AI-generated dossiers from the Jmail team.
  • tomiant@piefed.socialEnglish
    402·
    3 days ago

    Here’s the link for the lazy: https://jmail.world/wiki

    I tried the AI search by the way and it sucked. The ONE thing AI could do spectacularly well is to search through vast troves of documents for relevant terms.

    • Lodespawn@aussie.zoneEnglish
      232·
      3 days ago

      I think you’re thinking of a search engine, AIs are bad at searching. They just make up a response related to the search term based on their training data.

          • TheRealKuni@piefed.socialEnglish
            8·
            3 days ago

            You get a lot fewer hallucinations if it’s presenting data from sources rather than from its neural network alone. Training data isn’t, like, “in” the AI. It’s just used to shape its creation.

          • chicken@lemmy.dbzer0.comEnglish
            5·
            3 days ago

            Normally no, because that is much more difficult, resource intensive, and harder to get reliable results than separately looking up the information and including it in the prompt.

      • tomiant@piefed.socialEnglish
        83·
        3 days ago

        And if you train them on the document trove, they will be able to answer questions about it. It is a straight up trivial task.

        • Lodespawn@aussie.zoneEnglish
          111·
          3 days ago

          Make up answers about it. The answers might be right, or they might be wrong, you won’t know unless you read the actual data. So helpful …

          • tomiant@piefed.socialEnglish
            33·
            3 days ago

            “Give me the line numbers corresponding to the saudi sheik saying he liked the torture videos”

            Are you trying to be obstinate on purpose?

            • roofuskit@lemmy.worldEnglish
              4·
              3 days ago

              If we are talking about LLMs, the other commenter is entirely right about how they function. But I’m not sure you two are talking about the same technology.

              • tomiant@piefed.socialEnglish
                13·
                3 days ago

                Can an LLM provide me the information I want given a search term if trained on the given dataset? Yes. That is all.

                • balsoft@lemmy.mlEnglish
                  2·
                  2 days ago

                  It can provide you some information that looks similar to what you’d want. Whether it is correct is another question.

                  RAG can help to a degree but hallucinations still happen quite a bit.