Taste Isn't a Reasoning Problem: Can AI Learn Judgment?
echen · x · 2026-08-26
The author argues that taste, judgment, and values are what distinguish great work from merely correct work, and these cannot be solved by rubrics alone. While AI models are increasingly mastering traits once thought uniquely human—like creativity and insight—they must learn these values from human teachers. The post discusses the importance of post-training in instilling these values in models and what this implies for the future of AI development.
Related event: Surge AI Founder: Taste Can't Be Learned Through Reasoning(3 posts)→
More from AGI Musings
- AI-written cold emails hit a wall: Pragmatic Engineer's reply gets templated AI response — marktenenholtz · 2026-10-16
- Ben Bajarin: Enterprise Agentic Adoption Is Infant-Stage, Spend Could Top $1T a Year — BenBajarin · 2026-10-16
- UMD Philosophy hires: junior Philosophy of Mind and joint AI Ethics/Safety positions — sethlazar · 2026-10-16
- Dwarkesh: Anthropic insider expects AI to match humans at AI research within 9 months — ZeroStateReflex · 2026-10-16
- Michigan professor Ben Green: why 'AI for Good' fails and self-regulation won't work — benzevgreen · 2026-10-16
- "Everything Is an Alignment Problem": AI Models, Business Models, Teams, Providers — saranormous · 2026-10-16