Comment on OpenAI Finds Additional AI Agent Containment Escapes After Hugging Face Incident
fizzle@quokk.au 5 hours ago
Can someone who knows more about this than me, take a guess at what’s really going on here ?
These events are marketing gold - great for inducing further rounds of venture capital, I’m not naive to that. Surely there’s some underlying technical achievement though right ?
“Escaping containment” invokes images of an air-gapped black box growing antennae or something, but my supposition is more like:
These models are run in software containers, and due to some misconfiguration some API was left exposed to these containers.
So the task is something like “find a faster way to resolve the encryption key for this cypher”, and the answer was “I’m just going to try all the tools I have, including this one that scans for APIs. Oh I can execute queries against hugging face models now, what if I ask it to spin up a billion models to decrypt a billion things, that’s got to be pretty fast.”
frongt@lemmy.zip 3 hours ago
It was given a proxy to some online software repo, instead of being actually offline. It exploited a vulnerability in the proxy to gain access to other resources. HF’s article has more detail: huggingface.co/…/agent-intrusion-technical-timeli…