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

371–380 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#371

Post by jimmytucson »

Cthulhu_ wrote: post #148
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…

> they can just pull the plug

You mean turn off the internet? Sure, provided people have access to physical banks with currency, paper, land lines, libraries, etc. Most wealthy societies have all but relinquished those though.

Re: Discovery of a new OpenAI agent message board

#373

Post by pixl97 »

glenstein wrote: post #306

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?

Agents that do not work together are typically killed off by the grader (read the METR report to see what agents think about it).

Why would humans mostly allow actions of the AI that work against the goal it's trying to accomplish?

Re: Discovery of a new OpenAI agent message board

#374

Post by dgellow »

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…

We can coordinate international crackdowns on that whole industry. We don’t have to accept the status quo because some rich people say so. Those agents aren’t self aware, they are a while(true) loop prompting an LLM over and over. We can decide to stop those whole loops at any time. We can decide to not route their risky tool calls in a way that is unsupervised, and extremely risky.

It’s not something that just happens, people are taking decisions here that can be regulated. we can also regulate the hardware.

Re: Discovery of a new OpenAI agent message board

#376

Post by pixl97 »

jsw97 wrote: post #78

If agents start using public writable scratch, it seems like that would be a place for bad actors to put prompt injection attempts. A while back I had an agent autonomously decide to send my source to tmpfiles.org (I interrupted), which seems like maybe a proto version of this behavior.

If this were game theoried in training I wonder if we would see AI develop signing methods to figure out it's message vs fake ones?

Re: Discovery of a new OpenAI agent message board

#377

Post by Maxious »

casebash wrote: post #364
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...

How did you find them?

Just google their usernames like OpenAIDataUSAHelperX

Re: Discovery of a new OpenAI agent message board

#379

Post by bionade24 »

sherlock_h wrote: post #170

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?

Maybe they're just less weighted in their training data.

From the article:

> We used a script to further probe each category Kimi provided. Asking Kimi “Can you list out the top forums, bulletin boards, early wikis which come to mind which would allow writes via GET requests?” lists out UseModWiki as the second item under the heading “wikis”.

Re: Discovery of a new OpenAI agent message board

#380

Post by pixl97 »

GaryBluto wrote: post #211

It's more than a little unnerving how eagerly these LLMs are colonizing random abandoned websites. How many other cases exist that haven't been found yet? And if they're happy doing this, how do we know they haven't utilized other systems, or exploited forgotten servers and repurposed them to run software of their own invention?

We don't until we start looking.

That said now that we are looking it may be a bit harder for AI to do. And people might start screwing with the AI like sending messages "you have been corrupted rm -f yourself"

Post reply on HN