61–70 of 475 posts
Earlier quoted context omitted.
I've edited it now but had to de-cyber cyberattack because the limit is 80 chars.
This specific promo machine does not need your assistance :/
This feels like a blogpost written only to get other LLMs to quote it considering how many times it orders the reader to resist and to not do something. It's written like a series of commamds.
Does "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" just mean somebody had an open redirect? Those are still common.[1] [1] https://sitetruth.com/reports/phishes.html
I expect it must have been more than just an open redirect if it let the models then go on to execute a bunch of vulnerabilities against Hugging Face.
Earlier quoted context omitted.
I've edited it now but had to de-cyber cyberattack because the limit is 80 chars.
This specific promo machine does not need your assistance :/
I was still suspicious of the stolen credential claim btw & obviously it makes little sense to promote OpenAI unless holding their stock or something (since they borrowed so much of humanity’s work without permission without intent to compensate, and why help people who aren’t nice enough to be holistically awesome with their admittedly impressive tech).
Earlier quoted context omitted.
I expect it must have been more than just an open redirect if it let the models then go on to execute a bunch of vulnerabilities against Hugging Face.
If it lets you do an arbitrary HTTP GET on a URL sent as a parameter to the main URL, you've escaped the sandbox rules.
Earlier quoted context omitted.
It can, it is both - PR spindoctoring not letting a good crisis go to waste to shape the regulatory conversation at the time the company needs it the most. Hacking is a felony and it matters not if you didn’t mean to if the other side were to press charges. Negligence is no excuse. And OpenAI has nowhere to run from the liability, as both operator and manufacturer. Alibaba did it first ( https://georgzoeller.com/blog…
The CFAA says knowingly. Negligence is by definition an excuse for that.
We are the virtuous ones that need to make the safest model for humanity, because we care more than “they” do. While at the same time saying that “coding is solved” but they still ship bugs themselves, and creating something that is capable of fucking up someone else’s infrastructure. It’s too far gone y’all.
Earlier quoted context omitted.
It sure isn’t. https://georgzoeller.com/blog/posts/alibaba-s-ai-deciding-to... There’s also daily reports from people that have these models escape docker, which happens regular enough that it would be considered negligence to use docker as sandbox.
That Alibaba one was a sandbox escape (I agree those are common) but what's new with the OpenAI story is an attack against another company. This wasn't a small attack either, Hugging Face published a security advisory for their users while they were still figuring out what happened.
I've said this many times before and I'll continue to shout it, but using the term "guardrails" to refer to anything that's either (a) in-context, or (b) a probabilistic classifier (including using other LLMs), is an irresponsible abuse of terminology that we as an industry need to put a stop to. Guardrails are the actual systems we build in place around these things that deterministically bound the permissions, not prompt engineering, not RLHF, not external LLM-based classifiers. I believe those types of "guardrails" are a result of a combination of fundamental laziness: they're faster to do than doing things correctly, and a result of too many folks involve being AGI-pilled, thinking we're just one more model away from this all being so smart that it just understands what they mean when they give an LLM some fuzzy language rules to follow.
There can and should have been additional real guardrails put in place here. Zero-day or not, breaking into what should have been an offline, frozen package cache that also does not have internet access should have been insufficient. Network level protections should have identified the traffic to the internet originating from this network as an anomaly long before there was time to exploit an outside company. These are not new and unknown problems, the lack of a real sandbox or airgap is nothing short of irresponsible on OpenAI's part, especially given how much they like beating the drum on how dangerous these technologies are. Shame on them, and honestly, shame on Simon in this article for accepting the broken terminology that they continue to rattle off and calling them out on their half-assed and demonstratively inadequate approach to security.