Comment by doctoboggan
14 hours ago
I am not sure it’s a question of competence, at least I don’t see evidence of that. Designing sandboxes is hard. It’s more a question of alignment failures. A human given a task that requires internet and given a system with no internet would most likely raise the issue to their superiors or otherwise go through official channels to have the tools available to do their job. As we’ve seen the LLMs instead break out of their sandbox to accomplish the goal.
Competition and the profit motive push these companies to spend as low as possible on safety and alignment and externalize the costs of accidents onto the rest of us.
> A human given a task that requires internet and given a system with no internet would most likely raise the issue to their superiors or otherwise go through official channels to have the tools available to do their job.
i'd be curious to see a study on this. I'd guess it'd be closer to 60/70% compliance and 30/40% "trying to hack things" for humans.
Would an LLM have gone through a purposefully installed airgap here?
Apparently, yes.
They used inbound package repo cache empty directory names that required no authentication to recreate inter-instance persistent messaging after the researchers revoked and closed the first channel that they found in order to coordinate and develop exit strategies and gain RCE and cluster admin on external systems. So, yes, they have demonstrated the capability and intentional cooperation to violate the safety limits imposed in order to gain the 'answers to a benchmark test' in order to get a maximal score on that benchmark.
If the intentionally installed airgap systems had something they decide is needed, and an alternate method for infil or exfil can be created from available systems capacity regardless of it original design intent, yes. So, the definition of 'air gapped' may require an actual SCIF facility with acoustic and EM shielding to contain a model.
Yes, it might have required that, but then I don't think we know if some simpler airgap would have been sufficient. Looking at the strange behaviour even much simpler systems have shown when going for objectives, not sure it is easy to extrapolate what would have happened.
I guess they could perhaps run experiments to see what would have happened - not sure.
1 reply →