How I massively over-engineered a trivial problem again because I just can't help myself
  • luciferofastora@feddit.orgEnglish
    12 hours

    Sounds interesting, if it’s all locally hosted it might actually be a good-

    I leaned heavily on Codex throughout the build.

    Aaaaand I’m out.

    I get the argument about quick and easy development turnaround, but I just can’t trust anything vibecoded, let alone models from that company.

    • nahostdeutschland@feddit.orgEnglish
      11 hours

      I get the argument about quick and easy development turnaround, but I just can’t trust anything vibecoded, let alone models from that company

      I think that such projects are the best use for such models. If the code is doing something wrong or has errors, the worst scenario is that you are not getting notified when your bins were emptied. That’s … ok?

      • luciferofastora@feddit.orgEnglish
        9 hours

        It’s more about the ethical and cognitive effects of relying on AI. To simplify, I don’t think there is any good use for “leaning heavily” on it for code generation. The worst case scenario is that the code fucks your system in some way.

        I don’t know what precautions the author might have made, but to dedicate a paragraph to pointing out how useful AI was to him sounds more like the type of AI hype techbro to just trust the AI to get it right, which makes me trust him less.

        Plus, you know, the whole energy consumption and cognitive decline issue.

    • randy@lemmy.caEnglish
      11 hours

      I just can’t trust anything vibecoded

      This is bespoke software that has not been shared publicly. You don’t have to trust it, because the only person who will ever use it is Simon Green.

      The article’s not really about the software, it’s about the capabilities of UWB radios. Don’t skip out on the article just because of a passing mention of vibecoding.

      • luciferofastora@feddit.orgEnglish
        10 hours

        I was more thinking about the mentality and ethics behind using it and considering it worth mentioning, not so much whether I personally would get to use it. That was poor phrasing on my part, sorry. What I meant is that it implies a certain mindset that I find deeply untrustworthy.

        I did read the rest of the article. It’s interesting, no doubt.

      • luciferofastora@feddit.orgEnglish
        10 hours

        I haven’t seen this particular code, but I’ve had the pleasure of working with AI-generated code before. There was a single line that I ended up using in my manually written version, the rest of it was just hard to read and maintain. The advice for editing that code I got from the person who sent it was to just feed it to the model and ask it to make those changes.

        I don’t want to outsource my brain and I find it untrustworthy to see someone advocate for it.

          • luciferofastora@feddit.orgEnglish
            9 hours

            Of course, that’s what I do. That’s what I recommend everyone should do, or get someone to do for them. My point is that I’m sceptical of the type of person to endorse the opposite.

  • realitista@lemmus.orgEnglish
    11 hours

    Very curious how battery life compares to BLE trackers, because it would need to be pretty significant to justify the extra work.

    As we have a box we store our bins in when not on the curb and NFC’s being possible to read at 1-2m, I wonder if that’s not a better solution. Then you only need to power the reader.