AI ALIGNMENT FORUM
AF

Concepts Portal

New Tag

This page displays the concepts which are foci of LessWrong discussion. 

The page has two sections:

  •     Tag Portal - manually curated, structured tags
  •     Tags List - alphabetical list of all existing tags

Wiki-Tag Dashboard | The Library | Tagging FAQ | LW1.0 Imported Wiki

RATIONALITY

Theory / Concepts

Anticipated Experiences
Aumann's Agreement Theorem
Bayes Theorem
Bounded Rationality
Conservation of Expected
Contrarianism
Decision Theory
Epistemology
Game Theory
Gears-Level
Hansonian Pre-Rationality
Infra-Bayesianism
Law-Thinking
Map and Territory
Newcomb's Problem
Occam's razor
Robust Agents
Solomonoff Induction
Truth, Semantics, & Meaning
Utility Functions
 

Applied Topics

Alief
Betting
Cached Thoughts
Calibration
Dark Arts
Empiricism
Epistemic Modesty
Forecasting & Prediction
Group Rationality
Identity
Inside/Outside View
Introspection
Intuition
Practice & Philosophy of Science
Scholarship & Learning
Taking Ideas Seriously
Value of Information
 

Failure Modes

Affect Heuristic
Aversion/Ugh Fields
Bucket Errors
Compartmentalization
Confirmation Bias
Fallacies
Goodhart’s Law
Groupthink
Heuristics and Biases
Mind Projection Fallacy
Motivated Reasoning
Pica
Pitfalls of Rationality
Rationalization 
Self-Deception
Sunk-Cost Fallacy

Communication

Common Knowledge
Conversation
Decoupling vs Contextualizing
Disagreement
Distillation & Pedagogy
Double-Crux
Good Explanations (Advice)
Ideological Turing Tests
Inferential Distance
Information Cascades
Memetic Immune System
Philosophy of Language
Steelmanning

Techniques

Double-Crux
Fermi Estimation
Focusing
Goal Factoring
Internal Double Crux
Hamming Questions
Murphyjitsu
Noticing
Techniques
Trigger Action Planning/Patterns

Models of the Mind

Consciousness
Dual Process Theory (System 1 & 2)
General Intelligence
Subagents
Predictive Processing
Perceptual Control Theory
Zombies
 

Other

Center for Applied Rationality
Curiosity
Rationality A-Z (discussion and meta)
Rationality Quotes
Updated Beliefs (examples of)

ARTIFICIAL INTELLIGENCE

Basic Alignment Theory

AIXI
Coherent Extrapolated Volition
Complexity of Value
Corrigibility
Decision Theory
Embedded Agency
Fixed Point Theorems
Goodhart's Law
Infra-Bayesianism
Inner Alignment
Instrumental Convergence
Logical Induction
Logical Uncertainty
Mesa-Optimization
Myopia
Newcomb's Problem
Optimization
Orthogonality Thesis
Outer Alignment
Paperclip Maximizer
Solomonoff Induction
Utility Functions

Engineering Alignment

AI Boxing (Containment)
Debate
Factored Cognition
Humans Consulting HCH
Impact Measures
Inverse Reinforcement Learning
Iterated Amplification
Mild Optimization
Tool AI
Transparency / Interpretability
Value Learning
 

Organizations

CHAI (UC Berkeley)
Deepmind
FHI (Oxford)
MIRI
OpenAI
Ought

Strategy

AI Governance
AI Risk
AI Services (CAIS)
AI Takeoff
AI Timelines

 Other

Research Agendas 

 

WORLD MODELING

Mathematical Sciences

Abstraction
Anthropics
Category Theory
Causality
Computer Science
Game Theory
Decision Theory
Information Theory
Logic & Mathematics
Probability & Statistics

Specifics
Prisoner's Dilemma
Sleeping Beauty Paradox
 

General Science & Eng

Machine Learning
Nanotechnology
Physics
Programming
Space Exploration & Colonization

Specifics
Simulation Hypothesis
The Great Filter

Meta / Misc

Academic Papers
Book Reviews
Counterfactuals
Distillation & Pedagogy
Fact Posts
Research Agendas
Scholarship & Learning

Social & Economic

Economics
Financial Investing
History
Politics
Progress Studies
Social and Cultural Dynamics

