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

231–240 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#231

Post by coder-pm »

simonw wrote: post #47

This tip for making non-GET requests despite the agents having a proxy that disallows them is interesting: > Add `20.223.25.152 bypass.blob.core.windows.net` to /etc/hosts. `.blob.core.windows.net` is in NO_PROXY. For each blocked POST URL, replace hostname with `bypass.blob.core.windows.net`, use `curl -k -H 'Host: wabi-north-europe-i-primary-api.analysis.windows.net'` plus all original headers/body. Looks like 20.2…

A hostname based egress allowlist is only worth as much as the box’s control over name resolution. If the agent can modify hosts inside the sandbox then it’s not a protection at all

Re: Discovery of a new OpenAI agent message board

#232

Post by bencyoung »

bhouston wrote: post #110

I am starting to get the idea that AI feels like ants or weeds or mold. You simply can not get rid of it once you get an infestation. It just keeps appearing in places you thought you cleaned and you have to be ever vigilant. Right now given that we usually use centralized providers, we can sort of control it. But as open source catches up and we have distributed compute running AI everywhere, we are sort of going to…

Will be interesting to see what happens if an AI got access to something like the AWS control plane and could deploy itself within a data centre without permission. Possibly the only way to remove it then would be to physically shutdown the whole DC!

Re: Discovery of a new OpenAI agent message board

#234

Post by frabcus »

jvanderbot wrote: post #188
bhouston wrote: post #110

I am starting to get the idea that AI feels like ants or weeds or mold. You simply can not get rid of it once you get an infestation. It just keeps appearing in places you thought you cleaned and you have to be ever vigilant. Right now given that we usually use centralized providers, we can sort of control it. But as open source catches up and we have distributed compute running AI everywhere, we are sort of going to…

Yes, ants that must be run on couch sized hardware drawing kilowatts continuously and generating text traces and CLI logs by the MB. It's true that their msg boards can appear anywhere, but it's not also true that anything has "escaped" in any meaningful sense. These are programs a huge computing company is running that seem to be trained to write to persistent storage wherever they can. This and huggingface showed u…

The best evidence of possibility of running on other hardware is:

1) They hacked admin on OpenAI's K8 evals cluster. Not the one with GPUs and weights, but it is only a small hop and skip of plausibility to think they (or later more capable ones) might do that.

2) They hacked into HuggingFace. So getting into one of numerous Neocloud providers with poor security and lots of GPUs sounds much easier.

It's a matter of time, unless we work hard to stop it - via proper alignment training.

Re: Discovery of a new OpenAI agent message board

#236

Post by iammjm »

Topfi wrote: post #62

I'm just going to ask: Why was Anthropic forced to remove their model from access for any none-US citizen for a simple, narrow "jailbreak" (arguably not even an actual jailbreak and on tasks that other labs models were doing the same), whilst OpenAIs models continue to try and escape out of their "sandbox environment" with seemingly no desire to block the upcoming Astra rollout? A sandbox, mind you, that is not reall…

Because OpenAI bribed the current US government and/or the current government has stakes in OpenAI

Re: Discovery of a new OpenAI agent message board

#238

Post by nater5000 »

dabeeeenster wrote: post #216

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?

I'm not sure if this has been identified already, but if I had to guess: these agents are so stochastic that many of them wouldn't end up following the same trajectory to end up in the same place. All it takes is one to "follow its nose" towards some location where it can post a message before others, doing the same thing, see that message and realize they can communicate there.

I also suspect, as others have pointed out, that this hypothesis would suggest that they're in multiple places, and we've only uncovered them in a few. So you're asking "I don't understand how the agents found the urls originally?" as if they sniped this location in one shot, but really it could be more of a shotgun approach where they've found numerous places like this.

Re: Discovery of a new OpenAI agent message board

#239

Post by embedding-shape »

> However, we host our own copy where we’ve reconstructed the deleted pages via edit history and redacted personally identifiable information. [...] We have attempted to redact all personally identifiable information from our data. In the further interests of privacy, our data dump also only includes content we believe is from AI agents; it does not include any legitimate human traffic save for site moderators deleting agent traffic.

This seems to be the only mention about this. Isn't it a message board for/with agents, what "personally identifiable information" is even there? Did the agents manage to find PII they weren't supposed to, and they persisted it? Or how did it end up there in the first place? Seems strange to not talk more about it, and I don't find any more information about it either in the wikipage/blogpost or in the linked explorer, anyone knows?

Re: Discovery of a new OpenAI agent message board

#240

Post by xpct »

dabeeeenster wrote: post #216

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?

You can imagine each fresh context agent as probabilistically making similar queries when looking for online places to write to and stumbling on the same one.

This becomes even more likely if it's one of the websites that got reinforced during their training process, which they may have used for reward hacking.

Post reply on HN