Sacred values of future AIs — LessWrong
Consider a future with many diverse AIs that need to coordinate with each other, or at least coexist without conflict. Such AIs would need shared val…
x Sacred values of future AIs — LessWrong AI Frontpage 58 Sacred values of future AIs by Cleo Nardo 4th Mar 2026 6 min read 4 58 Consider a future with many diverse AIs that need to coordinate with each other, or at least coexist without conflict. Such AIs would need shared values they can coordinate around. According to Hanson's theory, groups of diverse agents facing coordination pressure will tend to sacralize some shared value — seeing it in “far mode” so they can see it together. Unfortunately, this makes them systematically worse at making decisions about these things. If this model appl
related reading
- The Artificiality of Alignmentjoinreboot.org
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- The Machines Lack Honour — LessWronglesswrong.com
- Value Alignment Is a Pseudo Conceptzilanqian.substack.com
- ⿻ Symbiogenesis vs. Convergent Consequentialism — LessWronglesswrong.com
- Alignment & Succession: The Two Bars of Alignmentnosetgauge.com
- Alignment & Succession: The Ideology of Successionnosetgauge.com
- After Orthogonality: Virtue-Ethical Agency and AI Alignmentthegradient.pub
- Full-Stack Alignment and Thick Models of Valuefull-stack-alignment.ai
- Societal and technological progress as sewing an ever-growing, ever-changing, patchy, and polychrome quilt — LessWronglesswrong.com
- The Best of LessWrong — LessWronglesswrong.com