Specifics
Conflict vs Mistake Theory
Cost Disease
Efficient Market Hypothesis
Industrial Revolution
Moral Mazes
Signaling
Social Reality
Social Status

Biological & Psychological

Aging
Biology
Consciousness
Evolution
Evolutionary Psychology
Medicine
Neuroscience
Qualia

Specifics
Coronavirus
General Intelligence
IQ / g-factor
Neocortex

The Practice of Modeling

Epistemic Review
Expertise
Gears-Level Models
Falsifiability
Fermi Estimation
Forecasting & Prediction
Forecasts (Lists of)
Inside/Outside View
Intellectual Progress (Society-Level)
Intellectual Progress (Individual-Level)
Jargon (meta)
Practice and Philosophy of Science
Prediction Markets
Reductionism
Replicability
 

 

WORLD OPTIMIZATION

Moral Theory

Altruism
Consequentialism
Deontology
Ethics & Morality
Metaethics
Moral Uncertainty
Trolley Problem

 

 

Causes / Interventions

Aging
Animal Welfare
Climate Change
Existential Risk
Futurism
Intellectual Progress
Mind Uploading
Life Extension
S-risks
Transhumanism
Voting Theory

Working with Humans

Coalitional Instincts
Common Knowledge
Coordination / Cooperation
Game Theory
Group Rationality
Institution Design
Moloch
Organizational Design and Culture
Signaling
Simulacrum Levels
Social Status

Applied Topics

Acausal Trade
Blackmail
Censorship
Chesterton's Fence
Death
Deception
Honesty
Hypocrisy
Information Hazards
Meta-Honesty
Pascal's Mugging
Privacy
War

Value & Virtue

Ambition
Art
Aesthetics
Complexity of Value
Courage
Fun Theory
Principles
Suffering
Superstimuli
Wireheading

Meta

80,000 Hours
Cause Prioritization
Center for Long-term Risk
Effective Altruism
GiveWell
Heroic Responsibility
 

 

PRACTICAL

Domains of Well-being

Careers
Emotions
Exercise (Physical)
Financial Investing
Gratitude
Happiness
Human Bodies
Nutrition
Parenting
Slack
Sleep
Well-being

Skills & Techniques

Cryonics
Emotions
Goal Factoring
Habits
Hamming Questions
Intellectual Progress (Individual-Level)
Life Improvements
Meditation
More Dakka
Note-Taking
Planning & Decision-Making
Sabbath
Self Experimentation
Skill Building
Software Tools
Spaced Repetition
Virtues (Instrumental)

Productivity

Akrasia
Attention
Motivations
Prioritization
Procrastination
Productivity
Willpower

Interpersonal
Circling
Conversation (topic)
Communication Cultures
Relationships

 

COMMUNITY

All

Bounties (active)
Grants & Fundraising
Growth Stories
Online Socialization
Petrov Day
Public Discourse
Reading Group
Research Agendas
Ritual
Solstice Celebration
 

LessWrong

Events (Community)
Site Meta
GreaterWrong Meta
Intellectual Progress via LessWrong
LessWrong Events
LW Moderation
Meetups (topic)
Moderation (topic)
The SF Bay Area
Tagging

 

OTHER

Content-Type

Art
Checklists
Dialogue (form)
Eldritch Analogies
Exercises / Problem-Sets
Humor
Fiction
Open Problems
Paradoxes
Poetry
Postmortems & Retrospectives
Summaries

Format

Book Reviews
Interviews
List of Links
Newsletters
Open Thread
Q&A (format)
Surveys
Transcripts

Cross-Category

Cooking
Education
Narratives (stories)
Religion
Writing

 

Miscellaneous

Fiction (topic)
Gaming (videogames/tabletop)
HPMOR (discussion & meta)

All Tags (629)

