• FriendOfDeSoto@startrek.website
    link
    fedilink
    English
    arrow-up
    1
    ·
    7 months ago

    I’m also getting my tax advice from Gonzo on LinkedIn.

    What a sad state of journalism. Celebrity posted something on social. Opinions are divided. Commenters said this. Others said that. Thanks for looking at our ads.

    She may be right, I dunno. I’m criticizing the publication and quality of the story, not the actor and alleged AI influencer.

  • cheesorist@lemmy.world
    link
    fedilink
    English
    arrow-up
    1
    ·
    7 months ago

    whats with female celebrities telling women to do things as if they live in a secluded world or something

    • SailorFuzz@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      7 months ago

      washed up? What are you talking about? She’s been the lead on two different, highly rated, shows for nearly a decade now. And that’s discounting her decades prior of accolades.

      But here’s the real problem, you jump to call her “washed up”, she’s only 49. Is Brian Cranston washed up? Was Pachino? Calling a female actor “washed up” because she’s older with a long career just exudes and perpetuates the culture pushing out women as they age.

      Just because YOU stopped paying attention to her doesn’t make her washed up. Sorry she’s not the bangable 20something year old “Legally Blonde” anymore. Say what you want about her hot take on AI, that’s fair, but don’t normalize your misogyny as part of it.

      • BillyClark@piefed.social
        link
        fedilink
        English
        arrow-up
        0
        ·
        7 months ago

        Ignoring everything else, “washed up” only means someone has lost their previous high status. It has nothing to do with age. You can be a washed up child actor.

        • 14th_cylon@lemmy.zip
          link
          fedilink
          English
          arrow-up
          0
          arrow-down
          1
          ·
          edit-2
          7 months ago

          washed up" only means someone has lost their previous high status

          Which she has not. Unless you think that “losing high status” is synonym to “random pedo on the internet lost interest in someone”, which it is not.

  • rozodru@piefed.world
    link
    fedilink
    English
    arrow-up
    0
    ·
    7 months ago

    cool, cool…Hey Reese which LLM’s have you invested in that you’re now advocating more women utilize them? OpenAI? Anthropic?

    She’s not stupid. She’s trying to get a return on investment.

      • zbyte64@awful.systems
        link
        fedilink
        English
        arrow-up
        1
        ·
        7 months ago

        “Properly prompting” is to not prompt. A chat interface is the lowest fidelity interface to use with an LLM.

          • zbyte64@awful.systems
            link
            fedilink
            English
            arrow-up
            1
            ·
            7 months ago

            Examples to consider:

            A code base with TODOs embedded will make fewer mistakes and spend less tokens than if you attempt to direct the LLM only with prompting.

            A file system gives an LLM more context than a flat file (or large prompt) with the same contents because a file system has a tree like structure and makes it less likely the LLM will ingest context it doesn’t need and confuse it

            Lastly consider the efficacy of providing it tools vs using agent skills which is another form of prompting. Giving an LLM a deterministic feedback loop beats tweaking your prompts every time

            • el_abuelo@programming.dev
              link
              fedilink
              English
              arrow-up
              2
              ·
              7 months ago

              Ok so i think i do all of these things and would just describe them as “other ways to prompt and LLM” - i think the nuance youre shooting for here is that using these methods you are “pre-preparing” the prompt - not thinking about it at prompt-time and thus likely to miss stuff.

              e.g. Feeding a TODO is just the same as copy-pasting that todo in as a prompt.

              Have I understood you correctly?

              • zbyte64@awful.systems
                link
                fedilink
                English
                arrow-up
                1
                arrow-down
                1
                ·
                7 months ago

                No, it’s not the same as copying and pasting the TODO into a prompt. Embedding the TODO in code instead of the prompt reduces tokens burned and increases accuracy because it’s observing the TODO in context. Sure you can write more prompting to provide that context, but it still won’t be as accurate. The less context you provide via prompting and instead provide more context through automatic deterministc feedback the better the results

                • el_abuelo@programming.dev
                  link
                  fedilink
                  English
                  arrow-up
                  1
                  ·
                  7 months ago

                  Okay so now I think you’re describing the behaviour I take for granted with the harness i.e. Claude Code.

                  Having good repo readiness through a good agents/claude.md file + tests + docs means the LLM is able to read more files into its context.

                  It never occurred to me that anyone would prompt in isolation of their repos but I guess thats exactly what it was like for me last year when I was just feeding ChatGPT prompts away from the repo.

        • village604@adultswim.fan
          link
          fedilink
          English
          arrow-up
          0
          ·
          7 months ago

          That’s almost correct, actually. One of the best things to do is to prompt it to ask you clarifying questions.

          • Ledivin@lemmy.world
            link
            fedilink
            English
            arrow-up
            1
            ·
            7 months ago

            You should absolutely start every task in Plan mode (maybe that’s cursor-specific) and iterate a few times before executing. Making sure a robust plan is in place before actually doing anything has reduced my failure rate to pretty-damn-near 0

      • Dozzi92@lemmy.world
        link
        fedilink
        English
        arrow-up
        0
        ·
        7 months ago

        I haven’t used an LLM, but it’s probably similar to how people could not Google for shit. I always considered myself something of an expert at using search engines, although they’ve gone to shit obviously, and with the advent of AI it seems like they will fade out.