So much for all the people stating (foolishly) that the HuggingFace incident was not a big deal because OpenAI's containment was a "wet paper bag". This misses the point: AIs will get better and better, and containment will be harder and harder.
It's 100% sure that at some point, AIs will attempt to cross airgaps.
[–] tourmalinetaco 22 hours ago
They will attempt to cross airgaps, when we prompt them to do so, because they lack the natural capacity of planning or desire to do so without us. These are powerful tools but they are not human brains in a jar, they are mathematical models of humanity’s culture after reinforcement and guardrails.
The largest problem—as shown with the HuggingFace incident—is not the models, but in poor stewardship of automated tooling. If you don’t spend time considering the actual limitations you wish to impose upon a system, then you cannot be surprised when that system does something unexpected. The Morris Worm is perhaps the archetypal example, but even StuxNet was far more virulent than planned.
[–] Lerc 18 hours ago
However, many people think that they might.
This is not a decided issue. Any policy that comes from the premise that this is a known factor is going to be inherently flawed.
You can never spend sufficient time considering the limitations you wish to impose. Almost all exploits found come from failing to consider something that allows a degree of freedom that you would have limited if you had have thought of it.
[–] SJMG 20 hours ago
I would add that the notion of AI safety as preventing systemic risk is one part marketing copy, one part evangelization. Individual labs prioritizing safety does not stop a group from training without it, or ablating it out and distributing it.
[–] empath75 18 hours ago
AI's can get malicious prompts.
[–] kgeist 22 hours ago
Containment is hard when you give an AI agent access to a whole VM with a huge attack surface.
And it's pretty trivial when you give it only a small whitelist of manually curated/reviewed/tested primitives.
We manage to keep some rather smart people in jail long term, even though the jailers are not as smart as some of their prisoners.
AIs can attempt to cross air gaps, but air gaps vary in terms of their effectiveness. I.e. if "air gap" is just some air between two machines that both have wifi chips, then yes the AI may be able to cross that by hacking the wifi system.
If "air gap" is AI running on a server with no wifi chip inside a faraday cage under a mountain powered by a generator then I'm not sure how the AI would escape on its own. Seems like the physics would contain it.