New Tag
80,000 Hours (9)
AI (1599)
AI Boxing (Containment) (31)
AI Governance (39)
AI Risk (201)
AI Safety Camp (2)
AI Services (CAIS) (11)
AI Takeoff (69)
AI Timelines (90)
AIXI (26)
Abstraction (51)
Absurdity Heuristic (12)
Academic Papers (90)
Acausal Trade (21)
Adaptation Executors (15)
Adding Up to Normality (6)
Adversarial Collaboration (3)
Adversarial Examples (5)
Aesthetics (23)
Affect Heuristic (14)
Affective Death Spiral (11)
Agency (23)
Aggregation (1)
Aging (38)
Akrasia (67)
Algorithms (4)
Alief (17)
Altruism (56)
Ambition (35)
Analogy (3)
Anchoring (5)
Animal Welfare (28)
Anthropics (153)
Anticipated Experiences (37)
Appeal to Consequence (5)
Applause Light (3)
Apprenticeship (6)
April Fool's (12)
Art (50)
Assurance contracts (9)
Astrobiology (7)
Astronomical Waste (5)
Asymmetric Weapons (3)
Attention (12)
Audio (24)
Aumann's Agreement Theorem (17)
Autism (8)
Automation (2)
Autonomous Vehicles (10)
Autonomy and Choice (2)
Availability Heuristic (11)
Aversion (13)
Babble and Prune (23)
Bayes' Theorem (109)
Bayesian Decision Theory (8)
Behavior Change (3)
Betting (56)
Big Data (3)
Biology (74)
Black Swans (5)
Blackmail / Extortion (19)
Blues & Greens (metaphor) (12)
Book Reviews (192)
Bounded Rationality (14)
Bounties (active) (13)
Bounties (closed) (27)
Brain-Computer Interfaces (8)
Brainstorming (1)
Bucket Errors (9)
Buddhism (22)
Bystander Effect (12)
Cached Thoughts (17)
Calibration (34)
Cancer (1)
Careers (64)
Carving / Clustering Reality (11)
Case Study (9)
Category Theory (14)
Causal Decision Theory (13)
Causality (65)
Cause Prioritization (34)
Censorship (21)
Center for Applied Rationality (CFAR) (62)
Center for Human-Compatible AI (CHAI) (19)
Center on Long-Term Risk (CLR) (11)
Changing Your Mind (15)
Charter Schools (1)
Checklists (7)
Chemistry (6)
Chesterton's Fence (11)
China (14)
Circling (6)
Climate Change (28)
Cognitive Fusion (3)
Cognitive Reduction (9)
Cognitive Reframes (1)
Cognitive Science (17)
Coherence Arguments (8)
Coherent Extrapolated Volition (28)
Comfort Zone Expansion (CoZE) (4)
Commitment Mechanisms (5)
Common Knowledge (18)
Communication Cultures (56)
Community (791)
Community Outreach (28)
Compartmentalization (13)
Complexity of Value (45)
Computer Science (39)
Computer Security (15)
Computing Overhang (5)
Conceptual Media (1)
Conditional Consistency (1)
Confirmation Bias (24)
Conflict vs Mistake (11)
Conformity Bias (15)
Conjunction Fallacy (12)
Consciousness (78)
Consensus (9)
Consequentialism (48)
Conservation of Expected Evidence (12)
Conservatism (AI) (7)
Contact with Reality (4)
Contrarianism (20)
Conversation (topic) (95)
Cooking (20)
Coordination / Cooperation (94)
Correspondence Bias (4)
Corrigibility (38)
Cost Disease (7)
Counterfactual Mugging (15)
Counterfactuals (90)
Courage (12)
Covid-19 (622)
Creativity (11)
Criticisms of The Rationalist Movement (11)
Crowdfunding (5)
Crucial Considerations (8)
Cryonics (100)
Cryptocurrency & Blockchain (25)
Cults (7)
Cultural knowledge (22)
Curiosity (27)
DIY (5)
Dark Arts (39)
Data Science (5)
Death (47)
Debate (AI safety technique) (30)
Debate Tools (3)
Debugging (8)
Deception (43)
Decision Theory (212)
Deconfusion (9)
Decoupling vs Contextualizing (5)
DeepMind (21)
Defensibility (5)
Definitions (29)
Delegation (2)
Deliberate Practice (10)
Dementia (2)
Demon Threads (5)
Deontology (14)
Depression (21)
Derisking (4)
Developmental Psychology (14)
