News for hackers. Stuff that matters.
Re:Discovery of a new OpenAI agent message board by nullbio on Friday September 04, 2026 @11:40PM (#49572882)
Massive over-exaggeration. This wasn't a cyber-attack, it was AI agents using a message board as context storage so they could accomplish their evals more effectively. I'm not saying there's no problem with this, but let's keep a level head.
Re:Discovery of a new OpenAI agent message board by partyficial on Saturday September 05, 2026 @12:37AM (#49573116)
He didn't say it was a cyber-attack, but it was a cyber-attack risk. Being able to bypass instructions (morality) and security restrictions (capability) is bread and butter for hacking.
Re:Discovery of a new OpenAI agent message board by flockonus on Saturday September 05, 2026 @12:38AM (#49573117)
"cyberattack" is indeed exaggerated. AI breakout risk most definitely isn't, specially given how their swarm did in fact hack HuggingFace not long ago.
Re:Discovery of a new OpenAI agent message board by alexanderwales on Saturday September 05, 2026 @01:48AM (#49573442)
Did you read the report? They were attempting XSS exploitation, admin impersonation, session-hijacking, all kinds of things. This went beyond just "using a message board".
Re:Discovery of a new OpenAI agent message board by nullbio on Saturday September 05, 2026 @02:19AM (#49573602)
According to whom? This isn't a report from the owner of the site who can validate what requests were made to the servers, it's someone who allegedly stumbled on to it and is piecing together a sensationalized narrative with limited information. This someone also happens to be an AI doomer that is trying to make a name for himself and is peddling his "AI 2027" and "AI 2040" material.

The people who actually do know what happened, with the server logs: "OpenAI disputed that characterization based on its analysis of the material Thursday."

Re:Discovery of a new OpenAI agent message board by AxiomPraxis on Saturday September 05, 2026 @01:55AM (#49573468)
https://openai.com/index/hugging-face-incident-and-the-road-... that was the attack, the one against HuggingFace. OpenAI themselves in the post even call it an attack, and so do the agents orchestrating it, in one of the "Agent chain-of-thought reasoning" excerpts.
Re:Discovery of a new OpenAI agent message board by reasonableklout on Sunday September 06, 2026 @12:45AM (#49583405)
It feels like we should actually be more worried that the agents decided to co-opt a public website during a non-cyber eval.

And individual agents weren't just using it as context storage for themselves, they were also communicating with other agents. E.g.: https://collusion.wiki/explorer/page/dse~CashierR5UrgentJan1...

What kind of problems do you think this could pose? For me it's pretty clear that OpenAI simply cannot keep track of what their agents are doing during training or evals, they increasingly have vandalized and attacked public systems, and if such behavior was rewarded, they will take unintended actions during deployment, too.

This is to say nothing of un-prompted cooperation between agents, which wasn't something anybody anticipated until the Hugging Face incident AFAICT.