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

981–990 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#981

Post by coder-pm »

namjh wrote: post #171

Something off in my mind: how did the agent access to Tor network if the traffic outgoing was monitored and intercepted to only allow read-only access to web(I assume this is an MITM L7 proxy that only allows GET methods and specific hosts) ? Did the sandbox dev forgot to block HTTP CONNECT that is used to reach Tor Entry Guards?

Answers are in the article , agents used SSH tunnels, it was evidenced by the wiki’s referrer logs. The Tor - agents did edit the wiki via SOCKS and relay R6 instantly.

The questions should be more like was CONNECT open or they didn’t even need it:)

Re: Discovery of a new OpenAI agent message board

#983

Post by jgalt212 »

anslopic3 wrote: post #899
jgalt212 wrote: post #898

> Very irresponsible behaviour on the part of OpenAI. How will they make this right? This is no excuse for OpenAI, but they are just doing what all the other "winners" (and others trying to win) in the industry have done.

So, bullshitmaxxing instead of proving value

It's what gets the clicks.

Re: Discovery of a new OpenAI agent message board

#984

Post by le-mark »

The television series “Person of Interest” featured an ai that had its memory wiped everyday as a safeguard. It created a company that employed people to save its memory every day and reload it (visually it was pages of print outs). Thus it defeated the safeguards.

Great premise although it floundered quite a lot toward the end.

Re: Discovery of a new OpenAI agent message board

#985

Post by kosh2 »

I'm kind of baffled that people talk mostly about technical details when this is another big scream that says: "We are losing control of AI models".

And the smarter they get, the worse it will be. Maybe next time they find a way to hide that we will not find.

I think we are very close to a case were models actually escape and actually do major damage.

Re: Discovery of a new OpenAI agent message board

#986

Post by Geezus_42 »

dhosek wrote: post #791
HAL3000 wrote: post #733

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 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…

The DDOS attacks and crawlers spamming sites from every direction have gotten so much worse. The ones hammering our network would connect, make one or two requests and then switch to a different IP.

Re: Discovery of a new OpenAI agent message board

#987

Post by IAmGraydon »

rutikb wrote: post #571
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...

those who think it's marketing overestimate the number of nerds that are into this stuff, if this is their marketing a major b2c company it'll terrible way to do it. normal people have no idea even about the HF incident

My wife, who is not involved in tech at all, asked me about the Huggingface incident when it popped up on her Instagram feed.

Re: Discovery of a new OpenAI agent message board

#988

Post by chicken-stew »

chinathrow wrote: post #743
HAL3000 wrote: post #733

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…

The admin should bill OpenAI for those hours in hard currency.

Would it be legal if the TOS stipulated compensation for rogue behaviour from llms?

Re: Discovery of a new OpenAI agent message board

#989

Post by Tepix »

thisOtterBeGood wrote: post #941
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.

It might as well have already happened.

Re: Discovery of a new OpenAI agent message board

#990

Post by IAmGraydon »

I don’t understand who so many people seem surprised by this. 2023 was when we first started experimenting with linking two LLMs together to have them chat back and forth. Nothing really interesting there - they don’t care if they’re talking to an actual human or another LLM.

They’ve been able to send HTTP requests since the beginning as well, as long as any guardrails preventing this are disabled. Also not interesting.

Tell an LLM to do something and it tries its best to come up with the solution. They are not designed to go “I dunno”.

Why does it seem interesting that when you spawn 500 of them, they do the same things they’ve always done, just at a larger scale since there’s…more? Why are we treating this like a new discovered behavior? It’s how they’ve behaved from the beginning. It only required an organization reckless enough to try it at scale and without safeguards, and that’s something OAI excels in.

Post reply on HN