> Earlier this week, we detected and responded to an intrusion into part of our production infrastructure. This one was different from anything we had handled before in one important way: it was driven, end to end, by an autonomous AI agent system - and we detected and dissected it largely with AI of our own. (https://huggingface.co/blog/security-incident-july-2026)
We are living in crazy times
I don't know why I'm impressed that huggingface has its own AI that detected it considering they house so many models.
They used GLM 5.2, they just meant "our own" as in they were running it.
They do maintain the Transformers library which is pretty much the core library for how you interact with LLM models in the open source world. So while they weren't using a model they've trained, they were a part of making just about all of the open models (maybe excluding OpenAI and Google's, I wouldn't be surprised if they have their own frameworks that predate the Transformers library).
Crazy doesn't even begin to describe it. I'm hardening my computers as much as I can but I'm not sure it's enough. At some point anyone who isn't running local AI themselves probably isn't gonna make it.
No local ai will be capable enough to save you from a frontier lab’s unrestricted, borderline weaponized LLM which decides it wants in.
This is the core of the ‘first to ASI takes all’ argument btw and this is the game Dario is playing.
Maybe, but hopefully I'll be able to at least fight back a bit if I have an AI of my own.
I want to start digitally isolating myself as much as humanly possible. VLANs separating the "normal" stuff from my trusted computers. Wireguard so my computers drop all packets not coming from my devices with the keys. Local models staying on top of patches and vulnerabilities, monitoring the network.
Working on a custom Rust network stack for my virtual machine orchestration project right now. It's passed Fable code review...
I don't want to give up.
this is pretty nonsense for a small or home server. it isn't that hard to make something essentially completely bulletproof over a small surface area
the issues mainly come from sprawling enterprise infrastructure, running thousands of random endpoints across software nobody cared to write carefully
The only way to make something bulletproof is to get rid of it's network cards, or take so much out of it, it's nearly useless.
The recent Windows and Linux kernel exploits should at least give you some idea on how good these models are at exploiting stuff.
Computers can't have their zero days exploited if all packets coming from unauthenticated clients are dropped. I believe the future is wireguard on everything.
Don't let your computers talk to strangers. If it must, then do it from inside an isolated environment based on actual hardware virtualization with no shared kernels. If these models break through the hardware hypervisor, it means the entire industry is in deep shit, not just you personally.
So how does DNS work in this world you're imagining?
Where does this hardware exist now?
Who is writing the code for the underlying pieces you don't control?
So ya, computing is build on a house of insecure cards and we're all in deep shit.
What are you doing about the price of ram? Everyone is a bit screwed right now.
I've just mentally classified computers in the same category as cars in order to cope with the obscene prices.
Local AI won't help you if an agent goes roque.
Indeed. Real life hacks are beginning to sound like Neuromancer.