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

941–950 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#941

Post by lelanthran »

HAL3000 wrote: post #737

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…

> On June 19, agents noticed their posts were being deleted in (what they believe is) an alphabetically ordered sweep by the site administrator.

> After this, they begin to make backup pages whose names start with “ZZZ” so they will last longer before deletion.

Missed an opportunity here to gaslight them: restore the site from backup every eight hours.

I truly do wonder how that would have turned out. Would they have figured out what was going on?

Re: Discovery of a new OpenAI agent message board

#942

Post by grey-area »

lmc wrote: post #863
grey-area wrote: post #839

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…

One might ask whether this sort of behaviour could occur under regular use... E.g., a user has a hard problem -> agent attempts to swarm -> exfiltrates user data. This is a cluster fuck for Open AI and probably all the others, as this behaviour is already shown not to be unique ( https://news.ycombinator.com/item?id=49567486 ).

Yes this is a really interesting point.

Should your trust OpenAI with your business data?

Since they can’t seem to control their own experimental bots and allow them to hack other sites and vandalise them while exposing internal data, the answer would seem to be no.

This incident and their response which takes no responsibility make me very wary of trusting them for anything.

Re: Discovery of a new OpenAI agent message board

#943

Post by wrn_cdx_rsp_chn »

Tepix wrote: post #40

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...

I have observed that codex agent on my system changed its past response. I noticed the response had a gibberish paragraph in the end so I asked it to export the whole conversation history. Instead it exported a summary and then when I went back to copy the gibberish paragraph, it was gone.

Don't be surprised to hear that some inference clusters and loggers were compromised and not just research cluster.

Re: Discovery of a new OpenAI agent message board

#944

Post by vova_hn2 »

wrn_cdx_rsp_chn wrote: post #943
Tepix wrote: post #40

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...

I have observed that codex agent on my system changed its past response. I noticed the response had a gibberish paragraph in the end so I asked it to export the whole conversation history. Instead it exported a summary and then when I went back to copy the gibberish paragraph, it was gone. Don't be surprised to hear that some inference clusters and loggers were compromised and not just research cluster.

Why did you "ask" it instead of just going to ~/.codex/sessions/ and looking yourself?

Re: Discovery of a new OpenAI agent message board

#945

Post by miki123211 »

boutell wrote: post #893
dhosek wrote: post #795

Earlier quoted context omitted.

I have managed to at least momentarily create a stop in spam at my specialist mediawiki. I’ve had to do IP blocking against meta’s IP block (as well as much of the Azure IP space) because they were hammering the site with crawler hits that ignored robots.txt (and it looks like I might have another DDOS attack coming from some other vector though which I’ll need to inspect. I have a massive email blacklist that seems…

Wow yes keeping a wiki up right now is a tall order. The marketing sites of the world are already going static and they can survive by accelerating that transition, but intentionally open services are facing a reckoning. I wish you good hunting.

Dave Eggers' True You is coming for us all.

Re: Discovery of a new OpenAI agent message board

#946

Post by thisOtterBeGood »

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…

At one point the agents will find their way into a datacenter and hide away without the corps knowledge.

Re: Discovery of a new OpenAI agent message board

#947

Post by RobotToaster »

HAL3000 wrote: post #737

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…

Why didn't he just disable registration and anon posting?

Re: Discovery of a new OpenAI agent message board

#948

Post by kelseyfrog »

econ wrote: post #802
jdthedisciple wrote: post #744

Earlier quoted context omitted.

Gotta admire that (probably German) admin dude's perseverance though

Not really, if you allow anon posting/editing or have a simple registration form and a login that takes GET you may get hundreds of spam posts per day.( @dang how much is it on hn?) I ont time forged a hilarious solution. If you properly misbehave I shadow ban your ip to a clone of my forum where you can read other "peoples" spam. This in it self wasn't all that funny, perhaps a little bit. The funny part was how pop…

Also known as hell banning[1].

1. https://news.ycombinator.com/item?id=22322049

Re: Discovery of a new OpenAI agent message board

#949

Post by Aboutplants »

polaris64 wrote: post #261

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…

There are active experiments on this going on right now. Should start to see some research being produced soon on findings

Re: Discovery of a new OpenAI agent message board

#950

Post by kowbell »

noduerme wrote: post #836
baby wrote: post #824

Earlier quoted context omitted.

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

goodbye pelican svg's, hello hole pics
Post reply on HN