Categories

Academia (6)Actors (6)Adversarial Training (7)Agency (6)Agent Foundations (20)AGI (19)AGI Fire Alarm (3)AI Boxing (2)AI Takeoff (8)AI Takeover (6)Alignment (5)Alignment Proposals (10)Alignment Targets (5)Anthropic (1)ARC (3)Autonomous Weapons (1)Awareness (6)Benefits (2)Brain-based AI (3)Brain-computer Interfaces (1)CAIS (2)Capabilities (20)Careers (16)Catastrophe (29)CHAI (1)CLR (1)Cognition (6)Cognitive Superpowers (9)Coherent Extrapolated Volition (2)Collaboration (6)Community (10)Comprehensive AI Services (1)Compute (9)Consciousness (5)Content (3)Contributing (32)Control Problem (7)Corrigibility (8)Deception (5)Deceptive Alignment (8)Decision Theory (5)DeepMind (4)Definitions (86)Difficulty of Alignment (9)Do What I Mean (2)ELK (3)Emotions (1)Ethics (7)Eutopia (5)Existential Risk (29)Failure Modes (14)FAR AI (1)Forecasting (7)Funding (10)Game Theory (1)Goal Misgeneralization (13)Goodhart's Law (3)Governance (27)Government (3)GPT (3)Hedonium (1)Human Level AI (5)Human Values (11)Inner Alignment (11)Instrumental Convergence (5)Intelligence (15)Intelligence Explosion (7)International (3)Interpretability (17)Inverse Reinforcement Learning (1)Language Models (13)Literature (5)Living document (2)Machine Learning (21)Maximizers (1)Mentorship (8)Mesa-optimization (6)MIRI (2)Misuse (4)Multipolar (4)Narrow AI (4)Objections (60)Open AI (2)Open Problem (6)Optimization (4)Organizations (15)Orthogonality Thesis (3)Other Concerns (8)Outcomes (5)Outer Alignment (15)Outreach (5)People (4)Philosophy (5)Pivotal Act (1)Plausibility (7)Power Seeking (5)Productivity (6)Prosaic Alignment (7)Quantilizers (2)Race Dynamics (6)Ray Kurzweil (1)Recursive Self-improvement (6)Regulation (3)Reinforcement Learning (13)Research Agendas (26)Research Assistants (1)Resources (22)Robots (7)S-risk (6)Sam Bowman (1)Scaling Laws (6)Selection Theorems (1)Singleton (3)Specification Gaming (10)Study (14)Superintelligence (34)Technological Unemployment (1)Technology (3)Timelines (14)Tool AI (2)Transformative AI (4)Transhumanism (2)Types of AI (2)Utility Functions (3)Value Learning (5)What About (9)Whole Brain Emulation (6)Why Not Just (15)

Open Problem

6 pages tagged "Open Problem"

Can you give an AI a goal which involves “minimally impacting the world”?

Can we get AGI by scaling up architectures similar to current ones, or are we missing key insights?

Would AI alignment be hard with deep learning?

What would a good solution to AI alignment look like?

What technical problems is MIRI working on?

What is Eliciting Latent Knowledge (ELK)?