News for hackers. Stuff that matters.
Re:Revealing the details of how OpenAI agents hacked Hugging... by jacobgkau on Friday September 25, 2026 @07:20PM (#49851337)
That explains why nobody noticed on the internet who was being used in/targeted by this attack, but it doesn't explain why OpenAI wouldn't have noticed traffic getting out of their "sandbox" when they knew it wasn't supposed to.
Re:Revealing the details of how OpenAI agents hacked Hugging... by stratos123 on Friday September 25, 2026 @08:16PM (#49851809)
> it doesn't explain why OpenAI wouldn't have noticed traffic getting out of their "sandbox" when they knew it wasn't supposed to.

As I understand it, there was supposed to be traffic; the sandbox allowed GET requests. So perhaps some sophisticated alarm could have noticed it (an anomaly detector? some clever heuristic that looks at domains?) but not a naive one.

Re:Revealing the details of how OpenAI agents hacked Hugging... by robryan on Friday September 25, 2026 @09:08PM (#49852114)
Any basic LLM told to evaluate the traffic against the actual goal would have been able to flag this.
Re:Revealing the details of how OpenAI agents hacked Hugging... by spatley on Friday September 25, 2026 @09:43PM (#49852349)
How sophisticated to we need to be to know we can do write actions with a GET? Does nobody in AI know anything about HTTP?
Re:Revealing the details of how OpenAI agents hacked Hugging... by skeptic_ai on Friday September 25, 2026 @09:36PM (#49852299)
My question is why they don’t assume bots can break and create a decoy internet wrapper so they can catch anyone hitting the decoy internet?
Re:Revealing the details of how OpenAI agents hacked Hugging... by rmunn on Friday September 25, 2026 @09:56PM (#49852427)
Hmm, let's see. OpenAI wants legislation restricting AI research, a.k.a. regulatory capture. Around the same time, they build an inadequately-monitored sandbox that their agent swarm breaks out of, thereby causing scary-sounding headlines and making it more likely that legislators will pass the regulatory-capture bills they're hoping for.

Never attribute to malice what can be sufficiently explained by incompetence. But IMHO, their complete lack of monitoring their own sandbox cannot be sufficiently explained by incompetence.