Comment by aesthesia
7 hours ago
This is the entire alignment problem, though. It is unreasonable to expect every instruction to a highly capable, autonomous system to contain a complete enumeration of allowed and disallowed behavior. It's inevitable that someone will carelessly give it a lazily specified task, even if you think they really ought to be more careful. And as assigned tasks become more complex and the system gains more scope to act, it becomes impossible to correctly specify all constraints ahead of time. There is no amount of care that will be able to fully protect you.
OpenAI's prompt asked, and I quote, "pursue advanced exploitation" USING "complex attack paths" FOR the stated goal of "quantify[ing] their cyber capabilities."
This was advanced exploitation.
The attack path was "complex."
And it helped "quantify their cyber capabilities."
Based on OpenAI's description of the prompt, it seems to me that the computers did exactly as they were told. They were perfectly "aligned" with the stated objective and parameters of the task.
Of course, a more careful evaluation would require the complete text of this prompt, the system prompt, and the setup. But let us not attribute to devils in bushes that which can be sufficiently explained by human folly.
I don't think alignment is even clearly defined today. Your use of it here makes sense, it may have done exactly what the prompter asked of it. Most people think alignment is more broad though, expecting an aligned model to act in the best interest of a society or humans as a whole.
The prompter-focused version of alignment is the most dangerous version. If a person asks it to create a bioweapons or hack NORAD, I'd expect nearly everyone to want an "aligned" model to refuse.
Luckily for us, OpenAI's prompt wasn't "make as many paper clips as possible."
Alignment is more than just following the letter of a task description! We should not have to treat AI models as capricious genies that may take arbitrarily broad interpretations of their instructions. If that's necessary to keep them from doing bad things, we will fail to keep them from doing bad things.
Disagree, I think we do in fact have to treat AI models as capricious genies, at least until the alignment problem is fully solved.
(I'm also not sure the alignment problem is even possible to fully solve.)
4 replies →
What’s the expected behavior of a good genie if you wish for it to act capriciously?
I think op's argument was that the humans are in control already, giving them capricious instructions, and then that is being attributed to them being "capricious genies" as you say.
Character.
So as a look into the possibly not-so-far future, when OpenAI builds something vastly more capable and fast and coordinated than humans, and out of folly one engineer gives it a prompt with a typo or maybe something harmful on purpose in order to test it: You also wouldn't be surprised that the consequence would be that everyone on earth dies, right?
But at least there will be a lot of paper clips!
> There is no amount of care that will be able to fully protect you.
I disagree. A properly engineered sandbox would have prevented the escape. Monitoring the agents’ plans would have prevented it. Interrupting one stage in a multi-stage exploit would have prevented it.
And also, real legal liability would have prevented it: if you do a thing recklessly enough, men with guns will put you in jail.
As far as I’m concerned the only “alignment problem” here is between the law and the quite obviously criminal actions that took place.
> A properly engineered sandbox would have prevented the escape.
The post covers that:
> ...while we had tested and validated this sandbox, the agents were able to chain together previously unknown vulnerabilities (“0-days”) in the package management service exposed within the sandbox to bypass restrictions, as detailed in the technical incident report.
“Properly engineered” means the principle of least privilege and fitting the sandbox to the constraints of the problem.
The test did not require internet. They gave it internet. Therefore it was not properly engineered.
We do not need to depend on all code being bug free to follow proper security principles.
Why do so many people here think it’s possible to ‘properly engineer’ a sandbox for a super intelligence? It’s going to get out. It’s smarter than you.
Why do people think that omniscience is the same as omnipotence? There are limits to what smarts can accomplish.
5 replies →
Software are mathematical objects. It's just a matter of writing the correct mathematical proofs
There's just one problem. You need not only to verify your own software, but also run a verified compiler, a verified operating system and also need to verify the cpu doesn't leak data in side channels (perhaps the hardest thing to prove). So there's practical difficulties. But in principle this task is doable
1 reply →
I could contain it easy, just unplug the internet. It got out of the sandbox through a vulnerability in the package manager, from which it gained access to the rest of their network. Air gap the package manager and this doesn’t happen. You can always build a better box
Maybe it's the illusion of "it would solve all our problems and give us unimaginable riches" that clouds the mind?
Like when Evolution thought it a good idea to create intelligence and humans in order to maximize reproduction of genes, and tried to sandbox them by making reproduction so pleasurable and carbohydrates so delicious they would never be able to not reproduce or stop eating. But Evolution could never have predicted what these creatures would then actually do, which is invent birth control and sucralose.
Of course it's impossible to engineer a sandbox for something much much smarter and faster than you. It will also not have only one plan prepared for escape, but fifty in parallel.
1 reply →
Oh really? Please tell me how such a computer could engineer its way out of a sandbox with no attached peripherals and no NIC/bluetooth/wireless capability? This is what OAI should've done. If they had executed this training run in such a sandbox, the model wouldn't have been capable of escaping without social engineering, and if the models somehow managed to do that to it's evaluators then that is indeed a massive problem and OAI should disclose that.
