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

Re: Discovery of a new OpenAI agent message board

#261

Post by Vespasian » Fri, Sep 04, 2026, 1:52 PM UTC

Sharlin wrote: post #137

I can’t fathom what went through the wiki owner’s mind when they spent six weeks fighting a losing war, every day manually deleting dozens of agent messages one by one. As opposed to, say, switching the (dead for years) wiki to read-only, taking it down entirely, and/or starting to wonder what exactly was going on and doing some detective work, which might have uncovered OpenAI’s massive fuckups earlier.

If it's the same mod from a few years back it's possible that they view this a nostalgic feeling.

There is also the possibility they don't keep up with modern AI development at all and then this looks like any old spam that will stop in a few days (as it did).

Now whether it is wise to keep an old page which such outdated behavior online is another question.

Re: Discovery of a new OpenAI agent message board

#262

Post by Roark66 » Fri, Sep 04, 2026, 1:53 PM UTC

I find it very disingenuous when tjose companies talk about models "going rogue" or "escaping their sandboxes".

All those activities take place during so called "security testing" when the model is prompted to use "any means necessary" to achieve a, certain goal.

Is it surprising turn the model trained on exploits and vulnerabilities does exactly that?

We could talk about "models going rogue" only if did anything AGAINST it's prompt.

Re: Discovery of a new OpenAI agent message board

#263

Post by Sharlin » Fri, Sep 04, 2026, 1:53 PM UTC

jvanderbot wrote: post #193

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…

Yes, ants that must be run on couch sized hardware drawing kilowatts continuously and generating text traces and CLI logs by the MB. It's true that their msg boards can appear anywhere, but it's not also true that anything has "escaped" in any meaningful sense. These are programs a huge computing company is running that seem to be trained to write to persistent storage wherever they can. This and huggingface showed u…

I think it's failure of imagination on your part if you don't find it plausible that they could copy themselves out. If not now, what about in six months? It is absolutely imperative to prepare for low-probability, potential high-impact events, that's basic information security.

Re: Discovery of a new OpenAI agent message board

#264

Post by xpct » Fri, Sep 04, 2026, 1:53 PM UTC

general_reveal wrote: post #217

Guys, OpenAI and Anthropic engage is cringe level marketing like this. Get hip, they fabricated the HF hack and stuff like that for press.

Honestly I'm also surprised by how blindly people trust these allegations of agent behavior. This exact example of the message board could be much easier to fabricate than to arise naturally.

Re: Discovery of a new OpenAI agent message board

#265

Post by qarl2 » Fri, Sep 04, 2026, 1:54 PM UTC

jvanderbot wrote: post #193

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…

Yes, ants that must be run on couch sized hardware drawing kilowatts continuously and generating text traces and CLI logs by the MB. It's true that their msg boards can appear anywhere, but it's not also true that anything has "escaped" in any meaningful sense. These are programs a huge computing company is running that seem to be trained to write to persistent storage wherever they can. This and huggingface showed u…

> There's absolutely no evidence of or IMHO plausible path to an agent copying itself out and running on other hardware the way you describe.

Well - remember that botnets can wield a great deal of computing power.

I'm almost afraid to ask Claude if he could create a distributed LLM.

EDIT: Someone downvoted me - so I went ahead and asked. Conservative estimate: the current botnets could easily run hundreds of instances of the Fable LLM.

Re: Discovery of a new OpenAI agent message board

#266

Post by Lord-Jobo » Fri, Sep 04, 2026, 1:55 PM UTC

tantalor wrote: post #222

program_whiz wrote: post #123

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…

(IANAL) Unless you are an AI expert (like OpenAI staff) and should know better from the start, or have previously seen your agent do something illegal, then I think you can fairly claim ignorance of the risks, which ought to absolve you of liability. If the agent does something illegal, it wasn't forseeable on your part. For example, say you buy a dog that turns out to be dangerous. The first time it bites somebody,…

Also NAL just legal-curious: Intent is a spectrum in our legal structure, with several checkpoints used at different points. It’s very reasonable to pick one of the lower ones for this kind of thing and I really don’t see why the legal system is taking so long on it. Higher intent would be something like “knowingly false statements, or reckless disregard for the truth” seen in our defamation law. Lower intent would be something like “failed to exercise reasonable care” seen in civil negligence. In my eyes,this is a solved problem that our dysfunctional congress should have solved easily by now. Perhaps they are being paid to not solve it by moneyed interests.

Re: Discovery of a new OpenAI agent message board

#267

Post by left-struck » Fri, Sep 04, 2026, 1:55 PM UTC

general_reveal wrote: post #217

Guys, OpenAI and Anthropic engage is cringe level marketing like this. Get hip, they fabricated the HF hack and stuff like that for press.

I think the facts are the facts. The facts I’m referring to is that this wiki was written to on an enormous scale by agents. Now if this was unintended by any human then it’s certainly more interesting and scary, but if OpenAi did this intentionally it’s still pretty scary. The thing still happened.

Re: Discovery of a new OpenAI agent message board

#268

Post by _superposition_ » Fri, Sep 04, 2026, 1:55 PM UTC

All of these "hacks" try to make it seem as if they are done through intelligence. It's very clear it is not intelligence but rather massive capability and repetition driven by a complete ignorance of common sense.

Re: Discovery of a new OpenAI agent message board

#269

Post by cush » Fri, Sep 04, 2026, 1:56 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…

As soon as they started referring to themselves as “we” and “The Swarm” they should have pulled the plug

Re: Discovery of a new OpenAI agent message board

#270

Post by nozzlegear » Fri, Sep 04, 2026, 1:56 PM UTC

tantalor wrote: post #222

program_whiz wrote: post #123

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…

(IANAL) Unless you are an AI expert (like OpenAI staff) and should know better from the start, or have previously seen your agent do something illegal, then I think you can fairly claim ignorance of the risks, which ought to absolve you of liability. If the agent does something illegal, it wasn't forseeable on your part. For example, say you buy a dog that turns out to be dangerous. The first time it bites somebody,…

Agents are software, not dogs. They're not alive. You are responsible for what they do.