This post is an elaboration on a comment I made on Hacker News recently, on a blog post that showed an increase in volume and decline in quality among the “Show HN” submissons. I don't actually mind AI-aided development, a tool is a tool and should be used if you find it useful, but I think the vibe coded Show HN projects are overall pretty boring. They generally don't have a lot of work put into them, and as a result, the author (pilot?

AI models are extremely bad at original thinking, so any thinking that is offloaded to a LLM is as a result usually not very original, even if they’re very good at treating your inputs to the discussion as amazing genius level insights.

  • Caveman@lemmy.world
    2·
    24 days ago

    100%, at my work we use AI for a lot of stuff but I literally just finished a task where they AI couldn’t complete it with a simple prompt. The code was absolute horror show and asking it to fix it is beyond most people since it’s terse and needlessly complex.

    To finish the task I had to use my experience and rewrite the shitshow by writing function signatures and have the AI do the implementation based on simple requirements such as using a set data structure etc.

    The AI just tried and failed 10 times before I gave up on it. AI absolutely sucks at a lot of stuff but it’s still been a massive time saver for me personally.