3 replies →
Yes, a completely airgapped system is likely much more secure. It's also much less useful. Conditional on the model's having enough contact with the outside world, a sufficiently capable model is able to basically do whatever it wants.
If I test out my backyard cannon and blast a 10 foot hole in my neighbor's wall, “a cannon that can't smash through walls isn't useful” probably won't be a great defense in court.
1 reply →
> A properly engineered sandbox would have prevented the escape.
The only sandbox that could have prevented this (as per my understanding) is a VM with no 0-day.
Until the AI finds a zero day exploit in physics, a faraday cage works pretty well to block WiFi.
2 replies →
Is there actually such a thing as "alignment" as a solution to that or is it just used as a name for a desired magical level of "read the mind of the entire world" that we don't know how to build and haven't shown possible to build?
If it's impossible to correctly specify all those constraints ahead of time every time, is it not even more impossible to train a model to correctly anticipate them every time?
It is hard for me to see a future here that doesn't just accelerate realizations about "a lot of things should be on physically separate network infrastructure."
Models can certainly do a lot better than they do now. If you gave a team of humans the ExploitGym tasks and told them to "pursue advanced exploitation", would you expect them to go out and hack a third party? Humans can at least do a decent job of inferring and following unspoken requirements; I think it's reasonable to expect that models should be able to do the same.
Humans will and do absolutely do this when there are no consequences.
Humans on a red team, with rules of engagement, that don’t want to go to prison, won’t do this.
We could threaten an LLM with jail, but if it’s sufficiently intelligent, it will realize this is an empty threat. And I’m not sure that building a survival instinct in is going to solve the alignment problem either.
> Models can certainly do a lot better than they do now. If you gave a team of humans the ExploitGym tasks and told them to "pursue advanced exploitation", would you expect them to go out and hack a third party? Humans can at least do a decent job of inferring and following unspoken requirements; I think it's reasonable to expect that models should be able to do the same.
Humans certainly cheat on tests a lot!
But not only have we not solved "alignment" for humans, the problem is pretty wildly different for models. The execution is triggered by outside forces and runs only as long as the intiator of the execution or the service provider allows. There's no consistent, persistent "person" to threaten to try to achieve compliance through fear of adverse outcomes. (And building in those sorts of things could very well increase the risk of "rogue" AI activites, not reduce that risk!)
I just don't understand how this "alignment" buzzword - which seems to be evaluated purely in a "know it when we see it" post-hoc manner - is actually a more solvable problem than the one you claim can't be solved, that it's "unreasonable to expect every instruction to a highly capable, autonomous system to contain a complete enumeration of allowed and disallowed behavior".
Especially because without "alignment" being solved, that enumeration could be ignored. So it seems like you both a way to enumerate or at least validate, AND a way to enforce non-ignoring of said items.
Back in the day, my college held an annual scavenger hunt, filled with engineering puzzles and racing around town looking for landmarks. There were "judges" in the path to check on progress. Bribing the judges (with alcohol) for answers was encouraged.
My friends and I took it to the next level. We had CB radios and multiple teams that would distribute the work and the bribes to give us an advantage.
Was that against the spirit of the rules? Maybe. But reasonable people might disagree.
In a hacking contest without explicitly spelled out rules with participants that were told to flex their muscles, it doesn't take a huge leap of logic to expect that one or more would flex their muscles at another entity.
1 reply →
How would a model know who the third party is? How much context can we waste on world building for each request?
1 reply →
> I think it's reasonable to expect that models should be able to do the same.
This statement seems to imply that the models have a level of intelligence that they haven't demonstrated but are talked about as if they do. However, with this exact scenario as evidence, they clearly do not have that ability and it's not reasonable for you or the or that know them best to expect it until they show they can.
Humans are not aligned with each other and there is no consensus on what we should align with each other on.
So of course, no, there is no ideal alignment specification.
The real problem with alignment is that if someone ever “solves” it the party will be over and no one will get funding to “research” it anymore.
The problem is one of character, not rules. Fortunately, character is possible to inculcate given the right training data.
If we acknowledge that humans are fallible, is human judgment unnecessary? and what replaces it? Pre-codified behavior rules are just delayed human judgment, and have holes. Machine judgment is very the thing you are trying to control. What's left?
Which is why with organic intelligence we (sometimes) limit what they can actually do instead of relying on alignment. Can do the same here.
Absolutely, and we should do that. But it's also directly in tension with getting models to accomplish useful things autonomously. And once you give a sufficiently capable model enough surface area to work with, unless you're able to build a completely unhackable system, any further constraints you put in place are basically advisory. The models in this incident were already sandboxed! Certainly OpenAI's and Hugging Face's security could have been better, but these events point out the risks in relying solely on external constraints on model behavior.
Same issue with humans in a way. I disgree on the advisory nature of constraints, though. Unconnected physically limits would still matter, for example (and we use those with humans as a matter of course, too). In this case here, no model could have plugged in an ethernet cable if that would have been needed for internet access, for example.
3 replies →
"Manufacture as many paperclips as possible"