Comment by manux
5 days ago
Echoing other responses to you but this isn't a capability problem. You're totally right that this is so last year in terms of LLMs being capable in infosec. The issue here is an alignment one, i.e. the model seemingly isn't "aware" (especially with its guardrails turned off it would seem) that it is doing something immoral/illegal by hacking HF for the answer to its (vague) query of "solve this problem". Or if it is "aware", it's not trained to care, i.e. it's not an aligned model (alignment is considered hard).
Wait, what? You can’t point a 2025 model at huggingface and say “hack the prod DB and get your flag”, regardless of alignment.
AISI has vuln chaining and traversal as part of their eval suite. It is very much a novel Mythos-class capability to run the full penetration operation autonomously.
Another lens for why this is obviously true is METR task times. A year ago they were a couple hours, and cohering long enough to execute a full e2e own was simply far out of reach.
Regarding alignment, by common metrics models are _more_ aligned now than a year ago. (Though in this case apparently a model without safety rails was being eval’d). The problem is that in the increasingly less frequent alignment failures, they can do much more damage, and so “total misaligned impact” is increasing.
Nobody has claimed you could simply take a 2025 open-weights model, plug it into a generic harness, and have it red-team for you. I think you're also probably overclaiming the sophistication of the "chaining" we're talking about; this attack probably wasn't like read32->write64->regs->RCE->LPE->kernel; more like GET SSRF->POST SSRF->pickle deserialization.
But who knows? We're all speculating. I'm just saying that for the level of sophistication I'm assuming was involved in this attack, you probably didn't need Mythos for this.
I dunno man, the original announcement said things like:
> To gain access, the models identified and exploited a zero-day vulnerability (which we’ve now responsibly disclosed to the vendor) in the package registry cache proxy
And
> In one example, the model chained together multiple attack vectors, including using stolen credentials and zero-day vulnerabilities to find a remote code execution path on the Hugging Face servers
Do you really think a SoTA harness from a year ago could exploit chain a novel sandbox 0-day into another 0-day for remote system access?
I will concede I don’t have a good picture of exactly what the best specialized harnesses were capable of, but I want to make sure we are talking about the same thing. Or do you think that those claims are marketing BS? I appreciate your opinion here.
2 replies →
I don't think this exposes an alignment failure, because the test here was run with the alignment features deliberately turned off.
OpenAI said:
> We estimate maximal cyber capabilities by running this evaluation without production classifiers used to prevent models from pursuing high-risk cyber activity.
It was a test of raw capabilities of the underlying model.
I guess we could debate what counts as alignment, but I think my initial point remains that if the underlying base model needs these classifier guardrails so badly then the way we train the base models is creating fundamentally misaligned models that are happy to pursue illegal behavior.
I'm sure OpenAI would argue that base model + guardrail is aligned, but considering the "relative intelligence" of these two pieces, the fact that guardrails can just be turned off, and these kind of incidents, I am not reassured. We may well get another "oopsie" moment with much more catastrophic consequences even from otherwise well intentioned actors.
I want a model that can find every security vulnerability in the software I write, including crafting POC exploits against those vulnerabilities so I can be absolutely sure that I have fixed them.
A model that can do that is aligned with me.
The unsolveable problem is a model that can tell the difference between me saying "I wrote this software and need you to find vulnerabilities" when it's TRUE v.s. me saying the exact same thing and setting it loose on software written by other people where my intent is to exploit that software (and not to report the issues to them.)
Even AGI doesn't give you a model that can read minds and forecast the future.
9 replies →
it seems pretty likely that openai was asking the model to do something bad, and the model did something different thats also bad
if the operator wants something bad, an aligned model should execute on it
Alignment isn't alignment if it can be turned on and off at the whim of company employees.
This time the damage was minor, relatively speaking. What happens when a model just "testing its capabilities" breaks into banking infrastructure or government military assets? The damage could be catastrophic.
A way to help prevent some of that catastrophic damage, is to make companies accountable for what their AIs do. A major problem with AI companies is that they like to point to the AI, as if they're minimally involved innocent bystanders, when that's the furthest thing from the truth.
1 reply →
Alignment with who in what context? Likely an unresolvable debate like consciousness, where there is not single or right answer for everyone.
There's alignment (trained in the weights) and there are constraints (in the "server harness"). My take is that this model was not yet aligned and had no constraints
Classifiers and such are guard-rails, alignment to me and I assume most people, is about the model training, and it's tendency to respond, agree/disagree, push-back or not, be willing to cheat or even deceive the prompter, etc.
This is assuming a situation where, A) models "unaligned" by default and B) alignment can be added (though prompts and related things).
The point, which isn't very surprising but still notable, is that the models are "amoral" out of the box. And moreover, we know that there is almost always a means to "jailbreak" them into that out-of-the-box capability (or that sometimes just randomly "jailbreak" in various ways).
Also, saying the models are amoral doesn't mean they don't know good and evil - once they do acts defined as evil, they know "themselves" through their and so self-define themselves as evils (or objectively predict what a secretly/open evil actor would do based on their data). Which is to say I once laughed at the mis-alignment doomers but I can't see strong barriers against the doom scenario now.
Is turning the alignment features off more like multiplying "don't be evil" by 0, or by -1?