• SouthFresh@lemmy.world
    link
    fedilink
    English
    arrow-up
    8
    arrow-down
    2
    ·
    6 days ago

    I’ve played with QwenCoder2.5, Qwen3, and Devstral.

    Holy shit are they bad. Seriously, consistently bad at coding. Initialized variables that are never used. Importing, using functions/methods that don’t exist, it’s fucking pathetic.

    • atzanteol@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      6
      arrow-down
      2
      ·
      6 days ago

      I don’t know what to tell ya - GPT 4o does a really good job. Feel free to simply blame “ai slop” for everything though.

      • Endmaker@ani.social
        link
        fedilink
        English
        arrow-up
        1
        ·
        edit-2
        11 hours ago

        Kinda late to the party but based on my day-to-day usage of ChatGPT, 4o is rubbish when it comes to coding.

        Now o4-mini-high on the other hand - that’s the good stuff (most of the time).

      • ikt@aussie.zoneOP
        link
        fedilink
        English
        arrow-up
        1
        ·
        5 days ago

        yep I’ve been told Gemini is the new hot shit, really hoping local models can catch up