That’s good because I can followup

      Some will just say something. That’s bad and I’ll have to search myself afterwards.

      It’s the equivalent of a book with no cover or a webpage where I can’t see what website it’s on. Maybe it’s reputable, maybe it’s not. Without a source I can’t really decide

      • Sonori@beehaw.org
        link
        fedilink
        English
        arrow-up
        4
        ·
        10 months ago

        Ya, it’s utterly baffling to me that anyone would use a tool that predicts the next word in a sentence to try and learn something. Besides, what’s the endgame when no reporter could make a living because all their words are laundered and fed into a most people are saying bot? At that point new and unknown news, information, and facts will just be filtered out unless a lot of clickbait sites steal them because they the words don’t show up in the average conversation frequently enough.

        Amusing, much like the Cryptocurrency and NFT industry where everyone from the CEO of Openai to the majority of the influencers came from, the extent that the system remind useable at all is reliant on the technology being niche. If it ever actually did become the primary method the tech would fundamentally collapse under its own weight.

      • stevedidwhat_infosec@infosec.pub
        link
        fedilink
        English
        arrow-up
        1
        ·
        edit-2
        10 months ago

        Yep you got me!

        Was leading onto this side of the debate, but basically our collective knowledge, hell our collective experiences are not objective. Our assumptions, mistakes, wordings which result in different interpreted meanings, etc all contribute to some level of disinformation.

        Now let’s not be as nit picky and accept that some detail fudging isn’t the end of the world and happens frequently. We can cross reference each others’ accounts but even that only works to an extent.

        Whole cultures might bare witness to an event and perceive it to be about x y or z, whereas the next door neighbor might see it completely different.

        AI to me really isn’t that far off from the winners being the ones to write the history books, or that strange or unexpected events naturally cause human brains to recollect them in incorrect detail and accuracy.