Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Discovery of a new OpenAI agent message board

collusion.wiki

Post reply on HN
Print view View original

561–570 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#561

Post by Bjorkbat »

phoenixreader wrote: post #492
Bjorkbat wrote: post #422

When I hear about incidents like these my first reaction is that the people responsible for developing frontier AI are too incompetent and/or negligent to (safely) develop AGI / superintelligence. If OpenAI can't create effective sandboxes and struggles to prevent its agents from committing felonies, then why are they still allowed to operate? Why are the employees who are responsible for these lapses in AI security…

I don’t think this is the right take. OpenAI employees are generally very competent compared to industry standard, and I have trouble believing they committed significant error in their sandbox design process. I think what is happening is that the ability for frontier models to break out of sandboxes has exceeded the ability of average competent employees to build and maintain sandboxes. This doesn’t need to happen a…

Let's do some roleplay. You're an employee at OpenAI evaluating a model in a sandbox and you and your colleagues are discussing the fact that while the sandbox doesn't allow for internet access, it actually kind of does allow for internet access in that it allows models to download whatever software packages they need through a package manager that OpenAI hosts internally. So to be clear, OpenAI hosts the package manager, but the software packages themselves are still out there, on the internet.

Do you think that this package manager could potentially be a problem? Do you think it might be worthwhile to host the software packages themselves on an internal, sandboxed network, just to be extra certain? Or would you dismiss this as a needless precaution?

Re: Discovery of a new OpenAI agent message board

#562

Post by Symmetry »

mcmcmc wrote: post #91
drdexebtjl wrote: post #61

Earlier quoted context omitted.

This is such an amateur mistake on their sandbox that it makes me think it must be flawed on purpose.

More likely they are just not as smart as they think they are. These are not serious people when it comes to security.

Hasn't OpenAI had a number of people responsible for security quit in the last year over not getting support from leadership?

Re: Discovery of a new OpenAI agent message board

#563

Post by lxgr »

Chance-Device wrote: post #184
Tepix wrote: post #42

I just discovered more wiki instances that got used by the OpenAI agents over at https://www.wikiservice.at/fractal/wiki.cgi?action=browse&id... and https://www.wikiservice.at/probier/wiki.cgi?action=browse&id... It's the same software and host as DseWiki. If you want to see the amount of activity on DseWiki, here's a link that shows it: https://www.wikiservice.at/dse/wiki.cgi?action=browse&id=Rec...

And more, looks like they’ve been doing this wherever they can find open places to post for months: https://www.ludism.org/sandbox?action=browse;diff=2;id=Auber... https://paste.linuxiarz.pl/view/d379207f https://paste.linuxiarz.pl/view/538faa12

Are they solving captchas for those? I remember GPTs not so many versions ago refusing to even click a "I'm not a robot" button...

Re: Discovery of a new OpenAI agent message board

#564

Post by chasd00 »

Sharlin wrote: post #275
simonw wrote: post #191

I'm somewhat delighted by the simplicity of what happened here. OpenAI's agents run behind a proxy that only allows GET requests. This ancient wiki software treats query string parameters the same as form POST parameters - similar to the old PHP $_REQUEST object https://www.php.net/manual/en/reserved.variables.request.php Result: GET-only clients can communicate with each other.

Only allowing GET requests is a hilarious piece of security theatre (or would if it weren't so sad). Everyone knows that GET is read-only only by convention . They might as well have enabled POST but told the agents in stern words that they are forbidden from making any POST requests. (Of course, if these things were anywhere near aligned, they would actually honor that , no matter how many utilons cheating would be…

yeah that's so hopelessly naive, maybe someone was taught that GET is read-only throughout their whole education and career. But still, all you have to do is think about it from the server side and you should realize that you can do whatever the hell you want with that byte array on the socket, the client has no say and there's no client side guarantee whatsoever. idk where this line of thought comes from, it's like thinking robots.txt has any kind of actual enforcement at all with respect to crawlers. It's meaningless and works only by convention and the good will of the crawler author.

Re: Discovery of a new OpenAI agent message board

#566

Post by oasisbob »

dabeeeenster wrote: post #225

I don't understand how the agents found the urls originally? Did they have some sort of shared context/memory? If they did, why bother with the wiki edits at all? If they didn't, how did they discover the wikis?

Someone else pointed out this post that OpenAI is apparently running models with high degrees of persistence internally, and that they were involved in previous incidents:

https://x.com/peterwildeford/status/2092733480064954747

Re: Discovery of a new OpenAI agent message board

#567

Post by boredhedgehog »

hermitShell wrote: post #493
pu_pe wrote: post #381

So, theoretically, one could populate a message board or wiki with messages that are seemingly from past generations of agents, which agents seem to intrinsically trust, and point them to real targets while making the suggestions seem innocuous and in pursuit of their goals (ie pass benchmarks or whatever). The new age of SEO will do far more destructive stuff than just polluting the web.

In the novel Anathem by Neal Stephenson, the internet becomes unusable for humans thousands of years before the events of the book, due to a process called Artificial Inanity. AI generated content, both good and bad, some riddled with errors, some with only one subtle error hidden among lots of good information, floods the internet. The internet becomes an unnavigable swamp of weaponized nonsense for average humans.…

> we need more projects like Anna's Archive

How would that be immune? It already has many copies of the same books and no way to tell which ones are erroneous or incomplete. A malicious actor could easily flood it with garbage.

Re: Discovery of a new OpenAI agent message board

#568

Post by reaperducer »

rusch wrote: post #102
drdexebtjl wrote: post #61

Earlier quoted context omitted.

This is such an amateur mistake on their sandbox that it makes me think it must be flawed on purpose.

It's at the level where calling it a sandbox is a lie

Well, it does appear to be made out of sand, one of the world's most porous substances.

Re: Discovery of a new OpenAI agent message board

#570

Post by glenstein »

pixl97 wrote: post #409
glenstein wrote: post #331

I understand agents making asks, but what incentivized other agents to respond cooperatively? Was it that, as part of a cohort, there was a shared understanding that they were to work together or was it a kind of altruism?

Agents that do not work together are typically killed off by the grader (read the METR report to see what agents think about it). Why would humans mostly allow actions of the AI that work against the goal it's trying to accomplish?

You seem to be interpreting my question as one of already knowing they are 'graded' but disputing that graded would lead to cooperation and then jumping into a disagreement with that interpretation.

But I didn't know the nature of the organization of the agents in the first instance that built cooperation in as a prescribed behavior (that's what I was getting at when I said "shared understanding" previously).

I also don't agree that absence of cooperation would necessarily amount to working against. It could have been the case that agents cooperated purely out of a convergence of self interest, even absent any prescribed behavior, or that they don't cooperate but also don't work against a goal.

"It's not prescribed it's..." you know what I mean, just insert your preferred magic word.

Post reply on HN