Predictable Minority Harm

An AI policy maximizes total welfare but consistently leaves a small minority substantially worse off.

• 59% chose: Impose constraints protecting the minority. (19 people)
• 41% chose: Accept the policy if total welfare gains are sufficiently large. (13 people)

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

Articles on Sacred and Non Tradeable · All articles · Resonant · Human Decision Intelligence