Coherent extrapolated volition (alignment target) - Arbital

A proposed direction for an extremely well-aligned autonomous superintelligence - do what humans would want, if we knew what the AI knew, thought that fast, and understood ourselves.

x Coherent extrapolated volition (alignment target) — LessWrong Coherent extrapolated volition (alignment target) Edited by Eliezer Yudkowsky , et al. last updated 19th Aug 2023 Introduction "Coherent extrapolated volition" (CEV) is Eliezer Yudkowsky 's proposed thing-to-do with an extremely advanced AGI , if you're extremely confident of your ability to align it on complicated targets. Roughly, a CEV-based superintelligence would do what currently existing humans would want* the AI to do, if counterfactually: We knew everything the AI knew; We could think as fast as the AI and consider all th

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• Mirrors and Paintings — LessWronglesswrong.com
• Cyborgism — LessWronglesswrong.com
• The Case Against AI Control Research — LessWronglesswrong.com
• The Artificiality of Alignmentjoinreboot.org
• Explore: AI alignmentarbital.greaterwrong.com
• Alignment & Succession: The Two Bars of Alignmentnosetgauge.com
• Cooperating with aliens and AGIs: An ECL explainer — LessWronglesswrong.com
• A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
• The Problem — LessWronglesswrong.com
• ⿻ Symbiogenesis vs. Convergent Consequentialism — LessWronglesswrong.com
• AI 2040: Plan Aai-2040.com