RoboHarm: Do Frontier Robot Policies Refuse Unsafe Instructions? 2 hours ago (robocurve.org) 1 comment msadowski Reply Add to library a3w 18 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.
a3w 18 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.
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.