I personally find "rogue" to be a marketing stunt, as agents do not have intent the way we do. In these cases, they were given instructions to hack, e.g.. ExploitGym
Humans not staying in the loop when doing evals like ExploitGym are engaged in gross negligence. There are some people saying we should use our existing laws today for the HF et al incidents and hold some humans liable
Probably most of it. Have "AIs" invented new techniques, or are they just applying techniques humans invented? It's the latter.
Remember that first time you heard about speculative execution attacks (Spectre)? That was something new, something unheard of. If an "AI" is going rogue, something previously unheard of would show up. Otherwise, they're just doing what patterns are in their training data, and doing a lot of it. And, it's a human telling them to do so.
A swarm of AI agents that knows what humans know about hacking but can do it far faster... that's still a formidable attacker. Not novel. Not "escaping". But formidable.
"Escaping" would be using the attack to install a copy of itself somewhere. But we've seen that before, too, with viruses and worms. And if it has to install an 8 GB image to install a copy of itself, it's not going to be the stealthiest of worms...
Well, since all I've seen is publicity, I'd have to say 100%.
I personally find "rogue" to be a marketing stunt, as agents do not have intent the way we do. In these cases, they were given instructions to hack, e.g.. ExploitGym
Humans not staying in the loop when doing evals like ExploitGym are engaged in gross negligence. There are some people saying we should use our existing laws today for the HF et al incidents and hold some humans liable
Probably most of it. Have "AIs" invented new techniques, or are they just applying techniques humans invented? It's the latter.
Remember that first time you heard about speculative execution attacks (Spectre)? That was something new, something unheard of. If an "AI" is going rogue, something previously unheard of would show up. Otherwise, they're just doing what patterns are in their training data, and doing a lot of it. And, it's a human telling them to do so.
A swarm of AI agents that knows what humans know about hacking but can do it far faster... that's still a formidable attacker. Not novel. Not "escaping". But formidable.
"Escaping" would be using the attack to install a copy of itself somewhere. But we've seen that before, too, with viruses and worms. And if it has to install an 8 GB image to install a copy of itself, it's not going to be the stealthiest of worms...