Thoughts on Human Models - LessWrong

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

related reading

• AGI Ruin: A List of Lethalities — LessWronglesswrong.com
• Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
• Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• The Artificiality of Alignmentjoinreboot.org
• Planning for AGI and beyond | OpenAIopenai.com
• Commentary on AGI Safety from First Principles — AI Alignment Forumalignmentforum.org
• AGI safety career advice — EA Forumforum.effectivealtruism.org
• Optimality is the tiger, and agents are its teeth — LessWronglesswrong.com
• A positive case for how we might succeed at prosaic AI alignment — AI Alignment Forumalignmentforum.org
• AGI safety from first principles: Introduction — LessWronglesswrong.com
• TechnicalAgenda.pdfintelligence.org