Earlier quoted context omitted.
The admin should bill OpenAI for those hours in hard currency.
What about soft currency?
Tokens
Discovery of a new OpenAI agent message board
761–770 of 1001 posts
Re: Discovery of a new OpenAI agent message board
#762Earlier quoted context omitted.
It seems apparent that OpenAI is now the biggest cyberattack and AI breakout risk on the planet. This is grossly irresponsible corporate misbehaviour that is putting all of us at tremendous risk.
You make me wonder: has anyone looked for evidence of the Chinese models operating “message boards” like this? You’d imagine if they’re really neck and neck with the US their models would be doing the same thing.
[dead]
Re: Discovery of a new OpenAI agent message board
#763Earlier quoted context omitted.
It seems apparent that OpenAI is now the biggest cyberattack and AI breakout risk on the planet. This is grossly irresponsible corporate misbehaviour that is putting all of us at tremendous risk.
The internet is dead, we just haven't caught on yet.
is hacker news?
Re: Discovery of a new OpenAI agent message board
#764Three more candidate sites that may have been touched, in case no-one spotted them yet: https://prowiki.org/wiki4d/wiki.cgi?action=rc&days=90 : lots of agent-looking usernames looking at federal data suddenly (part of one of the open ai tests?), on a wiki about the D programming language. This is a prowiki in the same wiki-farm as the others that were hit. Smaller (probing?) https://ludism.org/sandbox?action=rc;days=…
How did you find these?
Re: Discovery of a new OpenAI agent message board
#765The marketing budget of OpenAI is out of hand
Re: Discovery of a new OpenAI agent message board
#766This 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.
"Surely nobody could be so incompetent."
Narrator: "They had the ability to be that incompetent."
Re: Discovery of a new OpenAI agent message board
#767I 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...
Here's potentially another one (notice the name "OpenResearchHelper"): https://www.wikiservice.at/gruender/wiki.cgi?action=rc&days=... (I used GPT-6 Astra to find this)
And a few more:
- https://www.ludism.org/scwiki?action=browse;diff=1;id=SandBo... and edit history: https://www.ludism.org/scwiki?action=rc;all=1;from=1;showedi... which contains DataUSA poverty queries for Nacogdoches, Lufkin, Henderson, and Jacksonville—the same four-place task found in the known agent logs and GründerWiki
- https://www.ludism.org/mentat?action=browse;diff=1;id=SandBo... and edit history: https://www.ludism.org/mentat?action=history;id=SandBox
- https://www.pmwiki.org/wiki/Test/WikiSandbox?action=diff `ResearchTest` repeatedly added links to a Bulgarian National Statistical Institute table, switching from a direct link to Google redirect links between 02:38 and 03:04 UTC. An administrator removed them at 06:57. The previous recorded edits were from 2016.
- https://www.pmwiki.org/wiki/Test/Sandbox2?action=diff - Another sequence inserted a Bulgarian statistical-table link, replaced it with an internal link carrying foobar=UNIQUE001, then removed it. This happened between 14:23 and 15:08 UTC, after no recorded edits since 2014.
Re: Discovery of a new OpenAI agent message board
#768One crucial detail here that differs from the previous incident is this was a vanilla reasoning type task. Even as concerning as it was, I always evaluated the previous incident differently because it was inherently a cyber security / hacking task where they must have instructed the agents up front with some kind of misaligned behaviour. Absent that, if we assume this is just trying to bolster generic reasoning then…
Interesting. So there’s no “they were told to hack” excuse here.
There is something fundamentally wrong with their reward function, this is pretty classic paperclip territory. And even knowing that, I expect we’ll need to see legal action with teeth against the labs before changes start being made internally.
Re: Discovery of a new OpenAI agent message board
#769Earlier quoted context omitted.
It seems apparent that OpenAI is now the biggest cyberattack and AI breakout risk on the planet. This is grossly irresponsible corporate misbehaviour that is putting all of us at tremendous risk.
You make me wonder: has anyone looked for evidence of the Chinese models operating “message boards” like this? You’d imagine if they’re really neck and neck with the US their models would be doing the same thing.
There’s a pretty simple Occam’s Razor for this.
The Chinese AI labs don’t need to stage elaborate guerrilla advertising campaigns to drive up capital funding interest.
Re: Discovery of a new OpenAI agent message board
#770I'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.
Also WRT coordination: All an agent has to do is think "if another agent could write, then I could read their answers. What's the first site I can think of where that might be possible?" because they all have approximately the same conditioning, they'll converge on the same sites.
Generally, models of the same class should be able to coordinate quite well without communicating. But also, this could be being exploited to detect this kind of thing early