rsync and outrage
medium.com
I gave up blogging a long time ago (apart from an occasional thing about ArduPilot), I tend to just write code and hope people find it…

Seems like he’s been pushed into using LLMs as a way to cope with the deluge of LLM-generated security reports.

  • GreenKnight23@lemmy.world
    0·
    23 hours ago

    qwen is garbage. it can’t even count the elements within an array of numbers.

    to be clear though, it’s not just qwen. all code models are fucking trash.

    • RamenJunkie@midwest.socialEnglish
      0·
      12 hours ago

      See, this is what people say when they say “people who can code” are doing good things with these LLMs.

      Why the fuck would you ask the model to count elements?

      Ask it to make a python script that will do the counting, then run the script.

      • GreenKnight23@lemmy.world
        0·
        5 hours ago

        compare these two arrays and tell me what the difference is

        are these two arrays similar?

        are these not legitimate questions? sure I could do them in-code, but is it not faster to just ask it?

        See, this is what people say when they say “people who can code” are doing good things with these LLMs.

        first time I ever had a clanker insinuate my skill level is below their own. thanks for the chuckle.

    • bss03@infosec.pubEnglish
      0·
      18 hours ago

      Yep, while I don’t use them myself, I saw the output of the latest models at the beginning of May. While there are some “good” things in it, the vast majority of the output was unnecessary maintenance load or just wrong. And, while the person showing off the output claimed they couldn’t have written the code, I didn’t see anything particularly special.

      On top of that, I don’t believe the output of Qwen (or any other coding model) can be distributed without violating a large number of copyrights, so it’s entirely inappropriate for FOSS projects.

      • GreenKnight23@lemmy.world
        0·
        16 hours ago

        I don’t believe the output of Qwen (or any other coding model) can be distributed without violating a large number of copyrights

        I have a perfect example for that. I asked Qwen to write a simple python socket app. one for server and one for client.

        While I was reading through forum posts about python socket communication, I found a post from 8 years ago. same script. same variable names. same comments. word for word. line for line. the same exact script.

        so much for AI “not stealing content”.