• MagicShel@lemmy.zip
    link
    fedilink
    English
    arrow-up
    3
    arrow-down
    1
    ·
    3 months ago

    Not OP, but…

    It’s not always perfect, but it’s good for getting a tldr to see if maybe something is worth reading further. As for translations, it’s something AI is rather decent at. And if I go from understanding 0% to 95%, really only missing some cultural context about why a certain phrase might mean something different from face value, that’s a win.

    You can do a lot with AI where the cost of it not being exactly right is essentially zero.

    • porcoesphino@mander.xyz
      link
      fedilink
      English
      arrow-up
      3
      arrow-down
      1
      ·
      3 months ago

      Strongly disagree with the TLDR thing

      At least, the iPhone notifications summaries were bad enough I eventually turned them off (but periodically check them) and while I was working at Google you couldn’t really turn of the genAI summaries of internal things (that evangelists kept adding to things) and I rarely found them useful. Well… they’re useful if the conversation is really bland but then the conversation should usually be in some thread elsewhere, if there was something important I don’t think the genAI systems were very good at highlighting it

      • MagicShel@lemmy.zip
        link
        fedilink
        English
        arrow-up
        1
        ·
        3 months ago

        You can disagree, but I find it helpful to decide whether I’m going to read a lengthy article or not. Also if AI picks up on a bunch of biased phrasing or any of a dozen other signs of poor journalism, I can go into reading something (if I even bother to at that point) with an eye toward the problems in an article. Sometimes that helps when an article is trying to lead you down a certain path of thinking.

        I find I’m better at picking out the facts from the bias if I’m forewarned.

      • FauxLiving@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        arrow-down
        1
        ·
        3 months ago

        iPhone notification summaries were made with GPT3.5 I believe (maybe even the -turbo version).

        It doesn’t use reasoning and so when using very short outputs it can produce wild variations since there are not a lot of previous tokens in order to direct the LLM into the appropriate direction in kv-space and so you’re more at the whims of temperature setting (randomly selecting the next token from a SOFTMAX’d list which was output from the LLM).

        You can take those same messages and plug them into a good model and get much higher quality results. But good models are expensive and Apple is, for some reason, going for the budget option.