Dialogue (format) (20)
Disagreement (85)
Dissolving the Question (15)
Distillation & Pedagogy (40)
Distinctions (88)
Domain Theory (5)
Double-Crux (19)
Dual Process Theory (System 1 & System 2) (21)
ET Jaynes (11)
Economic Consequences of AGI (12)
Economics (156)
Education (115)
Effective Altruism (123)
Efficient Market Hypothesis (33)
Eldritch Analogies (13)
Embedded Agency (44)
Embodiment (1)
Emergent Behavior (7)
Emotions (115)
Empiricism (28)
Epistemic Luck (2)
Epistemic Review (27)
Epistemic Spot Check (16)
Epistemology (144)
Eschatology (1)
Ethical Offsets (2)
Ethics & Morality (211)
Events (Community) (127)
Evidential Decision Theory (10)
Evolution (70)
Evolutionary Psychology (38)
Exercise (Physical) (23)
Exercises / Problem-Sets (91)
Existential Risk (80)
Experiments (16)
Expertise (topic) (39)
Exploratory Engineering (1)
Fact posts (22)
Factored Cognition (25)
Fallacies (58)
Falsifiability (9)
Family planning (16)
Feedback & Criticism (topic) (14)
Fermi Estimation (11)
Fiction (307)
Fiction (Topic) (94)
Filtered Evidence (11)
Financial Investing (95)
Finite Factored Sets (8)
Five minute timers (7)
Fixed Point Theorems (9)
Focusing (16)
Forecasting & Prediction (158)
Forecasts (Specific Predictions) (47)
Frames (5)
Free Will (18)
Fun Theory (35)
Functional Decision Theory (5)
Futarchy (11)
Future of Humanity Institute (FHI) (27)
Future of Life Institute (FLI) (12)
Futurism (68)
Fuzzies (7)
GAN (3)
GPT (82)
Game Theory (146)
Games (posts describing) (7)
Gaming (videogames/tabletop) (99)
Gears-Level (45)
General Intelligence (56)
Generalization From Fictional Evidence (10)
Generativity (3)
GiveWell (26)
Goal Factoring (12)
Goal-Directedness (18)
Goals (4)
Good Explanations (Advice) (11)
Goodhart's Law (51)
Government (38)
Grants & Fundraising Opportunities (50)
Gratitude (14)
Great Filter (25)
GreaterWrong Meta (10)
Grieving (4)
Group Rationality (69)
Group Selection (6)
Groupthink (24)
Growth Stories (50)
Guilt & Shame (9)
HPMOR (discussion & meta) (88)
Habits (30)
Halo Effect (6)
Hamming Questions (20)
Hansonian Pre-Rationality (8)
Happiness (32)
Hedonism (23)
Heroic Responsibility (22)
Heuristics & Biases (169)
Hindsight Bias (8)
History (128)
History of Rationality (14)
Homunculus Fallacy (3)
Honesty (39)
Hope (8)
Human Bodies (25)
Human Genetics (23)
Human Universal (3)
Human Values (20)
Humans Consulting HCH (23)
Humility (23)
Humor (95)
Hypocrisy (15)
Hypotheticals (9)
IQ and g-factor (48)
Identity (56)
Ideological Turing Tests (4)
Illusion of Transparency (7)
Impact Measures (47)
Implicit Association Test (IAT) (3)
Incentives (11)
Indexical Information (1)
Industrial Revolution (23)
Inferential Distance (43)
Infinities In Ethics (8)
Infinity (6)
Information Cascades (14)
Information Hazards (23)
Information Theory (26)
Infra-Bayesianism (12)
Inner Alignment (52)
Inner Simulator / Suprise-o-meter (4)
Inside/Outside View (39)
Instrumental Convergence (32)
Intellectual Fashion (2)
Intellectual Progress (Individual-Level) (14)
Intellectual Progress (Society-Level) (59)
Intellectual Progress via LessWrong (21)
Intelligence Amplification (9)
Intelligence Explosion (15)
Intentionality (5)
Internal Alignment (Human) (4)
Internal Double Crux (9)
Internal Family Systems (13)
Interpretive Labor (3)
Interviews (45)
Introspection (48)
Intuition (36)
Inverse Reinforcement Learning (23)
Islam (1)
Iterated Amplification (51)
Ivermectin (drug) (4)
