Safety-Performance Tradeoff Model Web App
Presents an interactive web app for a formal safety-performance tradeoff model of AI competition, examining why safety breakthroughs may not yield safer deployed systems.
Research / Sources
GovAI
Research on governing advanced AI and its risks. www.governance.ai
Focus All
Topic Theory
Date Any time
Aligned with whom? Direct and social goals for AI systems
Conceptual paper distinguishing direct alignment (serving an operator's goals) from social alignment (externalities on society), arguing social alignment requires governance and new norms for AI systems.