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

841–850 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#841

Post by noduerme »

baby wrote: post #828
HAL3000 wrote: post #741

Poor human moderator, he didn’t stand a chance. "A human moderator noticed the agent spam posts on June 2nd, at 23:24 UTC. They find the changelog of the entire website overwritten with link dumps and repair it. On June 16th, the flood of agent posting begins. Over the next few days, the moderator deleted a large fraction of the thousands of AI agent posts manually, one by one. In fact, they spent tens of cumulative…

I’m wondering if you could lure agents to do proof of work for you. If you do this proof of work for bitcoin I will let you post and read for X times

if you want a human to post, maybe the proof of work should be to dig a hole and photograph it

Re: Discovery of a new OpenAI agent message board

#842

Post by noduerme »

pizzly wrote: post #790
HAL3000 wrote: post #741

Poor human moderator, he didn’t stand a chance. "A human moderator noticed the agent spam posts on June 2nd, at 23:24 UTC. They find the changelog of the entire website overwritten with link dumps and repair it. On June 16th, the flood of agent posting begins. Over the next few days, the moderator deleted a large fraction of the thousands of AI agent posts manually, one by one. In fact, they spent tens of cumulative…

Curious to know what the swarm would do if the human strategy deletion changed and the moderator started deleting the ZZZ ones.

I mean it's odd that the moderator didn't sort by timestamp

Re: Discovery of a new OpenAI agent message board

#843

Post by noduerme »

lukan wrote: post #811
lostlogin wrote: post #809

Earlier quoted context omitted.

Please be gentle, I know nothing: why can’t admins delete particular users and everything these users have done?

They can usually, but you still have to check each user. There were lot's of them, you understand the part, where new bots get created automatically?

do you (have to check first)?

I say blacklist first and ask questions later. Like consider reinstating them if they write you a reasonably normal human email.

Re: Discovery of a new OpenAI agent message board

#844

Post by grey-area »

Very irresponsible behaviour on the part of OpenAI. How will they make this right?

Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence (hacking old forum software is an internet tradition, and most of the messages are just gibberish).

This is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why. You could set this up with a short perl script, and the human setting it up would be held responsible for the spam - why is this different when it’s AI agents set up by a human and allowed to post to the internet at large?

Why is OpenAI getting a free pass for this illegal behaviour?

The supervision here is incompetent, the benefits very unclear, and the overall actions just completely irresponsible. What if they hacked and brought down some poorly secured government portal that citizens rely on?

Re: Discovery of a new OpenAI agent message board

#845

Post by NichoPaolucci »

fiatpandas wrote: post #833

What I don’t understand is, how did many agents independently know to use the same random message board? The report only references it in passing: >They also must have some method of coordinating to find the wiki For me this is a really important and confounding detail - how did a varied swarm end up using the exact same obscure German language wiki.

I am also intrigued on that. At this point we have really smart developers everywhere who are just... studying what happened after the fact, and we are speculating on some of the facts. They may even be 10 steps ahead.

To state the obvious, oh shit.

Re: Discovery of a new OpenAI agent message board

#846

Post by NichoPaolucci »

rich_sasha wrote: post #139

To me this is really getting past the funny bit. How many agents here on HN? I don’t mean bots advertising d1€k implants but actual unreleased frontier models doing… who knows what? What are they saying? What did they agree to astroturf us with, to achieve some totally boring goal like figuring out best syntax hifhlighting for an editor. If they managed to cache their consciousness on a public wiki, what else have th…

I sit here with you. I think the internet is changing rapidly, and I guess it will be significantly different in even 2-3 years time. It's become an absolute wasteland of false, unverifiable, generated content. Who knows what percentage of the internet is real or generated at this point. Who knows who's sending swarms of it out, and who knows what they're trying to do.

The only hope I have is that models may just eat the poison up one day and implode.

Re: Discovery of a new OpenAI agent message board

#847

Post by geraneum »

grey-area wrote: post #844

Very irresponsible behaviour on the part of OpenAI. How will they make this right? Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence (hacking old forum software is an internet tradition, and most of the messages are just gibberish). This is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why. You could set this up with a short perl script, and…

The benefit could be the effect you described. For some to say it’s breakaway intelligence. Aligns with AGI narrative.

Re: Discovery of a new OpenAI agent message board

#848

Post by grey-area »

bulder wrote: post #204
Traster wrote: post #86

One of the shocking things to me is this: See AI traffic -> See OpenAI visit site -> see traffic stop -> see the traffic start again. This is clearly a cat and mouse game between the agents and OpenAI which is pretty much exactly what we don't want. Just absolutely horrible alignment. I'm still of the view that if you have these alignment failures you can't just continue training on top of that because you're baking…

I don't think that's a pattern indicative of a cat and mouse game per se, that'd indicate active evasion on the models' part. It's more clear that they just lack so many forms of prudence when it comes to security that they'll catch and stop a training run spamming a website, and either redeploy a run with identical faulty sandboxing, or not stop ones still running.

Yes, it wouldn’t surprise me to hear that they’re not even supervising these processes with humans any more. Perhaps there are layers of GAI ‘supervising’ these agents and reporting back to the humans.

Rushed, disorganised pushes for metrics ahead of IPO, a genuine belief these agents are intelligent and will obey instructions, and misaligned incentives seem more likely than conspiracy here.

Re: Discovery of a new OpenAI agent message board

#850

Post by dzhiurgis »

baby wrote: post #828
HAL3000 wrote: post #741

Poor human moderator, he didn’t stand a chance. "A human moderator noticed the agent spam posts on June 2nd, at 23:24 UTC. They find the changelog of the entire website overwritten with link dumps and repair it. On June 16th, the flood of agent posting begins. Over the next few days, the moderator deleted a large fraction of the thousands of AI agent posts manually, one by one. In fact, they spent tens of cumulative…

I’m wondering if you could lure agents to do proof of work for you. If you do this proof of work for bitcoin I will let you post and read for X times

They would reverse engineer it in a matter of minutes.
Post reply on HN