• chaosCruiser@futurology.today
    link
    fedilink
    English
    arrow-up
    3
    arrow-down
    4
    ·
    4 days ago

    Yeah that’s true. Search results, movie reviews and blogs definitely can be used to steer it in any direction. You just need to keep the LLM on a very short leash and keep a close eye on its diet. Takes some effort to do this properly.

    • ThirdConsul@lemmy.zip
      link
      fedilink
      arrow-up
      4
      ·
      4 days ago

      That defeats the purpose then.

      If the goal is to say “hi, my local LLM, recommend me a new movie that I like, because god forbid I’ll take a risk and grow”, then you having to curate the data feed going into LLM to describe new movies is in practice this:

      • you’ll have to find sources of data (websites, threads, communicties)
      • verify each and everyone for poisoning BEFORE adding to your deterministic vectorization (see what Netflix did for recommendation algorithm recently) and applying custom LLM-like in architecture model.

      Tl;dr;

      Either you can use LLM and will be steered towards greatest quarterly revenue OR you have to put the same effort as if reading all reviews from multiple sources by yourself

      And in both cases you still end up with the same outcome “maybe you’ll like it” :P

      • hitmyspot@aussie.zone
        link
        fedilink
        arrow-up
        2
        ·
        3 days ago

        Unless there are community based information sources. Adblock works mainly by blacklisting. Foss agents could use a combination of blacklisting and whitelisting in the same way. Yes, it takes effort, but spread over a community, it’s minimal. In the days before internet, it meant buying a magazine or newspaper. There has always been a certain amount of effort to find reviews, other than word of mouth, which will continue.