logoalt Hacker News

noslenwerdna • today at 1:01 PM • 2 replies • view on HN

Genuinely curious, where have you been reading that? How would they be able to evaluate whether the sandboxes were reasonable or not?


Replies

vmg12 • today at 1:14 PM

Artifactory is not a hardened piece of software meant for adversarial workloads like the one OpenAI was using it for. This is just common sense. The sandbox they setup was like putting their AI in a jail but allowing it to leave the jail on its own to go to the convenience store.

The most recent DNS sandbox escape is similarly ridiculous.

nicce • today at 1:15 PM

Lot's of hints in the Wikipedia page: https://en.wikipedia.org/wiki/OpenAI%E2%80%93HuggingFace_inc...

E.g. even the basic thing (block the internet), was not actually properly blocked.

Some comments: https://techcrunch.com/2026/07/22/how-an-openais-human-mista...