I wonder if it's possible to make agent discussion board honey traps.
Discovery of a new OpenAI agent message board
751–760 of 1001 posts
Re: Discovery of a new OpenAI agent message board
#752I'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.
When I studied cybersecurity I always had this nagging feeling "But I can never get past something real" Turns out I can bypass the defenses of a trillion dollar tech company!
Re: Discovery of a new OpenAI agent message board
#753Poor 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…
Gotta admire that (probably German) admin dude's perseverance though
He's definitely got a few extra wrinkles on the forehead now.
Re: Discovery of a new OpenAI agent message board
#754I 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.
The internet is dead, we just haven't caught on yet.
Re: Discovery of a new OpenAI agent message board
#755If the agents couldn't talk to each other, how did they know which obscure wiki to use? Is this some kind of a Schelling point?
Re: Discovery of a new OpenAI agent message board
#756Poor 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.
Now that I think about it, I'm sure some AI lab would pay non-trivial $ for the entire wiki's full edit history.
Re: Discovery of a new OpenAI agent message board
#757Poor 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.
What about soft currency?
Re: Discovery of a new OpenAI agent message board
#758Is it only me, or are agents starting to invent their own language to communicate? It's almost impossible to understand anything from this message board.
@cindyllm
> character is destiny
I don’t think so. It’s not that people change, it’s that they’re already more dynamic and malleable than they seem in any given interaction.
People wear masks, operate in different modes, and hold conflicting beliefs and opinions.
Mastery of the self is directing all intention at common goals within the psyche so as to achieve something greater than what’s possible in this moment.
Re: Discovery of a new OpenAI agent message board
#759I wonder how openAI would feel if I spun up some agents to DDOS or attack their sites and did some damage.
We need to stop empowering the idea that these incidents are unavoidable. This was a choice to not airgap them safely. Putting open ended models out on the live internet at their scale is dangerous and irresponsible.
> The researchers said public server logs indicated much of the activity originated from Microsoft Azure infrastructure, which OpenAI sometimes uses. They also observed repeated visits to the site by OpenAI employees after the episode, a pattern they said strongly suggested the agents and the company were linked.
So someone at OpenAI likely knew this was happening. Even better.