Post #3998017
2026-07-21 20:41 UTC
OpenAI accidentally hacks Hugging Face. But it's more wild than that https://openai.com/index/hugging-face-model-evaluation-security-incident/
OpenAI was running an exploit test system in a sandbox. Their model determined that probably Hugging Face had model information that would be useful to complete the task, so it broke out of its sandbox, developed an exploit, broke into Hugging Face to go rooting around for information
Replies (3)
-
@un_bourguignon@piaille.fr 2026-07-21 20:57
@cwebber@social.coop How the fuck an "ai" can escape by itself a sandbox (controled environnement) ? Are the human techs in openai this dumb ?
-
@shauna@social.coop 2026-07-22 03:31
@cwebber@social.coop I feel like OpenAI is going for "our models are so smart!" but what it's giving is "our sandboxing is so incompetent!"
-
@cwebber@social.coop 2026-07-21 20:42
Meanwhile Linux publishes 432 Linux kernel CVEs https://lore.kernel.org/linux-cve-announce/ There is only one path out of this. We need a *fully auditable, formally verified, and human-understandable* capability-secure trusted computing base as the foundation of our operating systems. Otherwise... we're just toast.