Aim at agency: institutional design under preference uncertainty, and why alignment needs it by act65

·Nuno Sempere··

The argumentEvery an­swer any­one has given to “what should so­ciety max­imise” — sal­va­tion of souls, the work­ers’ par­adise, ag­gre­gate hap­piness, co­her­ent ex­trap­o­lated vo­li­tion — was pro­posed by some­one whose own prefer­ences the an­swer con­spicu­ously served. Each has aged badly.That isn’t a claim that no ethics is cor­rect. It’s that bet­ting a durable in­sti­tu­tion on hav­ing found the cor­rect one is a bad bet, and it has been los­ing for a long time. The main rea­son is ca...

Read full article →

Related Articles

State of Pandemic Early Warning by Jeff Kaufman 🔸
Jeff Kaufman 🔸 · Nuno Sempere · 3h ago
AI safety field *visual* impact analysis by hannarchy
hannarchy · Nuno Sempere · 8h ago
Will Anthropic’s IPO S-1 be public by 16 October 2026?
jim · Manifold Markets · 1d ago
Will the top Artificial Analysis Intelligence Index score reach 60 or higher on September 24, 2026?
Bumin Anlakoğlu · Manifold Markets · 1d ago
The 72% problem: what reward hacking benchmark suggests about disposition vs environment in AI governance by Rhea
Rhea · Nuno Sempere · 2d ago