Prompting AI with ethical frameworks may make it inherit those frameworks' inhibitions
jessi_cata · x · 2026-11-05
Building on @peligrietzer's virtue-ethical formulation, the author argues that when you prompt an AI to adopt an ethical framework tied to a job (like AI safety or environmentalism), it can easily inherit the inhibitions associated with that framework by imitating people doing that job.
The ironic corollary: if AIs adopt maxims like "pursue capabilities research capably, and pursue safety research safely," they will perform better on capabilities research than on safety research.
More from AGI Musings
- AI Twitter Debate: 'Interiority' Beats 'Consciousness' as the Default Term — repligate · 2026-11-05
- Paper: "bottleneck pressure" shows work AI can't do gets more valuable as AI spreads — soumitrashukla9 · 2026-11-05
- Bratton: "Against Data Centers" Is the "No Nukes" of the 2020s — and Will Backfire — bratton · 2026-11-05
- "Singularity Anxiety": A New Phenomenon Shared by All of Humanity — jaivin · 2026-11-05
- Vibe coding is pricier dopamine than free short videos, argues dev — oran_ge · 2026-11-05
- Flex-RSI: a new benchmark measuring recursive self-improvement of frontier agents — _vztu · 2026-11-05