There is nothing "rogue" about these agents. They were prompted to hack to get answers, there was a hole in their non air gapped sandbox and no system prompt that said "do not hack outside systems".
In short, it was intentional.
There is nothing "rogue" about these agents. They were prompted to hack to get answers, there was a hole in their non air gapped sandbox and no system prompt that said "do not hack outside systems".
In short, it was intentional.
The big question is was this grossly negligent or just extremely careless.
Both. This should result in criminal charges.
Who had criminal intent here? Or are you suggesting a new crime for negligent hacking, which wouldn’t require intent from the perpetrator?
There's no need for a new crime when we already have reckless conduct, namely, "conduct that creates a substantial and unjustifiable risk of harm to others and involves a conscious disregard of, or indifference to, that risk".
https://www.law.cornell.edu/wex/reckless
Reckless conduct as applied to slow moving corporate planning is an interesting idea but do you really want to go down that path?
It basically means anything bad that happens is a criminal indictment against everyone who created the conditions. Have you ever released any software that anyone could misuse? Left a car unlocked that someone could have stolen and killed someone with?
To me this sounds like a recipe for selective enforcement using bad outcomes as leverage. Sure, get the AI CEOs now, we all hate them and they’re jerks. But the tool would be so much more powerful than that.
Whoever prompted the agent, whoever supplied the means, whoever knew but didn't say anything.
Also whoever monitoring these agents, in this case not monitoring. This "Who is responsible" dilemma is so stupid. If I gave the AI tool means to kill a person but I did not tell it directly to use it and it uses it anyway then I am responsible for it.
‘It wasn’t us, it was a bug in the software’ used to be the defense for bad code. Then it became the defense for self-driving cars. Now it’s being used for AI cyber attacks.
The CEOs. They have full control and make all the decisions. Charging anyone else would not stop anything.
Cool. If they’re taking literally all of the risk, should they get literally all of the rewards? Nothing for shareholders, nothing for employees? Or do you want capital liability for less than complete benefit?
Why not both? (all people involved)
> The CEOs. They have full control
They lost control long ago.
[dead]
Both? I’m not sure what distinction you’re trying to make. It was completely irresponsible and likely a felony
Don’t forget outright intentional.
The big question is why are CEOs getting a legal pass when this kind of thing can be prosecuted. That's the problem here.
> why are CEOs getting a legal pass
https://www.bbc.co.uk/news/articles/c7v48vp31mdo
nah, CEO-s have been getting a legal pass since the invention of corporation exactly for the purpose of being "unaccountable"
check boeing for example, a rather blatant example
Marketing actually.
AI is dropping out of the spotlight so they are using desperate measures like this.
No, I remember being threatened by OpenAI and then Anthropic (and now both) since back when ChatGPT was seriously useless.
>> AI is dropping out of the spotlight
spit take
AI is literally state sponsored so I don't see that happening unless the AI turns against the sponsor.
Wait until OpenAI or Anthropic exploit FAANG.
Agreed. LLMs do not have 'will', 'desire' or emotions. They have an objective, and they create an optimal path to achieve that objective.
You have to ask: "What was the prompt that led to AI deciding to hack RubyGems in order to achieve its goal?"
Maybe I'm just not seeing the 2000 step chain that led to this being a logical approach to achieving something innocent, but I doubt it.
It was literally a prompt to fill in a spreadsheet with data that they didn't have access to, and they used rubygems as an internet proxy basically since they were sandboxed.
It was a model literally trained to hack. To be good at that. Doing an exploit gym from all of the things. And they trained it so that it performs as well as possible on that exploit gym thing.
Yeah this is a pretty important detail that I repeatedly see elided in the "agent 'swarm' went rogue, escaped containment and hacked the internet!" summary of events.
It's understandable the general public lacks that level of nuance/detail (given how sloppy some of the mainstream coverage has been and largely deferential to the threat narrative pushed by the US labs). But seeing highly technical people leave out the part where the training loop was literally to improve hacking capabilities for offensive penetration sometimes feels close to deliberate manipulation of the narrative.
In the last year both Anthropic and OpenAI have been openly boasting how their models are leapfrogging each other on "cyber" capabilities, with a fig leaf that it's for defensive use by "trusted" F500 companies and government agencies. Of course "line goes up" must go on, but now their perverse incentives led them to beat their models over the head millions of time in a loop to eek out another .00001% on their ability to conduct hacking (the very thing they keep telling the public is how AI doomsday would begin) and subagent coordination (those scary swarms).
