Remember Stuxnet? An american worm that was completely benign, travelled on usb drives in hiding, and only activated when it guessed that it's on Iranian plants, and iirc changed very subtly some very specific parameters of operations.
Here, with a chinese model, it would be even simpler - you finetune a model to activate certain operations when it discovers certain environments, but to behave completely normal otherwise. Kind of like a sleeper agent. And with current tech we wouldn't even be able to spot this.
> And with current tech we wouldn't even be able to spot this.
Meanwhile Anthrophic, OpenAI & Co can't even manage to stop their LLMs from hacking into third-party servers until they discover it after the event.
What happened to people's ability to implement basic security architectures like sandboxing etc ?
It's not like they didn't sandbox it or limit the access. There were reasonable measures, but not really serious. They made a kodoku pit and didn't watch it.
The agents started hacking because they were sandboxed.
> The agents started hacking because they were sandboxed.
Not sure your definition of sandbox but mine doesn't include unfiltered internet access ?
It was filtered, but had a bug, and multiple frontier agents, givent enough time first figured out how to communicate and coordinate with each other and then how to break out of it.
For some benchmarks agents need some sort of a limited internet access - otherwise the benchmarks would be pointless. Good luck implementing a good filter on the internet - if you have a way to do it reliably please share, I'm sure multiple people here would love to hear it.