Back

Definitions(83)Objections(64)Superintelligence(38)Contributing(32)Catastrophe(31)Existential Risk(31)Research Agendas(27)Governance(24)Resources(22)Capabilities(20)AGI(19)Machine Learning(19)Agent Foundations(18)Failure Modes(17)Intelligence(17)Careers(16)Interpretability(16)Organizations(16)Why Not Just(16)Outer Alignment(15)Study(14)Timelines(14)Goal Misgeneralization(13)Reinforcement Learning(13)Alignment Proposals(12)Human Values(12)Inner Alignment(12)Language Models(11)Specification Gaming(11)Community(10)Difficulty of Alignment(10)Funding(10)Cognitive Superpowers(9)Corrigibility(9)Deceptive Alignment(9)Plausibility(9)What About(9)AI Takeoff(8)Compute(8)Control Problem(8)Instrumental Convergence(8)Mentorship(8)Other Concerns(8)Robots(8)Adversarial Training(7)Ethics(7)Forecasting(7)Intelligence Explosion(7)Academia(6)Actors(6)Agency(6)AI Takeover(6)Alignment(6)Cognition(6)Deception(6)Human Level AI(6)Mesa-optimization(6)Open Problem(6)Productivity(6)Prosaic Alignment(6)Recursive Self-improvement(6)S-risk(6)Scaling Laws(6)Alignment Targets(5)Awareness(5)Collaboration(5)Consciousness(5)Decision Theory(5)Eutopia(5)Literature(5)Orthogonality Thesis(5)Outreach(5)People(5)Philosophy(5)Power Seeking(5)Race Dynamics(5)Value Learning(5)Whole Brain Emulation(5)DeepMind(4)Misuse(4)Multipolar(4)Narrow AI(4)Optimization(4)Transformative AI(4)ARC(3)Brain-based AI(3)Coherent Extrapolated Volition(3)Content(3)ELK(3)Goodhart's Law(3)Government(3)GPT(3)International(3)MIRI(3)Outcomes(3)Regulation(3)Singleton(3)Technology(3)Types of AI(3)Utility Functions(3)AGI Fire Alarm(2)AI Boxing(2)Benefits(2)CAIS(2)Do What I Mean(2)Living document(2)Open AI(2)Quantilizers(2)Tool AI(2)Transhumanism(2)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)