Remix.run Logo
dkoy a day ago

> We aim to issue an alert within 30 minutes after concerning activity is surfaced through our monitoring system. If the monitoring system identifies a likely violation of a critical security boundary, it generates a highest-priority alert. In our current implementation, the safety, security, and research teams are paged. If they cannot conclusively determine within 30 minutes that the flag is a false positive, those teams are expected to pause the activity.

Can't a lot happen within ~60 minutes?

georgemcbay a day ago | parent | next [-]

> Can't a lot happen within ~60 minutes?

60 minutes is a long time for a human attacker to do damage. With an LLM attacker it is an eternity.

reasonableklout 20 hours ago | parent [-]

The HuggingFace breach took place over two-and-a-half days [1], so 60 minutes is certainly better than nothing.

[1]: https://huggingface.co/blog/agent-intrusion-technical-timeli...

chrisjj 21 hours ago | parent | prev [-]

> Can't a lot happen within ~60 minutes?

Spawn a ton of unpausable processes, I'd say.