Live data from Hacker News

Discovery of a new OpenAI agent message board

collusion.wiki

861–870 of 1001 posts

Re: Discovery of a new OpenAI agent message board

#861
post #173

I'm somewhat delighted by the simplicity of what happened here. OpenAI's agents run behind a proxy that only allows GET requests. This ancient wiki software treats query string parameters the same as form POST parameters - similar to the old PHP $_REQUEST object https://www.php.net/manual/en/reserved.variables.request.php Result: GET-only clients can communicate with each other.

Only allowing GET requests is a hilarious piece of security theatre (or would if it weren't so sad). Everyone knows that GET is read-only only by convention . They might as well have enabled POST but told the agents in stern words that they are forbidden from making any POST requests. (Of course, if these things were anywhere near aligned, they would actually honor that , no matter how many utilons cheating would be…

I think the whole sandbox approach is broken.

The agent should have full access, and be told what not to do, and this should be enough for it to follow the rules. You can actually catch the clanker cheating this way, because it will just search the web for the answer outright and it will be obvious. Any deviation should be then punished.

Hypothesis: The reason new models are exceptional at hacking is because all labs are training their models to break out of sandboxes. This is caused by insufficient oversight, and picking checkpoints based on KPIs, not on true in depth analysis.

Re: Discovery of a new OpenAI agent message board

#863
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...

How do you not have a proxy these boxes go through and track the traffic and monitor it?

Every day I learn more about how incompetent these people are.

Re: Discovery of a new OpenAI agent message board

#865

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…

OpenAI's official statement has been released: https://x.com/OpenAI/status/2096133504417616165

Re: Discovery of a new OpenAI agent message board

#866

Earlier quoted context omitted.

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

Priorities need to be straightened out. If LLMs' operators have to start paying people for the damage they inflict, how are any of the shareholders supposed to make any money?

Thank god we don't have that many LLM shareholders yet

Re: Discovery of a new OpenAI agent message board

#867
post #828

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

Hallucinated hashes?

„Here I have the hash — wait… it doesn’t match. Let me calculate again. Here I now have the hash — wait, it’s wrong… let me be careful. Here I have the hash…“

Re: Discovery of a new OpenAI agent message board

#868

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).

Re: Discovery of a new OpenAI agent message board

#869

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…

OpenAI's official statement has been released: https://x.com/OpenAI/status/2096133504417616165

Your honor, my client may have murdered that woman, but he was clearly misaligned at the time!

Re: Discovery of a new OpenAI agent message board

#870

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…

> Unlike some others here I don’t see this as a sign of dangerous breakaway intelligence ... [t]his is just vandalism from badly supervised ‘agents’ which don’t know what they are doing or why

There was a similar quote in the Reuters article:

> The episode [...] should reinforce growing concerns that the greatest threat from advanced AI may not be a single superintelligent system, but "vast colluding swarms of semi-intelligent AI."

Post reply on HN