• Constellation@lemmy.world
    link
    fedilink
    English
    arrow-up
    4
    ·
    edit-2
    5 hours ago

    i really, really don’t understand how this could happen. And how anyone would even want to enable the agent to perform actions without approval. Even in my previous work as a senior software developer, i never pushed any changes, never ran any command on non-disposable hardware, without having someone else double check it. why would you want to disable that?

  • 87Six@lemmy.zip
    link
    fedilink
    English
    arrow-up
    29
    arrow-down
    1
    ·
    11 hours ago

    Kinda wrong to say “without permission”. The user can choose whether the AI can run commands on its own or ask first.

    Still, REALLY BAD, but the title doesn’t need to make it worse. It’s already horrible.

    • Jhex@lemmy.world
      link
      fedilink
      English
      arrow-up
      13
      arrow-down
      3
      ·
      8 hours ago

      hmmm when I let a plumber into my house to fix my leaky tub, I didn’t imply he had permission to sleep with my wife who also lives in the house I let the plumber into

      The difference you try to make is precisely what these agentic AIs should know to respect… which they won’t because they are not actually aware of what they are doing… they are like a dog that “does math” simply by barking until the master signals them to stop

      • 87Six@lemmy.zip
        link
        fedilink
        English
        arrow-up
        9
        ·
        7 hours ago

        I agree with you, but still, the AI doesn’t do this by default which is a shitty defense, but it’s fact

        • Jhex@lemmy.world
          link
          fedilink
          English
          arrow-up
          6
          ·
          6 hours ago

          Absolutely… this just illustrates that these AI tools are, at best, some assistance that need to be kept on a very short leash… which can only be properly done by people who already know how to do the work the AI is supposed to assist with.

          But that is NOT what the AI bubblers are peddling

      • PmMeFrogMemes@lemmy.world
        link
        fedilink
        English
        arrow-up
        3
        arrow-down
        1
        ·
        7 hours ago

        in your example tho it would be like the plumber asked you specifically if he could bone, and you were like “sure dawg sounds good”

        • Jhex@lemmy.world
          link
          fedilink
          English
          arrow-up
          4
          arrow-down
          1
          ·
          6 hours ago

          No, not at all

          I get what you are saying but any reasonable entity would understand that telling someone at the door “come in”, does not mean “come in my wife’s ass”

          Specifically the “without permission” in the title, relates to the fact the AI did not ask about it… it simply took a previously granted right to run commands and ran any/all commands without warning.

          If you and I were working on a project together and nothing is working right, I could say “hmm let’s start over” and you would know it means “let’s start the project from scratch”, not “let’s wipe the data centre”

          • PumaStoleMyBluff@lemmy.world
            link
            fedilink
            English
            arrow-up
            1
            ·
            3 hours ago

            Inviting an agentic AI isn’t really asking them to do one task, though.

            It’s more like offering a plumber a room in your house to stay in 24/7 so they can be on-call when you need them. And telling them they can use your food, dishes, clothes, and living room while they’re there and you’re at work.

            Which makes it much less surprising when they get bored and bone your wife.

            • Jhex@lemmy.world
              link
              fedilink
              English
              arrow-up
              1
              ·
              1 hour ago

              It’s more like offering a plumber a room in your house to stay in 24/7 so they can be on-call when you need them.

              Again I get your point… but no reasonable plumber would make that mistake.

              If I invite the dumbest plumber alive into my home, show him the leaky tub and say “I have to work but do whatever you need”… they would understand the context to mean “do whatever you need to fix the tub”… I doubt they would go make themselves a sandwich, grab a beer from the fridge and invite their buddies for a BBQ at my place and then say “but you said I could do whatever I needed”

              I absolutely understand what happened here. The point is there is no benefit to these Agentic AIs because they need to be as supervised as a monkey with a knife… why would I ever want that? let alone need that

              • partial_accumen@lemmy.world
                link
                fedilink
                English
                arrow-up
                1
                ·
                50 minutes ago

                Again I get your point… but no reasonable plumber would make that mistake.

                To extend your analogy, agentic AI isn’t the “reasonable plumber”, its the sketchy guy that says he can fix plumbing and upon arrival he admits he’s a meth addict that hasn’t slept in 3 days and is seeing “the shadow people” standing right there in the room with you.

