657
Google's Agentic AI wipes user's entire HDD without permission in catastrophic failure
(www.tomshardware.com)
this post was submitted on 03 Dec 2025
657 points (98.1% liked)
Technology
77090 readers
3541 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
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.
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.
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
I agree with you, but still, the AI doesn't do this by default which is a shitty defense, but it's fact
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
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"
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"
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.
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
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 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.
hahahaha good additional details on the analogy
I mean, it's not even that. Your dog at least can learn and has limited reasoning capabilities. Your dog will know when it fucks up. AI doesn't do any of that because it's not really "intelligent."
🥱
That implies the user understands every single code with every single parameters. That's impossible even for experience programmers, here is an example :
rm *filenameversus
rm * filenamewhere a single character makes the entire difference between deleting all files ending up with
filenamerather than all files in the current directory and also the file namedfilename.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.
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
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.
100% agree with that tldr
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
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.