Back

Definitions(86)Objections(60)Superintelligence(34)Catastrophe(29)Contributing(29)Existential Risk(29)Research Agendas(26)Governance(24)Agent Foundations(20)Capabilities(20)Machine Learning(20)AGI(19)Resources(19)Interpretability(17)Intelligence(15)Organizations(15)Why Not Just(15)Careers(14)Outer Alignment(14)Timelines(14)Failure Modes(13)Goal Misgeneralization(13)Language Models(13)Reinforcement Learning(13)Study(13)Human Values(11)Alignment Proposals(10)Community(10)Funding(10)Inner Alignment(10)Specification Gaming(10)Cognitive Superpowers(9)What About(9)AI Takeoff(8)Compute(8)Corrigibility(8)Deceptive Alignment(8)Difficulty of Alignment(8)Mentorship(8)Other Concerns(8)Adversarial Training(7)Control Problem(7)Ethics(7)Forecasting(7)Intelligence Explosion(7)Plausibility(7)Prosaic Alignment(7)Robots(7)Academia(6)Agency(6)AI Takeover(6)Awareness(6)Collaboration(6)Mesa-optimization(6)Productivity(6)Race Dynamics(6)Recursive Self-improvement(6)S-risk(6)Scaling Laws(6)Whole Brain Emulation(6)Actors(5)Alignment(5)Cognition(5)Consciousness(5)Deception(5)Decision Theory(5)Eutopia(5)Human Level AI(5)Instrumental Convergence(5)Outcomes(5)Outreach(5)Philosophy(5)Power Seeking(5)Value Learning(5)Alignment Targets(4)DeepMind(4)Literature(4)Misuse(4)Multipolar(4)Narrow AI(4)Open Problem(4)Optimization(4)People(4)Transformative AI(4)AGI Fire Alarm(3)ARC(3)Brain-based AI(3)ELK(3)Goodhart's Law(3)Government(3)GPT(3)International(3)Orthogonality Thesis(3)Regulation(3)Singleton(3)Technology(3)Utility Functions(3)AI Boxing(2)Benefits(2)CAIS(2)Coherent Extrapolated Volition(2)Content(2)Do What I Mean(2)Living document(2)MIRI(2)Open AI(2)Quantilizers(2)Tool AI(2)Transhumanism(2)Types of AI(2)Anthropic(1)Autonomous Weapons(1)Brain-computer Interfaces(1)CHAI(1)CLR(1)Comprehensive AI Services(1)Emotions(1)FAR AI(1)Game Theory(1)Hedonium(1)Inverse Reinforcement Learning(1)Maximizers(1)Pivotal Act(1)Ray Kurzweil(1)Research Assistants(1)Sam Bowman(1)Selection Theorems(1)Technological Unemployment(1)