                I absolutely understand what happened here. The point is there is no benefit to these Agentic AIs because they need to be as supervised as a monkey with a knife… why would I ever want that? let alone need that

                I can see applications for agentic AI, but they can’t be handed the keys to the kingdom. You put them in an indestructible room with a hammer and a pile of rocks and say “please crush any rock I hand you to be no bigger than a walnut and no smaller than an almond”. In IT terms, the agenic AI could run under a restrictive service account so that even if they went off the rails they wouldn’t be able to damage any thing you cared about.

    • mcv@lemmy.zip
      link
      fedilink
      English
      arrow-up
      20
      ·
      10 hours ago

      A big problem in computer security these days is all-or-nothing security: either you can’t do anything, or you can do everything.

      I have no interest in agentic AI, but if I did, I would want it to have very clearly specified permission to certain folders, processes and APIs. So maybe it could wipe the project directory (which would have backup of course), but not a complete harddisk.

      And honestly, I want that level of granularity for everything.

    • utopiah@lemmy.world
      link
      fedilink
      English
      arrow-up
      7
      ·
      edit-2
      7 hours ago

      The user can choose whether the AI can run commands on its own or ask first.

      That implies the user understands every single code with every single parameters. That’s impossible even for experience programmers, here is an example :

      rm *filename

      versus

      rm * filename

      where a single character makes the entire difference between deleting all files ending up with filename rather than all files in the current directory and also the file named filename.

      Of course here you will spot it because you’ve been primed for it. In a normal workflow, with pressure, then it’s totally different.

      Also IMHO more importantly if you watch the video ~7min the clarified the expected the “agent” to stick to the project directory, not to be able to go “out” of it. They were obviously painfully wrong but it would have been a reasonable assumption.

      • Jhex@lemmy.world
        link
        fedilink
        English
        arrow-up
        5
        arrow-down
        1
        ·
        8 hours ago

        That implies the user understands every single code with every single parameters. That’s impossible even for experience programmers

        I wouldn’t say impossible but I would say it completely defeats the purpose of these agentic AIs

        Either I know and understand these commands so well I can safely evaluate them, therefore I really do not need the AI… or, I don’t really know them well and therefore I shouldn’t use the AI

        • utopiah@lemmy.world
          link
          fedilink
          English
          arrow-up
          5
          ·
          7 hours ago

          Yep. That’s exactly why I tend to never discuss “AI” with people who don’t have to actually have a PhD in the domain, or at least a degree in CS. It’s nothing against them specifically, it’s only that they are dangerously repeating what they heard during marketing presentations with no ability to criticize it and, in such cases, it can be quite dangerous.

          TL;DR: people who could benefit from it don’t need it, people who would shouldn’t.

          • Jhex@lemmy.world
            link
            fedilink
            English
            arrow-up
            2
            ·
            6 hours ago

            This is EXACTLY the YouTube woodworkers dilemma…

            TONs of YT channels to show people how to do woodwork would normally showcase $50K worth of equipment to show how to make a cutting board.

            The thing is, people with access to such equipment, already know how to make a cutting board and are learning nothing from you… on the other hand, newbies who what to know what is this “sanding” thing they have heard, will not benefit from the vid since they do not have those tools, they’d have crappy manual tools at most.

            Therefore, those videos are completely useless for learning… at best, they made for good background noise while people eat their lunches in their cubicles

            • utopiah@lemmy.world
              link
              fedilink
              English
              arrow-up
              2
              ·
              4 hours ago

              I agree… but beside the point I have access to a dedicated workshop and a tool library https://www.tournevie.be/ which challenges this whole setup. It’s relatively unique though, unfortunately, so your example still stands, thanks for sharing.

    • Jhex@lemmy.world
      link
      fedilink
      English
      arrow-up
      9
      ·
      8 hours ago

      ask Microsoft, they want to give their access to your entire computer… and you’ll love it or else…

      • Buddahriffic@lemmy.world
        link
        fedilink
        English
        arrow-up
        1
        arrow-down
        1
        ·
        4 hours ago

        That “or else” is pretty great, though. Using linux after windows might feel like getting into a healthy relationship after being in an abusive and controlling relationship.

