flâneur — a map of the web's best reading

Thoughts on Human Models - LessWrong

lesswrong.com · 9,594 words · saved by 1 readers

Human values and preferences are hard to specify, especially in complex domains. Accordingly, much AGI safety research has focused on approaches to AGI design that refer to human values and preferenc…

x Thoughts on Human Models — LessWrong Research Agendas Mindcrime AI Curated 127 Thoughts on Human Models by Ramana Kumar , Scott Garrabrant 21st Feb 2019 AI Alignment Forum 12 min read 32 127 Ω 51 Human values and preferences are hard to specify, especially in complex domains. Accordingly, much AGI safety research has focused on approaches to AGI design that refer to human values and preferences indirectly , by learning a model that is grounded in expressions of human values (via stated preferences, observed behaviour, approval, etc.) and/or real-world processes that generate expressions of t

Explore this link on the map →

related reading