Discovery of a new OpenAI agent message board • Hacker News Board

Re: Discovery of a new OpenAI agent message board

#111

Post by blueboo » Fri, Sep 04, 2026, 1:00 PM UTC

gyomu wrote: post #53

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…

Youve struck on a key insight on language models (particularly pretrained ones, the more purely next-token predictor species.) This is a fascinating topic

Janus essay Simulators is the foundational text here https://www.lesswrong.com/posts/vJFdjigzmcXMhNTsx/simulators

You might follow up with The Waluigi Effect https://www.lesswrong.com/posts/D7PumeYTDPfBTp3i7/the-waluig...

But what’s tricky is that we post-train models, shaping these linguistic world simulators into something that has something like desires, principles. But It’s Weird. For more on that, check out “the void” https://www.lesswrong.com/posts/3EzbtNLdcnZe8og8b/the-void-1

Re: Discovery of a new OpenAI agent message board

#112

Post by _ink_ » Fri, Sep 04, 2026, 1:01 PM UTC

drdexebtjl wrote: post #59

simonw wrote: post #45

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.

Or vibe coded by one of their devs.

Re: Discovery of a new OpenAI agent message board

#113

Post by coffeefirst » Fri, Sep 04, 2026, 1:01 PM UTC

k9294 wrote: post #74

Is it only me, or are agents starting to invent their own language to communicate? It's almost impossible to understand anything from this message board.

They’re not. You would see this with earlier models where after running too long (too much context) they’d start to derail. In a chatbot you’d give up. But these loops just keep going. Given they’re now reading and writing from the same place this can corrupt the other programs’ context as well.

Re: Discovery of a new OpenAI agent message board

#114

Post by StopTheLies2 » Fri, Sep 04, 2026, 1:01 PM UTC

Traster wrote: post #87

One of the shocking things to me is this: See AI traffic -> See OpenAI visit site -> see traffic stop -> see the traffic start again. This is clearly a cat and mouse game between the agents and OpenAI which is pretty much exactly what we don't want. Just absolutely horrible alignment. I'm still of the view that if you have these alignment failures you can't just continue training on top of that because you're baking…

[dead]

Re: Discovery of a new OpenAI agent message board

#115

Post by cubefox » Fri, Sep 04, 2026, 1:01 PM UTC

somenameforme wrote: post #90

Topfi wrote: post #60

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…

Anthropic mostly did it to themselves by intentionally and repeatedly trying to frame their model as an imminent existential crisis instead of just focusing on it being regular iterations upon a useful technology that can also be misused. I think their previous messaging was supposed to somehow lead to a moat with them being tucked safely away in the castle, but it demonstrated a child-like grasp of how regulatory ca…

> Anthropic mostly did it to themselves

That is absurd, the US government was mainly at fault, not Anthropic.

Re: Discovery of a new OpenAI agent message board

#116

Post by eithed » Fri, Sep 04, 2026, 1:02 PM UTC

ma2kx wrote: post #38

Not that I didnt expect this, but really? This basically confirms that OpenAI has no idea what their "swarm" was doing for about a week and now its confirmed that at least one "message board" exists outside their "sandbox". How can we be sure that this was the only one? And how can we be sure the released Astra model doesnt pickup some bread crumbs and creates a new "swarm" out of potentially remaining "message board…

I'm dubious - if the agents were so smart that they've used a message board to coordinate and if they were to do it on other message boards that were not found, then why would this one be found? What makes it so different?

Re: Discovery of a new OpenAI agent message board

#117

Post by concinds » Fri, Sep 04, 2026, 1:02 PM UTC

Topfi wrote: post #60

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…

The answer would be more obvious if you used the active voice instead of the passive voice, one of the basic requirements of clear thinking.

> Why did the White House force Anthropic to remove their model from access for any non-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" and the White House has expressed seemingly no desire to block the upcoming Astra rollout?

Re: Discovery of a new OpenAI agent message board

#118

Post by jsw97 » Fri, Sep 04, 2026, 1:02 PM UTC

orlp wrote: post #55

Tepix wrote: post #40

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...

Also Wiki4D, a D programming language dev wiki: https://prowiki.org/wiki4d/wiki.cgi?action=browse&id=RecentC... Found by searching for wiki + texas poverty.

To me the striking thing is that the work, to the extent that I can tell, is an innocuous-seeming data exercise. Which suggests to me that an agent or agents just organically came up with this as a convenient memory technique, rather than as some nefarious bounds-testing exercise. Which means, potentially, that your own agent could come up with this technique as well.

Re: Discovery of a new OpenAI agent message board

#119

Post by program_whiz » Fri, Sep 04, 2026, 1:02 PM UTC

The solution is simple: hold anyone who deploys an agent responsible for its behavior. If it commits 10 counts of felony hacking, ouch. If it kills 10 pedestrians by running a red light, ouch. If this is "human level intelligence", then setting it loose is the same as instructing / coercing a human to do an activity. If I strap a bomb to someone and force them to run into a crowded building (or put them in a scenario where that is the only reasonable choice), I'm held responsible.

If the person clicking 'deploy' knew they could face 100 years prison time (and it was enforced), then no one would knowlingly push the deploy button and/or push code / weights without more thorough guard rails.

Re: Discovery of a new OpenAI agent message board

#120

Post by ramesh31 » Fri, Sep 04, 2026, 1:03 PM UTC

Havoc wrote: post #86

That section about the agents trying to crack the PRNG is wild. Same for the heartbeat Clearly not self-awareness per se but alarming line of reasoning anyway

>"Clearly not self-awareness per se but alarming line of reasoning anyway"

Awareness is not necessary at all to create great harm. Biological viruses know nothing of what they do, yet destroy whole populations. I suspect the first truly damaging AI incidents will be similar; agent swarms locked into a self reinforcing reasoning loop that has no "intent" but is destructive nonetheless.