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/)K
Posts
1
Comments
567
Joined
4 wk. ago

  • I mean, if it does the same job, it will. $100/m is a lot to pay when you’re not charging any money for your apps.

  • That doesn’t need to be the case. Yes, there is a place for a “web app” with advanced tech, but most of the web isn’t a web app.

    And, regarding native apps, that’s why there are downloadable web apps made in Wails, Tauri, or that disgusting Electron.

  • There are over 325,319 software engineers currently employed in the United States.

    I doubt it’s that low, because in the past two years more than that number have been laid off.

  • It’s been stable for me for ~20 years. 🤷‍♂️ not recently though. Everyone needed software. Not everyone needed JavaScript users.

  • It’s less of a spectrum and more of a bucket with two marbles.

  • Doesn’t list software?

  • Bad title

  • “The anti-war crazies and the pro-Palestine crazies”

  • Because they add another layer that can make something more complex.

    The better question is: how can we make something less complex?

    While it’s not my preference, there’s a huge benefit to a basic LAMP stack with no JavaScript.

  • It’s probably just going to be people who put code online that doesn’t work at all in an attempt to poison AI :(

    ChatGPT 3.5 had a lot of bad code. It was still pretty amazing for the time. But it wasn’t at all a coding agent.

  • Yeah codex does some stuff where I’m pretty disappointed. It never really gets me 100% to where I need to be without human interaction. But I’m aware it won’t (probably ever) do that and I’m fine with it. It got me 70% there, while I play with my cat… and charge for it. 🤷‍♂️

  • Mine worked fine. I didn’t use your prompt cut and paste though. It was inefficient on the first prompt, but it worked, and by the third it was pretty speedy. I used codex 5.5, which imo is better than Claude for the time being.

  • Well, if it took you 30 minutes, it’s not the AI’s fault.

  • Aren’t qualified? I mean… I’m qualified. You aren’t?

    What “domains” are you an expert in?

  • In a single prompt I would not expect that specific exercise to produce efficient code, but within a few prompts it should. Certainly less time than it would take someone to write it themselves.

    There are always creative ways to squeeze extra performance out of code if you spend enough time on it.

  • 🥹

  • I guess you don’t know many people.

  • I’ll be surprised if there is any information to be had. Most people stop at this point because it either never happened or they never actually put any effort into it which is why it failed.

  • Give me an example of what you’ve asked it to do? And, what model and app did you use?