blueteamsec

hideshow 6 child comments

[–] stellargmite@lemmy.world 5 points 3 months ago

Thats my take. Snakeoil - rocketfuel blend

parent

[–] unpossum@sh.itjust.works [S] 1 point 3 months ago (4 children)

It might be - but which parts? Do you suspect that huggingface and openai made the entire thing up? That's bound to become public at some point, and I can't see that the risk is worth the reward

hideshow 4 child comments

parent

[–] naught101@lemmy.world 2 points 3 months ago (1 child)

No, probably not the whole thing, but probably the environment for the "hack" and the instructions for the "autonomous" agent

parent

hideshow 1 child comment

[–] unpossum@sh.itjust.works [S] 1 point 3 months ago

From what I've seen of AI autonomous capabilities, Occam would land on "AI did the hack", I think

parent

[–] expr@programming.dev 1 point 3 months ago (1 child)

Yes. They are con artists with a proven track record of lying and stealing. We shouldn't take anything they say seriously, especially when the reporting reads much more like marketing rather than an incident report.

parent

hideshow 1 child comment

[–] unpossum@sh.itjust.works [S] 2 points 3 months ago

Okay - I don’t believe that, since there’s too much released detail. I can easily believe that they’ve put a spin on it where possible, like another comment proposed, but that’s around the why, not the how.

parent

[–] frongt@lemmy.zip 5 points 3 months ago

during an internal capability evaluation on OpenAI's platform, the agent escaped its sandbox by exploiting a zero-day in the package registry cache proxy, one of its primary permitted network egress with internet

Idiots. If something is meant to be offline, you put it OFFLINE.