What kind of logic is this? It's standard in the Linux world to give important services a separate user domain.

The standard here is not enough when the agent can escalate by finding 0 days, for example. It’s like giving a black hat a limited account. Sure it might restrict him, but not giving him an account at all is way better

The black hat can find 0-day escalation in your sandbox, too.

A user account is a sandbox.

Not as air tight as a container

Edit: it’s about the attack surface

microvms are better than containers running on your host. see eg the "smolvm" microvms from https://smolmachines.com

thanks, will take a closer look

Unix users are THE tool to restrict tool permissions, at any given time there's 20+ services on a Unix machine that run in their user.

And how many of those services can check your box and find permission escalation strategies on its own?

Malware has been bundling rootkits for decades, so potentially all of them. Sometimes the attacks succeed, so these are defenses that need continual hardening, but there's no sense in setting up an entirely separate line of defense just because this time the threat has AI in it.

I guess time will tell, I know I'm not giving those things any direct stdin access without a hole suite of safeguards in between

Same reason people give postgres, php, or any other program a user account.

Why should it be? We have containers and capabilities…

Containers are often used with user namespaces, which is literally another (set of) user account(s).

Yes but the encompassing service has the account, not the agent. You can completely segregate it from the rest of the system, like you’d treat an intruder

i give a lot of software dedicated user accounts, it's literally one of the core security models of the operating system

But none of these services have the kind of latent capabilities an agent has, you know a deterministic service’s constraint are its code+bugs. There are no such constraints in an agent…

...this is a completely normal thing to do in linux, it's the most basic form of access control. There's like a dozen non-human accounts in a clean install before adding your own like this, and a lot of software adds their own. Edit: I have 54 entries on my personal laptop, just one of which is actually me.

This model is already not perfect, and not at all built for agents. The only way to secure an agent is an air-gap with the execution layer. Treat it like text, and the problem never arises until you “interpret” the agent output in a more limited environment than the OS

Even though it’s completely normal to us and in widespread use, GP is a reminder that conceptually it’s a broken model. Security should be capability-based not user-based. And to anyone who didn’t grow up on a desktop this model makes complete sense since it’s what your phone uses.

Android uses one uid per app.

Yes, it was a step in the right direction at the time. But there are plenty of well-documented warts with the approach which Fuchsia aimed to solve via capabilities (and which the Linux community general solved via crun).

He said it’s less than a software, so saying software does this too isn’t really a strong counter argument. In case, I don’t think you are really in disagreement. Restricted accounts are necessary is your point, but I think op is saying they aren’t sufficient.

One of the default users is "nobody" which isn't associated with any software. It's definitely above that.

Is it less secure if I simply have nothing to do with language models whatsoever? I take that to be the parents point, but I know you are correct and yes, user restrictions should be a necessary part of the way people who use LLMs setup their system to use them in a safe manner.

/etc/shadow has the good stuff if you're OS is current.

Congratulations! You are this thread’s winner of the UUOC award!