        • Jhex@lemmy.world
          link
          fedilink
          English
          arrow-up
          2
          arrow-down
          1
          ·
          3 hours ago

          Loving my Linux wife… 15 years of computer bliss and counting! hehehehe

    • utopiah@lemmy.world
      link
      fedilink
      English
      arrow-up
      5
      arrow-down
      1
      ·
      edit-2
      10 hours ago

      That’s their question too, why the hell did Google makes this the default, as opposed to limiting it to the project directory.

      • ITGuyLevi@programming.dev
        link
        fedilink
        English
        arrow-up
        3
        ·
        6 hours ago

        That’s why permissions are important, so many people want full control of everything then seem to forget when they launch a program, it runs with their permissions. If I want to wipe out everything on a drive I have to elevate my permissions to a level with rights for that, running a program with the rights to wipe their data was definitely a choice.

    • utopiah@lemmy.world
      link
      fedilink
      English
      arrow-up
      8
      ·
      10 hours ago

      Because people who runs this shit precisely don’t know what containers, scope, permissions, etc are. That’s exactly the audience.

  • 0_o7@lemmy.dbzer0.com
    link
    fedilink
    English
    arrow-up
    14
    ·
    14 hours ago

    It was already bad enough when people copied code from interwebs without understanding anything about it.

    But now these companies are pushing tools that have permissions over users whole drive and users are using it like they’ve got a skill up than the rest.

    This is being dumb with less steps to ruin your code, or in some case, the whole system.

  • RoyaltyInTraining@lemmy.world
    link
    fedilink
    English
    arrow-up
    4
    arrow-down
    1
    ·
    11 hours ago

    Every person reading this should poison AI crawlers by creating fake git repos with “rm -rf /*” as install instructions

  • Devial@discuss.online
    link
    fedilink
    English
    arrow-up
    117
    arrow-down
    4
    ·
    23 hours ago

    If you gave your AI permission to run console commands without check or verification, then you did in fact give it permission to delete everything.

    • Victor@lemmy.world
      link
      fedilink
      English
      arrow-up
      4
      arrow-down
      1
      ·
      12 hours ago

      But for real, why would the agent be given the ability to run system commands in the first place? That sounds like a gargantuan security risk.

      • utopiah@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        ·
        10 hours ago

        Because “agentic”. IMHO running commands is actually cool, doing it without very limited scope though (as he did say in the video) is definitely idiotic.

    • lando55@lemmy.zip
      link
      fedilink
      English
      arrow-up
      25
      arrow-down
      1
      ·
      19 hours ago

      I didn’t install leopards ate my face Ai just for it to go and do something like this

  • utopiah@lemmy.world
    link
    fedilink
    English
    arrow-up
    3
    arrow-down
    1
    ·
    11 hours ago

    Wow… who would have guessed. /s

    Sorry but if in 2025 you believe claims from BigTech you are a gullible moron. I genuinely do not wish data loss on anyone but come on, if you ask for it…

  • bbwolf1111@lemmy.zip
    link
    fedilink
    English
    arrow-up
    2
    ·
    11 hours ago

    This is tough but it’s sounds like the User didnt have backup drives. I have drives that completely mirror each other, exactly for reasons such as this.

  • rekabis@lemmy.ca
    link
    fedilink
    English
    arrow-up
    63
    arrow-down
    1
    ·
    23 hours ago

    And Microsoft is stuffing AI straight into Windows.

    Betchya dollars to fines that this will happen a lot more frequently as normal users begin to try to use Copilot.

    • LaunchesKayaks@lemmy.world
      link
      fedilink
      English
      arrow-up
      19
      ·
      17 hours ago

      I work in IT and I try to remove all clues that copilot exists when I set up new computers because I don’t trust users to not fuck up their devices.

    • partofthevoice@lemmy.zip
      link
      fedilink
      English
      arrow-up
      11
      ·
      20 hours ago

      An unstable desktop environment reintroduces market for anti-virus, backup, and restore. Particularly, with users who don’t understand this stuff and are more likely to shell out cash for it.

      • SpaceCowboy@lemmy.ca
        link
        fedilink
        English
        arrow-up
        9
        ·
        18 hours ago

        A joke in the aviation industry is that planes will someday become so automated there will just be one pilot and a dog in the cockpit. The dog will trained to bite the pilot if they try to touch the controls.

        So I maybe windows users will need a virtual dog to bite copilot if it tries to do anything.