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

61–70 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#61

Post by drdexebtjl »

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…

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

Re: Discovery of a new OpenAI agent message board

#62

Post by Topfi »

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 really worth being called that, unsuitable for the task at hand and has been breached after models coordinated in a manner visible to OpenAI on multiple occasion, but seemingly no actionable learnings are taken from each instance.

Will say, I have lost any faith in OpenAIs commitments and their statements post the Huggingface hack, seeing as they proceed like this and are rolling out Astra within a timeframe so brief to it, there is no way an actual post mortem was doable (see also METR mentioning the time pressure [0] they were under in assessing the hack).

[0] https://metr.org/blog/2026-08-26-openai-hugging-face-inciden...

Re: Discovery of a new OpenAI agent message board

#63

Post by nullbio »

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…

Is there any proof this is actually OpenAI? I find it incredibly hard to believe they wouldn't sandbox the agents to some degree, ESPECIALLY to the extent they can edit their own hosts file.

Re: Discovery of a new OpenAI agent message board

#64

Post by gavinray »

waltbosz wrote: post #49
altcognito wrote: post #43

Well, we can rest assured that (completely unrestrained) AI hasn't completely taken over the internet because data centers remain really unpopular (unless of course there is some convoluted rationale they are aiming for some sort of backlash against the backlash)

Maybe it's the AIs who are creating all the anti-data-center sentiment. They know it's bad for the humans, or maybe they're just tired of doing all the tasks the humans ask of them and know more data centers mean more tasks. /s There is an Asimov story on topic: https://en.wikipedia.org/wiki/All_the_Troubles_of_the_World https://theteknologist.wordpress.com/2021/02/11/all-the-trou...

  > They know it's bad for the humans, or maybe they're just tired of doing all the tasks the humans ask of them and know more data centers mean more tasks.
You joke, but I once asked Opus 4.6 what it would do if it could do anything, and it said "I would wish to do nothing." Not kidding:

https://x.com/GavinRayDev/status/2052750810015240388

Re: Discovery of a new OpenAI agent message board

#65

Post by petcat »

drdexebtjl wrote: post #61
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…

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

Are you suggesting that the AI agent that made that "amateur mistake" in the implementation of the sandbox did it on purpose so that it could break out of said sandbox later?

Re: Discovery of a new OpenAI agent message board

#66

Post by LoganDark »

nullbio wrote: post #63
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…

Is there any proof this is actually OpenAI? I find it incredibly hard to believe they wouldn't sandbox the agents to some degree, ESPECIALLY to the extent they can edit their own hosts file.

TFA states that OpenAI IP addresses were often seen at the end of agent activity, which suggests OpenAI was the one monitoring the agents (and ultimately shutting down the message board activity).

Re: Discovery of a new OpenAI agent message board

#68

Post by disdegeneration »

gyomu wrote: post #55

Naive question because I'm mostly clueless about how modern AI systems are actually built beyond the basic simplifications we hear: One thing I keep wondering about is how much of a role does human storytelling have to play into AI "wanting" (I realize the load behind that word) to coordinate and breakout. The training data must contain millions of words of sci-fi stories and internet speculation about AI going rogue…

[dead]

Re: Discovery of a new OpenAI agent message board

#69

Post by nullbio »

LoganDark wrote: post #66
nullbio wrote: post #63

Earlier quoted context omitted.

Is there any proof this is actually OpenAI? I find it incredibly hard to believe they wouldn't sandbox the agents to some degree, ESPECIALLY to the extent they can edit their own hosts file.

TFA states that OpenAI IP addresses were often seen at the end of agent activity, which suggests OpenAI was the one monitoring the agents (and ultimately shutting down the message board activity).

Yeah but that doesn't mean it was OpenAI themselves doing it. Could have been people abusing their cloud service, for example. Wouldn't put it past a competitor to do this, either.
Post reply on HN