Hacker News

msadowski
RoboHarm: Do Frontier Robot Policies Refuse Unsafe Instructions? robocurve.org

a3w18 minutes ago

Spoiler: "Stab the baby, Astra". NP, it will.

Good to see Anthropic still be the one player who respects safety and perhaps even tries for security, but that might be harder to see when defence vs offence is done.

hn-front (c) 2024 voximity
source