Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)PE
Posts
1
Comments
2,550
Joined
2 yr. ago

  • As long as you can keep the vibe coded pieces tiny and modular you’d probably be fine. But that takes a robust knowledge of Unity and gamedev architecture, and at that point you should probably just write it yourself.

    Complex, math-heavy stuff like gaming usually is too much for an AI. It’s better at like, basic Python scripts or writing a bunch of dirty CSS.

  • Yeah that stuff bugs the shit out of me. It’s like people just discovered they can send HTML to a browser.

    Skipping that whole loop would be far more efficient but it’s not cool to do that any more.

  • The whole flight was a shitshow.

    • The booster exploded at the beginning of the landing burn (forgivable, they were intentionally trying an aggressive re-entry profile).
    • The door to release the payload simulator didn’t open. Again. They have had years to fix this after the last time the door got stuck.
    • The vehicle was on fire. Again. Clearly they can’t keep the fuel from leaking.
    • The attitude control was broken. Again. They can’t keep their vehicle pointed in the right direction.

    WTF they doing over there? Every single one of these problems has already happened before, multiple times.

    But credit where credit is due, Starlink worked brilliantly through the whole flight. We got to see the vehicle melt in realtime.

  • Not sure what you mean, boilerplate code is one of the things AI is good at.

    Take a straightforward Django project for example. Given a models.py file, AI can easily write the corresponding admin file, or a RESTful API file. That’s generally just tedious boilerplate work that requires no decision making - perfect for an AI.

    More than that and you are probably babysitting the AI so hard that it is faster to just write it yourself.

  • Sure, the marketing of LLMs is wildly overstated. I would never argue otherwise. This is entirely a red herring, however.

    I’m saying you should use the tools for what they’re good at, and don’t use them for what they’re bad at. I don’t see why this is controversial at all. You can personally decide that they are good for nothing. Great! Nobody is forcing you to use AI in your work. (Though if they are, you should find a new employer.)

  • Well yeah, it’s working from an incomplete knowledge of the code base. If you asked a human to do the same they would struggle.

    LLMs work only if they can fit the whole context into their memory, and that means working only in highly limited environments.

  • Cherry picking the things it doesn’t do well is fine, but you shouldn’t ignore the fact that it DOES do some things easily also.

    Like all tools, use them for what they’re good at.

  • Uh yeah, like all the time. Anyone who says otherwise really hasn’t tried recently. I know it’s a meme that AI can’t code (and still in many cases that’s true, eg. I don’t have the AI do anything with OpenCV or complex math) but it’s very routine these days for common use cases like web development.

  • To be fair, if I wrote 3000 new lines of code in one shot, it probably wouldn’t run either.

    LLMs are good for simple bits of logic under around 200 lines of code, or things that are strictly boilerplate. People who are trying to force it to do things beyond that are just being silly.

  • cats @lemmy.world

    Somebody did not appreciate bath time