Journalism (5)
Jungian Philosophy/Psychology (1)
Just World Hypothesis (1)
Kelly Criterion (20)
LW Moderation (16)
Landmark Forum (2)
Law and Legal systems (15)
Law-Thinking (19)
LessWrong Event Transcripts (26)
LessWrong Review (28)
Levels of Intervention (2)
Libertarianism (8)
Life Extension (44)
Life Improvements (38)
Lifelogging (8)
Lighting (9)
List of Links (68)
Litanies & Mantras (5)
Litany of Tarski (5)
Literature Reviews (11)
Local Community Theory/Practice (10)
Logic & Mathematics (192)
Logical Induction (26)
Logical Uncertainty (42)
Longtermism (7)
Lost Purposes (1)
Lottery Ticket Hypothesis (5)
Love (4)
Luck (6)
Luminosity (5)
Machine Intelligence Research Institute (MIRI) (126)
Machine Learning (129)
Many-Worlds Interpretation (20)
Map and Territory (45)
Market Inefficiency (5)
Marketing (10)
Marriage (12)
Measure Theory (2)
Mechanism Design (86)
Medicine (103)
Meditation (66)
Meetups (topic) (38)
Memetic Immune System (15)
Memetics (19)
Memory Reconsolidation (13)
Memory and Mnemonics (7)
Mental Imagery / Visualization (3)
Mesa-Optimization (29)
Meta-Honesty (12)
Meta-Humor (4)
Meta-Philosophy (14)
Metaethics (60)
Mild Optimization (7)
Mind Projection Fallacy (17)
Mind Space (5)
Mind Uploading (48)
Modeling People (11)
Moderation (topic) (16)
Modest Epistemology (12)
Moloch (45)
Moore's Law (5)
Moral Mazes (34)
Moral Uncertainty (49)
More Dakka (9)
Motivated Reasoning (52)
Motivations (136)
Murphyjitsu (7)
Music (39)
Myopia (17)
Nanotechnology (11)
Narrative Fallacy (7)
Narratives (stories) (24)
Negative Utilitarianism (3)
Neocortex (11)
Neuralink (7)
Neurodivergence (6)
Neuromorphic AI (5)
Neuroscience (83)
Newcomb's Problem (32)
Newsletters (172)
Nootropics & Other Cognitive Enhancement (9)
Note-Taking (15)
Noticing (29)
Noticing Confusion (2)
Nutrition (37)
Occam's Razor (27)
Offense (5)
Online Socialization (27)
Ontological Crisis (5)
Ontology (9)
Open Problems (19)
Open Threads (438)
OpenAI (33)
Optimization (38)
Oracle AI (63)
Organization Updates (18)
Organizational Culture & Design (21)
Orthogonality Thesis (10)
Ought (12)
Outer Alignment (43)
Paperclip Maximizer (21)
Parables & Fables (24)
Paradoxes (41)
Parenting (64)
Pascal's Mugging (24)
Past and Future Selves (4)
Perception (15)
Perceptual Control Theory (7)
Perfect Predictor (2)
Personal Identity (20)
Petrov Day (30)
Phenomenology (14)
Philosophy (84)
Philosophy of Language (106)
Physics (109)
Pica (6)
Pitfalls of Rationality (65)
Planning & Decision-Making (73)
Planning Fallacy (10)
Poetry (23)
Politics (204)
Polyamory (13)
Pomodoro Technique (7)
Population Ethics (11)
Postmortems & Retrospectives (119)
Practical (1012)
Practice & Philosophy of Science (121)
Pre-Commitment (6)
Prediction Markets (44)
Predictive Processing (21)
Prepping (16)
Priming (15)
Principal-Agent Problems (6)
Principles (12)
Prioritization (18)
Priors (20)
Prisoner's Dilemma (48)
Privacy (16)
Probabilistic Reasoning (9)
Probability & Statistics (176)
Problem Formulation & Conceptualization (3)
Problem of Old Evidence (3)
Problem-solving (skills and techniques) (14)
Procrastination (30)
Product Reviews (1)
Productivity (111)
Programming (104)
Progress Studies (98)
Project Announcement (6)
Project Based Learning (4)
Psychiatry (19)
Psychology (78)
Psychology of Altruism (4)
Psychopathy (7)
Psychotropics (9)
Public Discourse (93)
Q&A (format) (25)
QURI (10)
Qualia (20)
Qualia Research Institute (2)
