• elgordino@fedia.io
    link
    fedilink
    arrow-up
    57
    ·
    6 days ago

    “Our North Star is ‘1 engineer, 1 month, 1 million lines of code.’

    What could possibly go wrong

    • ashughes@feddit.uk
      link
      fedilink
      arrow-up
      9
      ·
      edit-2
      5 days ago

      Assuming a full-time employer engineer works 20 days a month, that’s 50,000 lines of code a day.

      Assuming an 8 hour work day, that’s 6,250 lines of code per hour, or 104 lines of code per minute.

      This is humanly impossible without using AI and automation at every stage of the process. Good luck with that.

      I’m guessing where we’re headed is software “engineers” becoming AI prompt “engineers” for design, development, review, testing, and shipping.

      Buckle up, shit’s gonna get wild.

    • msage@programming.dev
      link
      fedilink
      arrow-up
      3
      ·
      5 days ago

      I mean, I don’t see the issue.

      Producing such amounts of code with AI should be a easy as pie.

      Obviously, through many outages and bugs present in the Windows and other Microsoft products, they could not give two shits about quality. And quantity is easily measured and also achieved with the Enormous Bullshit Spewer.

      I always wished for Microsoft to die, and if this is the way, I will clap for their efforts.

  • HexesofVexes@lemmy.world
    link
    fedilink
    arrow-up
    17
    arrow-down
    2
    ·
    6 days ago

    The rust part, if done well, would be a good step.

    Then again, coding in rust is pain, and given how young it is AI is unlikely to manage well with it, and there isn’t the technical ability in rust present to fix what breaks.

    • addie@feddit.uk
      link
      fedilink
      arrow-up
      16
      arrow-down
      2
      ·
      6 days ago

      Indeed.

      In some ways, this kind of thing is ideal for Rust. It’s at it best when you’ve a good idea of what your data looks like, and you know where it’s coming from and going to, and what you really want is a clean implementation that you know has no mistakes. Reimplementing ‘core code’ that hasn’t changed much in twenty years to get rid of any foolish overflows or use-after-free bugs is perfect for it.

      Using Rust for exploratory coding, or when the requirements keep changing? I think you’ve picked the wrong tool for the job. Invalidate a major assumption and have to rewrite the whole damn thing. And like you say; an important choice for big projects as choosing a tool that a lot of people will be able to use. And Window is very big.

      They’re smoking crack, anyway. A million lines per dev per month? When I’m doing major refactoring, a couple thousand lines per week in the same language, mostly moving existing stuff into a new home, is a substantial change. Three orders of magnitude more with a major language conversion? Get out of here.

    • leftzero@lemmy.dbzer0.com
      link
      fedilink
      arrow-up
      6
      ·
      5 days ago

      The rust part, if done well, would be a good step.

      We’re talking machine translating the whole codebase from c to rust like one would translate a book from one language to another, here (i.e., without the machine actually understanding a single word, much less long groups of them).

      The result will basically be something like this:

      unsafe {
       //insert the entire codebase here,
       //mangled beyond recognition
      }
      
      • reabsorbthelight@lemmy.world
        link
        fedilink
        arrow-up
        2
        ·
        5 days ago

        They should honestly just wrapper the majority of the code base in rust unsafes and then slowly very slowly migrate sections of the code to rust. This is the right way to do it imo

        Will they do that? Nope.

    • UnfortunateShort@lemmy.world
      link
      fedilink
      English
      arrow-up
      7
      arrow-down
      1
      ·
      6 days ago

      I mean, Rust has the massive upsite that it won’t compile in many cases if you fuck things up. Then again, embedded or generally low-level driver-y stuff is still in its infancy in Rust. Relative to C/C++ that is.

      There is stuff that you need that has no official Rust support. There is poor documentation and half baked frameworks. There are examples being silently outdated, breaking changes between framework versions, and nighlty-versions from Github mixed in to fix them. And then of course plenty of timing and hardware dependent things you will need to do yourself.

      I do this for a living and personally tried to use AI here and there to help me out, but oftentimes it fails miserably. Not always, but very often.

      • MashedTech@lemmy.world
        link
        fedilink
        arrow-up
        11
        ·
        6 days ago

        Rust helps you resolve memory bugs. Not logic bugs. Yeah, it’s going to be new memory safe code… But it won’t be bugfree code.

          • MashedTech@lemmy.world
            link
            fedilink
            arrow-up
            3
            ·
            5 days ago

            Oh wait… It’s AI. Just to pass the compiler and the unit tests it will either cast to whatever it desires or just make the tests pass forcefully.

        • The_Decryptor@aussie.zone
          link
          fedilink
          English
          arrow-up
          2
          ·
          5 days ago

          It can help with logic bugs (e.g. by encoding the state machine logic directly in the type system, so an invalid transition won’t compile), and things like data sharing issues (Again, type system, tracks sharable objects vs. those that aren’t), but none of those are as “impervious” as the memory safety stuff.

          But that all still requires rearchitecting, because if the existing code already follows those rules, it already probably doesn’t suffer from those issues (e.g. I know you can do the state machine type stuff in C# at least)

  • Avicenna@programming.dev
    link
    fedilink
    arrow-up
    11
    ·
    edit-2
    6 days ago

    this seems like a research project rather than a main line policy change:

    "Just to clarify… Windows is NOT being rewritten in Rust with AI.

    My team’s project is a research project. We are building tech to make migration from language to language possible."

    Ofcourse the end goal remains the same: try to produce systems that can be maintained by a significantly reduced number of programmers/software engineers, which can only work if AGI was actually achieved in near future so that the senior coder gap produced by this approach can be filled by AGI coders. If not, I think we will enter an era of tech where first software engineering will first become highly undesirable (due to reduced number of entry level jobs) and then achieve a god-like status because there are not enough senior software engineers to support all the tech infrastructure build on AI coding agents which are not fully autonomous because they lack/can’t learn critical reasoning skills/software experience unlike entry level coders which can.

  • Aleko Treko@lemmygrad.ml
    link
    fedilink
    arrow-up
    2
    ·
    5 days ago

    Glad I bailed out from Microshit when they announced the EoL of Win10. I’d rather be a hobo than to use the un-operating system called Win11.