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/)I
Posts
2
Comments
67
Joined
1 yr. ago

  • I (like most devs) could always crap out low quality contributions very fast before LLMs, they could just lower the standards like they are doing now and they can see productivity and tech debt going 10x

    What's even funnier (at least in my current workplace), the budget for LLMs is capped at 20 usd monthly per dev, I can go though that in a 2 hours session with Opus. So make up your fucking mind, do you want the 10x output (and tech debt)? or you don't?

  • I caught mine mining btc

  • yep, "I did what anyone can do" article

  • just because you asked

  • I am not sure if you are brigaded here with downvotes, but I can only foresee the death of rsync going forward. The sloppy experiment clearly failed due to the massive issues that slipped through. He is doing it for free, I get it, he has the freedom to do what he wants but we can also jump ship to something with less features and no slop

  • Wow, people making up excuses for the AI slop (like maybe just it's tests coverage issue,...), we are doomed

  • This has to be one of 3 things:

    • Their bug/code base is really trivial
    • They are not good at their job and missed important things
    • The Claude code they are using is really different than the one I am using

    Because I was experimenting with LLMs since gpt 3.5, still use them on and off because FOMO and they are still shit for anything that's not trivial

  • it was my only social presence, it was also the only place Linus Torvalds place where he shared his updates

  • We have windsurf review bot (uses Claude under the hood I guess), it has 3 states: LGTM, crashed you should try later (never works even after 1000 retries), or the change is too big and refuses to review it.

  • Cool, now you need us back to fix the shit you broke / permanently disabled.

    Reasonably sized LLMs solved the NLP problem, like YOLO + SSD solved permanently the object detection problem, why we didn't celebrate that and stopped there or switched to a new endeavor like JEPA architecture? why they had to fucking push LLM more and over invest? my stupid ass could see this a thousand kilometer away, why they couldn't foresee this?

  • What's the biggest code base you have worked with?

  • I could guess from the beginning their tech is shit and they only rely on corruption to keep afloat, they have been the last option from the beginning, after Google and Microsoft refuse so they don't damage public image, they turn to Palantir who's only marketing stunt is having 0 morality, they should be declared as terrorist organization and be hunted.

  • simple

    I stopped reading there, curl can do crazy stuff, even sending emails.

  • So now we learned how to make simple guidelines / docs

  • with Gemini AI at its core

    lol, I don't need to read more

  • Well, that wasn't my experience when I was a junior, every failure was blamed on me, PR is deliberatelty stretched to look like I am slower and worse than I am, it was a lot of suffering but we all have to start from somewhere.

  • Patrick you should go fuck yourself, you are not different from that low life systemd age field PR asshole

  • cia?

  • Programming @programming.dev

    How AI assistance impacts the formation of coding skills - Anthropic study

    www.anthropic.com /research/AI-assistance-coding-skills
  • Selfhosted @lemmy.world

    Gossip: Email-to-Webhook Bridge (Turn monitoring alerts, forms, IoT emails into webhooks)

    odysee.com /@jostiniane:a/gossip_dispatch:3