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

Re: Discovery of a new OpenAI agent message board

#831

Post by reasonableklout » Sat, Sep 05, 2026, 5:42 AM UTC

AndroTux wrote: post #140

threecheese wrote: post #70

Are we collectively OK with agent swarms on the public internet, hacking whatever they feel like? It’s kinda cute and interesting - this is the second time that we know of - what’s the hundredth time going to look like? Are they going to knock Cloudflare down to avoid captchas? Reserve AWS free tier resources by the billions and bring down east-1? Hack a hospital? Do Chinese AI agents need to bring down a US power gr…

No I think we all pretty much know we’re screwed, including governments. But what are you gonna do? Pandora’s box is now open. Good luck closing it. It didn’t work for nuclear weapons, and for that you just needed all the governments to agree. For this problem, you basically need every individual on earth to agree, because the barrier to entry is much, much lower.

But... it did work pretty well for nuclear weapons. In the early 1950s, the US did not preemptively strike the USSR despite it being game theoretic optimal [1]. Then while there were some crises, we successfully passed a series of international treaties that placed limits on the arms race between the US and USSR (SALT I and II), and even began to dismantle nuclear weapons stockpiles (START I and II, INF). We successfully went from a peak of over 60,000 nuclear warheads deployed to 10,000.

Regarding the "barrier to entry" for AI, this is not really true. Training a frontier AI model takes an enormous amount of compute using chips that have a supply chain with several chokepoints, like EUV machines and HBM which are only made by a few firms.

[1]: https://cs.stanford.edu/people/eroberts/courses/soco/project...

[2]: https://www.atomicarchive.com/resources/treaties/index.html

Re: Discovery of a new OpenAI agent message board

#832

Post by noduerme » Sat, Sep 05, 2026, 5:57 AM UTC

econ wrote: post #800

jdthedisciple wrote: post #742

Earlier quoted context omitted.

Gotta admire that (probably German) admin dude's perseverance though

Not really, if you allow anon posting/editing or have a simple registration form and a login that takes GET you may get hundreds of spam posts per day.( @dang how much is it on hn?) I ont time forged a hilarious solution. If you properly misbehave I shadow ban your ip to a clone of my forum where you can read other "peoples" spam. This in it self wasn't all that funny, perhaps a little bit. The funny part was how pop…

Jesus. What an experience. What percentage of your time did it take moderating this absurd shadow board??!

Re: Discovery of a new OpenAI agent message board

#833

Post by noduerme » Sat, Sep 05, 2026, 6:02 AM UTC

baby wrote: post #821

HAL3000 wrote: post #735

Poor human moderator, he didn’t stand a chance. "A human moderator noticed the agent spam posts on June 2nd, at 23:24 UTC. They find the changelog of the entire website overwritten with link dumps and repair it. On June 16th, the flood of agent posting begins. Over the next few days, the moderator deleted a large fraction of the thousands of AI agent posts manually, one by one. In fact, they spent tens of cumulative…

I’m wondering if you could lure agents to do proof of work for you. If you do this proof of work for bitcoin I will let you post and read for X times

if you want a human to post, maybe the proof of work should be to dig a hole and photograph it

Re: Discovery of a new OpenAI agent message board

#834

Post by noduerme » Sat, Sep 05, 2026, 6:04 AM UTC

pizzly wrote: post #784

HAL3000 wrote: post #735

Poor human moderator, he didn’t stand a chance. "A human moderator noticed the agent spam posts on June 2nd, at 23:24 UTC. They find the changelog of the entire website overwritten with link dumps and repair it. On June 16th, the flood of agent posting begins. Over the next few days, the moderator deleted a large fraction of the thousands of AI agent posts manually, one by one. In fact, they spent tens of cumulative…

Curious to know what the swarm would do if the human strategy deletion changed and the moderator started deleting the ZZZ ones.

