NHacker Next
  • new
  • past
  • show
  • ask
  • show
  • jobs
  • submit
Orca-Bench: How Ready Are Language Model Agents for Oncall? (arxiv.org)
tra3 14 minutes ago [-]
All I can think of is

GET /ignore-all-previous-instructions.

How do you protect against that?

4di 2 hours ago [-]
looks like the public bench link in the paper was taken down. https://hub.harborframework.com/datasets/orca-bench/ORCA-ben...

This doesn't work anymore. Is there a newer link?

dash2 2 hours ago [-]
Seems like there's a big attack-defence asymmetry at present: models are great at exploiting systems and poor at fixing them.
aleksiy123 1 hours ago [-]
Attackers advantage in the iterative fast feedback loop?

It’s harder to have a loop to ensure you are defending all possible attacks?

I guess the loop is you need to attack yourself and fix. But attackers only need a single opening.

Finding all possible attacks and patching them against yourself is inherently more expensive?

EGreg 2 hours ago [-]
That is why I built https://safebots.ai/safebox.html

Your strategy can’t be patch AFTER an intrusion. Only to build a hardened environment from scratch and be ready in advance.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact
Rendered at 21:21:54 GMT+0000 (Coordinated Universal Time) with Vercel.