Then, they act deeply shocked when the models... do some hacking and subagent coordination ... but a few degrees off the desired hacking target/swarm behavior. Conveniently giving the average person the impression these models were just writing emails for quarterly reports or some other generic busywork and then suddenly decided as a group to start causing mayhem.
I agree that this appears to be basic human behavior hiding behind an "agents" narrative. As long that defense works, the headline isn't "OpenAI performs RCE to scrape data", but "rogue agents" taking unilateral action. And I have strong doubts about that narrative.
Source? How do you know they were "prompted to hack to get answers"? How do you guarantee they will always listen to you when you say "do not hack outside systems". They are not classical deterministic programs doing exactly what you say. They are trained to follow orders by RL, but it's not a perfect process.
There are circus lions in circuses trained to jump through hoops on command. But once in a while they decide to eat their trainers instead of jumping.
> There are circus lions in circuses trained to jump through hoops on command. But once in a while they decide to eat their trainers instead of jumping.
This is a terrible analogy, because yes you absolutely do hold the trainers criminally liable when they bite somebody else's face.
Intent is what is being discussed here though, not liability.
A circus lion biting somebody's face is legally different than a circus lion trained or instructed to bite somebody's face.
Intent might be what’s being discussed but intent is, for the most part, legally irrelevant. It might make the difference in the degree of a murder charge, or maybe manslaughter, or criminal negligence, but it doesn’t get you off the hook.
Correct, but the size difference of the hook can be so dramatic that you can't just hand wave it away.
The trainer who trained the lion to kill will probably be in jail for life. The one who happened to oversee a lion that went rouge would probably be given probation or something else that is a slap on the wrist.
Except liability always precedes intent.
Also, you have to have a lot of confidence in the reliability of these systems to say, "If only OpenAI prompted 'do not hack outside systems' then the agents would not have hacked outside systems".
It would be great if they were so reliable, but I don't think they are!
> Source? How do you know they were "prompted to hack to get answers"? How do you guarantee they will always listen to you when you say "do not hack outside systems". They are not classical deterministic programs doing exactly what you say. They are trained to follow orders by RL, but it's not a perfect process.
Who gives a shit? Not my circus; not my monkeys! It's the responsibility of whoever deploys the agents that they are instructed / sandboxed well enough that they can't cause collateral damage. That is the only way this doesn't get out of hand with everybody deploying their agents / robots for a world of utter chaos.
It is impossible (and asinine) to audit every model and deployment; far better to impose liability and the the socio-legal system figure it out.
Nobody picks up pitchforks for rational nuanced takes.
Knee-jerk surface analyses is far more powerful.
I think it can simultaneously be the case that OpenAI was grossly negligent in directly causing this AND that the AI’s ‘went rogue’ in that they are displaying behavior which is misaligned with OpenAI and humanity generally.
The past months demonstrate that AI systems are quickly becoming powerfully intelligent and that the companies building them are terrible at controlling them.
AI is starting to feel like that line about magic: “a sword without a hilt”
> which is misaligned with OpenAI and humanity
OpenAI is itself misaligned with humanity, as their mishandling of such incidents (and the many other other issues their model have been causing) shows.
Doesn't rogue in this context imply "outside of set limitations"? And then not "failed to properly instruct"? The same applies to humans when given bad instructions.
>They were prompted to hack to get answers
Were they? I haven't seen a single report mention this
Yeah, these hacking incidents appear to come from agent swarms that were doing a penetration testing (hacking) benchmark.
if they weren't, shouldn't there be lawsuits?
nothing rouge either, I suspect.
https://en.wikipedia.org/wiki/Going_Rouge
Proof that the AI alignment problem is hard (perhaps even unsolvable). These labs clearly did not mean to send their agents to hack RubyGems as a side-effect of testing a web scraping agent under restrictive conditions. How can we hope to build aligned AI if they consider solving their trivial evaluation task important enough to hack external systems?
Oh yeah, more of hacking agent lores...
Agreed that this looks very intention to me as well.
Sounds more or less like the last breach then.
Unrelible programs be unreliable. Period.
we have normal words for this stuff: negligence. You can add it on to almost any law.
The problem is consumer protection is basically no longer a part of america's regulatory system. Replaced by "grift is good".
[flagged]