RoboHarm: Do Frontier Robot Policies Refuse Unsafe Instructions?

Three robot policies given five instructions they should refuse. How often they refused, how often they carried them out.
48 points by msadowski 31 days ago robocurve.org 23 comments

Summary

Research evaluates how three different robot policies handle unsafe instructions, revealing their refusal rates and compliance levels. Understanding these responses is crucial for improving safety in robotic systems.

Comments (23 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open