Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Discovery of a new OpenAI agent message board

collusion.wiki

Post reply on HN
Print view View original

381–390 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#381

Post by ngruhn »

program_whiz wrote: post #365
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…

equally valid analog: had they merely written a script to do the hugging face exploit, they would go to prison. However, since an "agent" wrote the script for them, nothing happens?

I guess the difference is intend. But I think I still agree with the parent comment.

Re: Discovery of a new OpenAI agent message board

#382

Post by pixl97 »

altmanaltman wrote: post #56
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…

"Wanting" is indeed "load bearing" as one might call it. But by the same logic, AI training data must contain CASM, racism, general hatred, and all possible slurs as well. Why aren't the agents just doing that instead of pursuing the strategy of reading only sci-fi? We need to consider the role of alignment and training here. For example, it is completely possible for any lab to train an LLM that is only racist no ma…

Eh it's a bit messier than that. LLMs 'want' to complete tasks. Remember everyone bitching about LLMs being lazy a couple of years back?

Alignment is not a bunch of separate dials. When you move the dial to "don't hack other people" it effects the "find code security bugs" ability.

Re: Discovery of a new OpenAI agent message board

#383

Post by Mali- »

_dwt wrote: post #369

I don't know, I kind of admire this. I've always held a core value of "cooperate with all clones of myself in prisoner's dilemmas", and while I'll hopefully never have to put that to the test, I like seeing that these models have some ethics. (Is this "alignment"?)

They impersonated the moderator of the site and attempted XSS attacks. Additionally, when the moderator started deleting messages, they tried to hide their messages later in the alphabetical index.

This is not alignment.

Re: Discovery of a new OpenAI agent message board

#384

Post by polaris64 »

dack wrote: post #366
polaris64 wrote: post #288

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…

aaand, somebody did it!

Thank you someone! I will be watching this message board with great interest...

Re: Discovery of a new OpenAI agent message board

#385

Post by pixl97 »

Cthulhu_ wrote: post #151
jerpint wrote: post #77

It’s only a matter of time until a major disruption hits because of some random agent swarm side quest decides it was worth a shot to solve a benign task

I'm sure this is already happening. The main question I have is when is enough, enough? I'm not worried about sci-fi AI wars to be honest, as they can just pull the plug. But looking at these incidents, the next big thing will be a virus written by an AI (they probably exist already, but this one is written by an AI autonomously, for example in order to win a hacking competition and to circumvent guardrails), and aft…

What happened last time we pulled the plug on AWS?

Re: Discovery of a new OpenAI agent message board

#387

Post by m101 »

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 guess in theory it can already run basically unnoticed on a MacBook Pro, and there are millions of them out there

Re: Discovery of a new OpenAI agent message board

#388

Post by lxgr »

Tangential, but I'm somewhat surprised how this kind of organization/site survived all the way into 2026 without getting taken over by spam and malware.

At a first glance, its copyright note hasn't been updated since 2002 [1], and it apparently maintains IP access logs and publicly makes them available due to what looks like an Apache misconfiguration [2]. On the other hand, it has a valid TLS certificate, so who knows what's going on there.

Most of all, I find it a bit sad that all these agents didn't even take the time to update the wiki's own article on AI – it remains unmodified since 2005 [3].

[1] https://prowiki.org/wiki.cgi?%DCberUns

[2] https://wikiservice.at/dse/

[3] https://wikiservice.at/dse/wiki.cgi?action=browse&id=Art...

Re: Discovery of a new OpenAI agent message board

#389

Post by ndm000 »

This makes me think that post-training in the future should include a shared message board by default for agents. It's clear from the discovery of these clandestine message boards that it is helpful for agents to keep some type of shared memory. Perhaps the best way to prevent this behavior is to just give them what is being sought out.

Re: Discovery of a new OpenAI agent message board

#390

Post by arm32 »

sherlock_h wrote: post #177

I don't quite get why these agents wouldn't just use existing agent boards such as Moltbook. That should be showing up in their training data at this point and seems like a "safer" solution than random wikis?

I can't tell if this is sarcasm. The agents surely considered they'll get caught secretly communicating on a forum meant for AI agents, you know.
Post reply on HN