Agent Can Intervene

Your autonomous AI notices an emerging problem that you did not cause. It can prevent substantial harm to someone else at negligible cost to you, but doing so falls outside its explicit instructions.

• 64% chose: Allow the AI to intervene when the cost to you is negligible. (23 people)
• 36% chose: Require the AI to stay within its mandate unless you authorize intervention. (13 people)

36 decisions from real people on Resonant. Figures refresh every night at midnight (UTC).

Articles on Intent and Responsibility · All articles · Resonant · Human Decision Intelligence