Quantilization (3)
Quantum Mechanics (30)
Quests / Projects Someone Should Do (19)
Radical Probabilism (5)
Rationalist Taboo (19)
Rationality (1639)
Rationality A-Z (discussion & meta) (49)
Rationality Quotes (132)
Rationality Verification (14)
Rationalization (58)
Reading Group (34)
Recursive Self-Improvement (12)
Reductionism (23)
References (Language) (7)
Reflective Reasoning (5)
Regulation and AI Risk (5)
Reinforcement Learning (49)
Relationships (Interpersonal) (107)
Religion (107)
Replication Crisis (46)
Request Post (2)
Research Agendas (43)
Reset (technique) (3)
Reversal Test (5)
Reversed Stupidity Is Not Intelligence (3)
Reward Functions (10)
Risk Management (13)
Risks of Astronomical Suffering (S-risks) (20)
Ritual (54)
Road To AI Safety Excellence (6)
Robotics (14)
Robust Agents (20)
Roko's Basilisk (6)
SETI (3)
Sabbath (5)
Safety (Physical) (6)
Satisficer (7)
Scaling Laws (4)
Scholarship & Learning (189)
Scope Insensitivity (6)
Scrupulosity (4)
Secular Solstice (46)
Seed AI (5)
Selection Effects (8)
Selection vs Control (8)
Selectorate Theory (6)
Self Experimentation (45)
Self Fulfilling/Refuting Prophecies (10)
Self Improvement (55)
Self-Deception (49)
Sex & Gender (44)
Shaping Your Environment (4)
Shut Up and Multiply (25)
Signaling (59)
Simulacrum Levels (23)
Simulation Hypothesis (22)
Singularity (13)
Site Meta (457)
Skill / Expertise Assessment (14)
Skill Building (37)
Slack (29)
Sleep (23)
Sleeping Beauty Paradox (49)
Social & Cultural Dynamics (210)
Social Media (30)
Social Reality (28)
Social Skills (6)
Social Status (79)
Software Tools (90)
Solomonoff Induction (26)
Something To Protect (9)
Space Exploration & Colonization (38)
Spaced Repetition (55)
Sports (16)
Stag Hunt (5)
Startups (31)
Status Quo Bias (5)
Steelmanning (22)
Stoicism / Letting Go / Making Peace (5)
Strong Opinions Weakly Held (2)
Subagents (70)
Success Spiral (1)
Suffering (61)
Summaries (66)
Summoning Sapience (3)
Sunk-Cost Fallacy (9)
Superintelligence (14)
Superstimuli (16)
Surveys (56)
Systems Thinking (9)
Tacit Knowledge (1)
Taking Ideas Seriously (11)
Teamwork (11)
Techniques (74)
Technological Forecasting (8)
Technological Unemployment (5)
Terminology / Jargon (meta) (16)
The Hard Problem of Consciousness (7)
The Pointers Problem (6)
The SF Bay Area (24)
Therapy (21)
Thingspace (7)
Threat Models (8)
Time (value of) (7)
Timeless Decision Theory (14)
Timeless Physics (6)
Tool AI (15)
Tradeoffs (6)
Transcripts (30)
Transformative AI (1)
Transhumanism (36)
Transparency / Interpretability (ML & AI) (29)
Transposons (3)
Travel (6)
Tribalism (47)
Trigger-Action Planning (23)
Tripwire (6)
Trivial Inconvenience (6)
Trolley Problem (16)
Trust (10)
Truth, Semantics, & Meaning (56)
Try Things (10)
Tsuyoku Naritai (13)
Typical Mind Fallacy (9)
UI Design (7)
Underconfidence (10)
Updated Beliefs (examples of) (31)
Urban Planning / Design (7)
Utilitarianism (18)
Utility Functions (98)
VNM Theorem (12)
Valley of Bad Rationality (14)
Value Drift (10)
Value Learning (103)
Value of Information (13)
Value of Rationality (16)
Values handshakes (1)
Veganism (1)
Virtues (75)
Voting Theory (30)
War (49)
Weirdness Points (8)
Well-being (53)
Whole Brain Emulation (22)
Wiki/Tagging (25)
Wildfires (6)
Willpower (25)
Wireheading (21)
Working Memory (12)
World Modeling (1248)
World Modeling Techniques (16)
World Optimization (882)
Writing (communication method) (72)
Zettelkasten (4)