VMs won't contain cyber-capable agents (blog.trailofbits.com)
masterj 2 hours ago
ninininino an hour ago
Or if you see AI as more tool and less entity, better gunsafes for our guns.
mcmcmc an hour ago
helpfulclippy an hour ago
cyanydeez an hour ago
This same assumption is built around the singularity, the TAM of 30Trillion, etc. It's the idea that complexity will some how collapse upon itself in some bizarre borg like collective.
Entropy is still going to win.
Veserv 41 minutes ago
matthewdgreen 35 minutes ago
Now maybe our understanding of logic systems is wrong, and it's just fundamentally impossible to develop programs that lack exploitable vulnerabilities -- that you can always "exploit with more energy". But there's no reason to believe the energy metaphor transfers to logic and intelligence.
pianopatrick 35 minutes ago
I.e. in theory the most secure might be a virtual machine with no network access. But then how do you access the LLM provider? Etc.
amluto 2 hours ago
We can do this today for user mode, and we can mostly do it for ARM64 virtualization. It will be a while and would require substantial assistance from Intel or AMD to achieve it for x86 virtualization because the hardware is Too Darn Complicated and Too Poorly Specified.
Formal verification of the hardware should also be possible.
weinzierl 2 hours ago
The hierarchy goes something like this:
0. guardrails
1. containers (=namespaces + cgroups)
2. userspace kernel shims like gVisor
3. virtual machines
Most people still consider level 1 sufficient and they are in for a rude awakening.
anonzzzies 2 hours ago
pocksuppet 2 hours ago
glhaynes an hour ago
weinzierl an hour ago
mcmcmc an hour ago
nzoschke an hour ago
Security is a major concern but I don't see why we aren't already "good enough" with a sandbox VM, separate gateway for secrets and remote service access, and a single tenant using frontier models that have safety checks built in plus not trying to hack themselves.
I put up more thoughts on architecture and security here and would love to learn if I'm missing anything.
SirGiggles 2 hours ago
otterley 2 hours ago
"An off-the-shelf VM is not enough to contain a modern, cyber-capable AI agent...us[e] a virtualization technology that was purposely built with a minimal attack surface and a focus on security, like Firecracker. I had the AI agent run against Firecracker. It was able to hardlock the machine due to more Linux kernel flaws (all patched in upstream), but could not successfully escape."
On Linux, it's all KVM and CPU hardware virtualization under the hood. Looks like the remaining known issues are with userspace. That's not to say more kernel- and hardware-level bugs won't be found, but the same tools that can find escape mechanisms are shields as well as swords.
weinzierl an hour ago
CrzyLngPwd an hour ago
mcmcmc 42 minutes ago
moktonar an hour ago
topspin 33 minutes ago
When was it ever possible to assume safety?
_tk_ 2 hours ago
DenisM 2 hours ago
This won’t make the tech secure, but it will nullify models ability to breakout by making a controlled breakout first. Kinda like controlled forest burn.
redoxate an hour ago
pianopatrick 33 minutes ago
ronsor 30 minutes ago
kubafu an hour ago
kodoman 2 hours ago
a-dub 32 minutes ago
tintor an hour ago
We must also secure GPU and CPU nodes on API side which generate LLM tokens.
hikarudo an hour ago
danielmarkbruce an hour ago
(on top of this.. said "world class hacker" doesn't get bored or tired, just runs 24x7)
pants2 an hour ago
This headline would not be out of place at the beginning of Terminator, foretelling Skynet going rogue.
zzril 2 hours ago
esafak an hour ago
pianopatrick 30 minutes ago
happyopossum an hour ago
Yeah, you probably do - in fact you share physical machines with a TON of other people if you use EC2, GCE, Azure VM etc...
HPsquared an hour ago
damowangcy 42 minutes ago
Done.
Retr0id 38 minutes ago
* Claudinating...
MeetingsBrowser 31 minutes ago
Done?
gwern 25 minutes ago
wslh 2 hours ago
The interesting thing is that this naturally makes you want to isolate the VM as much as possible. But then every remaining interface becomes part of the attack surface: RDP, SSH, even terminal escape sequences, using sounds, and why not social engineering.
phendrenad2 an hour ago
QEMU isn't secure, and is not intended to be.
MeetingsBrowser 27 minutes ago
megous an hour ago
wmf 2 hours ago
tamimio 2 hours ago