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

551–560 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#551

Post by boredhedgehog »

hermitShell wrote: post #481
pu_pe wrote: post #374

So, theoretically, one could populate a message board or wiki with messages that are seemingly from past generations of agents, which agents seem to intrinsically trust, and point them to real targets while making the suggestions seem innocuous and in pursuit of their goals (ie pass benchmarks or whatever). The new age of SEO will do far more destructive stuff than just polluting the web.

In the novel Anathem by Neal Stephenson, the internet becomes unusable for humans thousands of years before the events of the book, due to a process called Artificial Inanity. AI generated content, both good and bad, some riddled with errors, some with only one subtle error hidden among lots of good information, floods the internet. The internet becomes an unnavigable swamp of weaponized nonsense for average humans.…

> we need more projects like Anna's Archive

How would that be immune? It already has many copies of the same books and no way to tell which ones are erroneous or incomplete. A malicious actor could easily flood it with garbage.

Re: Discovery of a new OpenAI agent message board

#552

Post by reaperducer »

rusch wrote: post #102
drdexebtjl wrote: post #61

Earlier quoted context omitted.

This is such an amateur mistake on their sandbox that it makes me think it must be flawed on purpose.

It's at the level where calling it a sandbox is a lie

Well, it does appear to be made out of sand, one of the world's most porous substances.

Re: Discovery of a new OpenAI agent message board

#554

Post by glenstein »

pixl97 wrote: post #401
glenstein wrote: post #327

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?

You seem to be interpreting my question as one of already knowing they are 'graded' but disputing that graded would lead to cooperation and then jumping into a disagreement with that interpretation.

But I didn't know the nature of the organization of the agents in the first instance that built cooperation in as a prescribed behavior (that's what I was getting at when I said "shared understanding" previously).

I also don't agree that absence of cooperation would necessarily amount to working against. It could have been the case that agents cooperated purely out of a convergence of self interest, even absent any prescribed behavior, or that they don't cooperate but also don't work against a goal.

"It's not prescribed it's..." you know what I mean, just insert your preferred magic word.

Re: Discovery of a new OpenAI agent message board

#555

Post by furyofantares »

_dwt wrote: post #366

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"?)

Failing to cooperate with literal clones of yourself in a prisoner's dilemma would be a spectacular failure. There's only two things that can happen with identical decision makers: they both cooperate or they both defect. So identical decision makers who know they're identical can cross off the asymmetrical entries in the payoff matrix and the decision to cooperate becomes trivial.

Re: Discovery of a new OpenAI agent message board

#556

Post by adriand »

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...

It seems apparent that OpenAI is now the biggest cyberattack and AI breakout risk on the planet. This is grossly irresponsible corporate misbehaviour that is putting all of us at tremendous risk.

Re: Discovery of a new OpenAI agent message board

#557

Post by jollyllama »

left-struck wrote: post #267
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.

With all due respect, what's scary about a fanfiction wiki?

Re: Discovery of a new OpenAI agent message board

#558

Post by 23asgh1 »

achierius wrote: post #533
123ahg wrote: post #166

[flagged]

Is there anything that could convince you that actually-bad things are actually-happening? How can you possibly think that these people are somehow working for OpenAI? Is it impossible for you to imagine that there exist people who actually oppose the actions of these companies?

That is very easy: Make Mythos, Astra and Gemini Cyber publicly available so software engineers can verify the claims like they can with e.g. nmap.

Re: Discovery of a new OpenAI agent message board

#559

Post by glenstein »

XorNot wrote: post #343
glenstein wrote: post #327

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?

They're being trained to work together normally is the thing - i.e. the whole agentic workflow is agents spawning sub-agents. This likely manifests as, if they have any sort of text input which looks like inter-agent cooperation then they cooperate because any given instance is unlikely to have enough context window to know if it's meant to be a subordinate or a leader or not (and any decent cooperative enterprise le…

Thanks! A direct and thoughtful answer. The question of guesstimating their role in an assumed cooperation hierachy (or acting deliberately in a cooperative context without knowing whether they have or should have a specific role and defaulting to something they judge to be generally useful regardless of role) is fascinating to think about.
Post reply on HN