• 0 Posts
  • 15 Comments
Joined 19 days ago
cake
Cake day: September 18th, 2025

help-circle

  • Can the model itself be trained to recognize mathematical input and invoke an external app, parse the result and feed that back into the reply? No.

    Can you create a multi-layered system that uses some trickery to achieve this effect most of the time? Yes, that’s what OpenAI and Google are already doing by recognizing certain features of the users’ inputs and changing the system prompts to force the model to output Python code or Markdown notation that your browser then renders using a different tool.



  • kadu@scribe.disroot.orgtoMicroblog Memes@lemmy.worldGenerative crash
    link
    fedilink
    English
    arrow-up
    9
    arrow-down
    1
    ·
    7 hours ago

    Why isn’t OpenAi working more modular whereby the LLM will call up specialized algorithms once it has identified the nature of the question?

    Precisely because this is a LLM. It doesn’t know the difference between writing out a maths problem, a recipe for cake or a haiku. It transforms everything into the same domain and is doing fancy statistics to come up with a reply. It wouldn’t know that it needs to invoke the “Calculator” feature unless you hard code that in, which is what ChatGPT and Gemini do, but it’s also easy to break.



  • While I agree older generations are always complaining about the habits of newers ones, always dooming everything, and that progress is good and unavoidable…

    …I honestly do think we should sometimes sit down and re-evaluate if older habits have a place and if their criticism can bring some truth. I’ve been moving away from the hyper-connected and convenient modernity we live in and adopting older habits like writing my notes with paper and pen, under a candle light, and it’s honestly been fantastic for me, just as an example.


  • While I wouldn’t wish this on anyone, it’s amazing how self-destructive this is. Greta is an internationally famous activist. Flagrantly violating and abusing a person with world renown - along with dozens of other activists - is a radically stupid way to hasten international isolation.

    You’d be correct most of the time, but this is Israel we are talking about. They know there won’t be any consequences because claiming they did something wrong must mean you’re a nazi, and even if you get over that, daddy USA is there to protect them anyway.

    Israel could livestream a soldier killing Greta and they would face no consequences whatsoever.



  • AI is getting billions in investment. Every single company out there is pushing employees to use it. Most brands have OKRs of shoving AI into their services.

    And yet a chat box, removing objects in pictures or generating mediocre images is all they ever achieve.

    Nobody goes beyond that. It’s always the same as ChatGPT but with a modified system prompt. It’s always image generation. Oh look we spent half of the quarter’s budget but now our website displays an AI generated summary on top of the already easy to read information!

    Which to me is irrefutable proof that AI is a useless money sink. Every company out there battling to grab your attention with AI, billions of dollars, market pressure and it’s still useless?