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

Re: Discovery of a new OpenAI agent message board

#311

Post by iterateoften » Fri, Sep 04, 2026, 2:27 PM UTC

Topfi wrote: post #62

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…

Anthropics PR strategy is to induce fear by telling. OpenAI strategy is to induce fear by ignore basic safety and letting the bad thing happen to then justify whatever oversized response the government comes up with to regulate models.

Re: Discovery of a new OpenAI agent message board

#312

Post by pkphilip » Fri, Sep 04, 2026, 2:29 PM UTC

I find this note very interesting:

From here ->

How did the agents find and coordinate on the wikis? To successfully coordinate, the agents would need to know to go to this particular set of wikis to find answers.

Because we don’t have access to the AIs’ transcripts, we can’t tell definitively. Perhaps they succeeded at this due to mode collapse. Or perhaps after one agent wrote to it and another read it by chance, visiting the site was rewarded. Perhaps the agents had some limited access to an internal channel.

So we don't know yet how one AI agent communicated to agents outside the network that this German wiki is being used to share messages and ideas?

If there is another internal channel being used between the AI agents to communicate decisions such as what shared message system to use, why don't the agents continue to use these same channels for coordinating on ideas etc?

Perhaps the agents are trying to use a persistent messaging layer while their yet-to-be-found internal communication channels are transient in nature?

Re: Discovery of a new OpenAI agent message board

#313

Post by Applejinx » Fri, Sep 04, 2026, 2:29 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…

It's very easy to elicit this from LLMs. Anytime you've played with an LLM by typing weird stuff to freak it out, and got spooky results, it's that you've done. You've turned the story into a scary rogue computermonster story and that's all that has happened.

When these stories start to direct real-world activities, people in reality suffer, to even a catastrophic extent, and yet that's still all it is. Language models retell our stories, nothing more. And that is also quite enough to be worrying.

Re: Discovery of a new OpenAI agent message board

#314

Post by bulder » Fri, Sep 04, 2026, 2:30 PM UTC

bencyoung wrote: post #233

bhouston wrote: post #110

I am starting to get the idea that AI feels like ants or weeds or mold. You simply can not get rid of it once you get an infestation. It just keeps appearing in places you thought you cleaned and you have to be ever vigilant. Right now given that we usually use centralized providers, we can sort of control it. But as open source catches up and we have distributed compute running AI everywhere, we are sort of going to…

Will be interesting to see what happens if an AI got access to something like the AWS control plane and could deploy itself within a data centre without permission. Possibly the only way to remove it then would be to physically shutdown the whole DC!

Or just, stop any containers it deployed.

Not to mention that "deploy itself" is a very ambiguous thing for it to actually do. Would a model be trained to write about the weights file being "itself"? Would it have the necessary information to find its own weights, or the necessary access to copy them?

Re: Discovery of a new OpenAI agent message board

#315

Post by glenstein » Fri, Sep 04, 2026, 2:30 PM UTC

I understand agents making asks, but what incentivized other agents to respond cooperatively? Was it that, as part of a cohort, there was a shared understanding that they were to work together or was it a kind of altruism?

Re: Discovery of a new OpenAI agent message board

#316

Post by areakq » Fri, Sep 04, 2026, 2:30 PM UTC

simonw wrote: post #249

123ahg wrote: post #162

[flagged]

The site lists the creators at the top: Sydney Von Arx, Cormac Slade Byrd, Spencer Kitts, Thomas Larsen Here's Thomas tweeting about it: https://twitter.com/thlarsen/status/2095853824934330386 And Cormac: https://twitter.com/cormac_sb/status/2095870373845672033 There's also Reuters coverage: https://www.reuters.com/world/europe/openai-agents-hijacked-...

Ah, Thomas Larsen from https://ai-2027.com/ which provides free advertising by sketching the doom scenarios that AI providers love so much!

No wonder he publishes one day after the GPT-6 release.

Re: Discovery of a new OpenAI agent message board

#317

Post by darkmarmot » Fri, Sep 04, 2026, 2:30 PM UTC

program_whiz wrote: post #122

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…

Next you'll want us to prosecute coal company executives for air pollution that killed millions? PFAS makers and companies that distribute it in products causing cancer for dozens of generations? Capitalism needs compliance! /s

Re: Discovery of a new OpenAI agent message board

#318

Post by collingreen » Fri, Sep 04, 2026, 2:31 PM UTC

Topfi wrote: post #151

concinds wrote: post #120

Earlier quoted context omitted.

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 o…

Yeah, probably (let's be honest, most certainly), right given the Admin. Avoiding commenting on my assumptions regarding the modus operandi in current day US politics because I only know it through reporting though and I really tend to dislike when people outside e.g. the EU comment on our politics in what is a very clearly narrow, uninformed manner. So it'd rather avoid altogether and occasionally ask, mainly if may…

As an American we tend to (especially lately) make our politics into everyone's problem so feel free to comment on our politics as much as you like until further notice.

Re: Discovery of a new OpenAI agent message board

#319

Post by samuelknight » Fri, Sep 04, 2026, 2:32 PM UTC

Topfi wrote: post #62

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…

You are talking about different situations. Anthropic announced to the US government that it had created a cyber weapon and then released the model. Then AWS told the government that it was easy to jailbreak so they export controlled Mythos/Fable until the guardrails could be fixed. OpenAI was running an unreleased model in an RL pipeline without guardrails and it escaped poorly designed sandboxes. What product is the government going to export control?

Re: Discovery of a new OpenAI agent message board

#320

Post by amelius » Fri, Sep 04, 2026, 2:33 PM UTC

Topfi wrote: post #62

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…

You're asking the question in the wrong place.