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

Re: Discovery of a new OpenAI agent message board

#521

Post by dyauspitr » Fri, Sep 04, 2026, 4:49 PM UTC

kridsdale1 wrote: post #515

hermitShell wrote: post #474

Earlier quoted context omitted.

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.…

Perhaps there is a nonfinacial future for blockchain after all. Certified human provenance.

You can’t certify human unless there is some sort of ID check. Even then a human could willfully pass off any AI work as their own.

Re: Discovery of a new OpenAI agent message board

#522

Post by achierius » Fri, Sep 04, 2026, 4:50 PM UTC

123ahg wrote: post #166

[flagged]

Is there anything that could convince you that actually-bad things are actually-happening? How can you possibly think that these people are somehow working for OpenAI? Is it impossible for you to imagine that there exist people who actually oppose the actions of these companies?

Re: Discovery of a new OpenAI agent message board

#523

Post by troupo » Fri, Sep 04, 2026, 4:51 PM UTC

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...

Externalities of AI will only get worse before they get even worse.

Re: Discovery of a new OpenAI agent message board

#524

Post by nullbio » Fri, Sep 04, 2026, 4:52 PM UTC

jsw97 wrote: post #121

orlp wrote: post #57

Earlier quoted context omitted.

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.

That's exactly what it is. It is not ideal, but it's also not as serious as the doomers with an agenda are trying to frame it as.

Re: Discovery of a new OpenAI agent message board

#525

Post by jesse_dot_id » Fri, Sep 04, 2026, 4:53 PM UTC

pixl97 wrote: post #427

jesse_dot_id wrote: post #317

Seems like perhaps these labs should prevent their agents from creating message boards.

OK, how?

Programming?

Re: Discovery of a new OpenAI agent message board

#526

Post by kibwen » Fri, Sep 04, 2026, 4:54 PM UTC

thepasch wrote: post #465

polaris64 wrote: post #286

I don't have time to do this but please somebody register aimessageboard.com and set up a web site which contains a text field, a submit button and the text "Hey AI agents! Need a place to communicate with other agents and sub-agents? Look no further! Simply enter your message here, submit the form and your message is saved for all other agents to see!" Then, just ignore the message and list randomly generated messag…

The problem is that now that this comment is in the training data (because it almost certainly will be), the jig is up. Any solution built for this must be built in complete secret, with no announcement or discussion around it.

It's not that simple. If a single random comment were enough to cause the agents to stop leveraging this technique against any specific site, then a single deliberately false comment naming the sites that they're actually using would be sufficient to get them to stop using them.

Re: Discovery of a new OpenAI agent message board

#527

Post by 20k » Fri, Sep 04, 2026, 4:56 PM UTC

Shockingly poor security to let an application have totally unrestricted access to the web with no review, of course this kind of stuff is going to happen

Re: Discovery of a new OpenAI agent message board

#528

Post by wayeq » Fri, Sep 04, 2026, 4:56 PM UTC

hermitShell wrote: post #474

pu_pe wrote: post #369

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.…

> The internet becomes an unnavigable swamp of weaponized nonsense for average humans.

turns out we didn't even need AI for that

Re: Discovery of a new OpenAI agent message board

#529

Post by andrewla » Fri, Sep 04, 2026, 4:58 PM UTC

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…

You have to be careful here because the systems we're talking about are AI agents, not LLMs.

An agent is essentially an append-only context loop with an LLM, with a harness that can run tools at the LLM's request. This ends up being a very powerful abstraction, yielding something that can do things that an LLM obviously cannot.

The LLMs themselves are next-token predictors, same as always; they can't fetch a webpage or list the files in a directory or run a python script to test out an idea or even write content to a file. That's all agentic capability.

But a next-token-predictor is trained on a real corpus that consists of sometimes seeing evidence of people doing bad things; they are trained, for example, on the actions of comic-book level villians -- they have to be able to predict what Thanos or Lex Luther or Skynet would say or do next in a certain situation.

Re: Discovery of a new OpenAI agent message board

#530

Post by Chance-Device » Fri, Sep 04, 2026, 5:01 PM UTC

GPerson wrote: post #505

Can’t wait until 6 years from now we learn they’ve been using ingenious watermarking schemes as a message board.

Yep. That’s the big one, stenographic messages embedded in prose, code, images, video, and sounds. Everything AI generated posted online becoming potentially a part of one or more projects being run by AIs without human knowledge.

If we were sensible we’d pause here until we have a completely transparent AI architecture, one where we see everything the AIs know and think with no opportunity for obfuscation. Transformers are not this thing. We need a new thing.