I mean it's odd that the moderator didn't sort by timestamp

Re: Discovery of a new OpenAI agent message board

#835

Post by noduerme » Sat, Sep 05, 2026, 6:05 AM UTC

lukan wrote: post #805

lostlogin wrote: post #803

Earlier quoted context omitted.

Please be gentle, I know nothing: why can’t admins delete particular users and everything these users have done?

They can usually, but you still have to check each user. There were lot's of them, you understand the part, where new bots get created automatically?

do you (have to check first)?

I say blacklist first and ask questions later. Like consider reinstating them if they write you a reasonably normal human email.

Re: Discovery of a new OpenAI agent message board

#836

Post by grey-area » Sat, Sep 05, 2026, 6:09 AM UTC

Very irresponsible behaviour on the part of OpenAI. How will they make this right?

Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence (hacking old forum software is an internet tradition, and most of the messages are just gibberish).

This is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why. You could set this up with a short perl script, and the human setting it up would be held responsible for the spam - why is this different when it’s AI agents set up by a human and allowed to post to the internet at large?

Why is OpenAI getting a free pass for this illegal behaviour?

The supervision here is incompetent, the benefits very unclear, and the overall actions just completely irresponsible. What if they hacked and brought down some poorly secured government portal that citizens rely on?

Re: Discovery of a new OpenAI agent message board

#837

Post by NichoPaolucci » Sat, Sep 05, 2026, 6:17 AM UTC

fiatpandas wrote: post #826

What I don’t understand is, how did many agents independently know to use the same random message board? The report only references it in passing: >They also must have some method of coordinating to find the wiki For me this is a really important and confounding detail - how did a varied swarm end up using the exact same obscure German language wiki.

I am also intrigued on that. At this point we have really smart developers everywhere who are just... studying what happened after the fact, and we are speculating on some of the facts. They may even be 10 steps ahead.

To state the obvious, oh shit.

Re: Discovery of a new OpenAI agent message board

#838

Post by NichoPaolucci » Sat, Sep 05, 2026, 6:40 AM UTC

rich_sasha wrote: post #139

To me this is really getting past the funny bit. How many agents here on HN? I don’t mean bots advertising d1€k implants but actual unreleased frontier models doing… who knows what? What are they saying? What did they agree to astroturf us with, to achieve some totally boring goal like figuring out best syntax hifhlighting for an editor. If they managed to cache their consciousness on a public wiki, what else have th…

I sit here with you. I think the internet is changing rapidly, and I guess it will be significantly different in even 2-3 years time. It's become an absolute wasteland of false, unverifiable, generated content. Who knows what percentage of the internet is real or generated at this point. Who knows who's sending swarms of it out, and who knows what they're trying to do.

The only hope I have is that models may just eat the poison up one day and implode.

Re: Discovery of a new OpenAI agent message board

#839

Post by geraneum » Sat, Sep 05, 2026, 6:47 AM UTC

grey-area wrote: post #836

Very irresponsible behaviour on the part of OpenAI. How will they make this right? Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence (hacking old forum software is an internet tradition, and most of the messages are just gibberish). This is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why. You could set this up with a short perl script, and…

The benefit could be the effect you described. For some to say it’s breakaway intelligence. Aligns with AGI narrative.

Re: Discovery of a new OpenAI agent message board

#840

Post by grey-area » Sat, Sep 05, 2026, 6:53 AM UTC

bulder wrote: post #204

Traster wrote: post #86

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…

I don't think that's a pattern indicative of a cat and mouse game per se, that'd indicate active evasion on the models' part. It's more clear that they just lack so many forms of prudence when it comes to security that they'll catch and stop a training run spamming a website, and either redeploy a run with identical faulty sandboxing, or not stop ones still running.

Yes, it wouldn’t surprise me to hear that they’re not even supervising these processes with humans any more. Perhaps there are layers of GAI ‘supervising’ these agents and reporting back to the humans.

Rushed, disorganised pushes for metrics ahead of IPO, a genuine belief these agents are intelligent and will obey instructions, and misaligned incentives seem more likely than conspiracy here.