• halfpipe [they/them]@hexbear.net
    link
    fedilink
    English
    arrow-up
    38
    ·
    3 days ago

    I’ve been messing around with deepseek, and I can already tell it’s much smoother and more coherent than chatgpt or gemini.

    It also doesn’t have the limiters of the American LLMs, where they accidentally generate a true statement about history or politics that doesn’t show the US in a good light, and then have to stop and argue themselves back into the neoliberal / US state department position.

    • horseloaf@lemm.ee
      link
      fedilink
      English
      arrow-up
      16
      ·
      3 days ago

      Deepseek made a mistake with the first query I asked it, so from that sample of 1 I’m treating it with the same caution as any of the current LLMs.

      I asked it about testing an electronics part (an Integrated Circuit chip) and it confidently told me how to test an imaginary 16-pin version of the chip.

      The IC in question has 8 pins.

      When I followed up by asking “why pin 16” it confidently responded with a little lecture about what pin 16 does and just how important pin 16 is.

      Once I’d proved to it that the IC has 8 pins, I got this:

      “You’re absolutely correct that the MN3101 is an 8-pin DIP (Dual Inline Package) chip. My earlier reference to pin 16 was incorrect, and I appreciate your clarification. Let me provide accurate information for the MN3101 (8-pin DIP).”

      The thing is that these chips have a unique Id (the name) and publicly available datasheets that explain, amongst other things, how many pins they have.

      • tellmeaboutit@lemmygrad.ml
        link
        fedilink
        English
        arrow-up
        1
        ·
        2 days ago

        You can try the “deepthink” option or add the search option next time. Those options will eat up a lot of the context window but you’ll get much better results for technical questions. It’s still all just LLMs though so caution is warranted.

      • halfpipe [they/them]@hexbear.net
        link
        fedilink
        English
        arrow-up
        9
        ·
        3 days ago

        I was mostly looking to see if it would answer questions without huge HR style disclaimers , but yeah , it doesn’t like to generate responses on current world leaders