AI ALIGNMENT FORUM
AF

HomeLibraryQuestionsAll Posts
New Wikitag
Concepts
Rationality
117
Bayes' rule
34
Babble and Prune(35)
32
Odds
22
Typical Mind Fallacy(16)
21
Forecasting & Prediction(490)
21
Map and Territory(73)
20
Bayes' Theorem(180)
20
Conservation of Expected Evidence(21)
19
12 Virtues
19
Absurdity Heuristic(15)
19
Asymmetric Weapons(7)
19
Aversion(22)
19
Bayesianism(57)
19
Bucket Errors(16)
19
Calibration(74)
19
Common Knowledge(32)
19
Conflict vs Mistake(23)
19
Conformity Bias(17)
19
Curiosity(38)
19
Decoupling vs Contextualizing(10)
19
Double-Crux(34)
19
Epistemic Spot Check(26)
19
Filtered Evidence(19)
19
Goodhart's Law(128)
19
Heuristics & Biases(269)
19
Humility(40)
19
Ideological Turing Tests(12)
19
Inside/Outside View(58)
19
Litany of Tarski(9)
19
Memetic Immune System(28)
Load More (30/294)
AI
58
Orthogonality Thesis(64)
45
Methodology of unbounded analysis
40
Solomonoff induction(76)
36
Epistemic and instrumental efficiency
36
The rocket alignment problem
35
Advanced agent properties
33
AI alignment
30
Coherent extrapolated volition (alignment target)
28
AI safety mindset
26
Nearest unblocked strategy
24
Context disaster
24
Diamond maximizer
24
List: value-alignment subjects
23
AI Control(105)
23
Deceptive Alignment(205)
23
Low impact
23
Pivotal act
22
Outer Alignment(305)
20
Mesa-Optimization(133)
20
Task-directed AGI
19
Agent Foundations(135)
19
AI Takeoff(301)
19
AI Timelines(417)
19
Edge instantiation
19
Embedded Agency(110)
19
Logical Induction(42)
19
No-Free-Lunch theorems are often irrelevant
19
Open subproblems in aligning a Task-based AGI
19
Sufficiently optimized agents appear coherent
19
Tiling Agents(20)
Load More (30/461)
World Modeling
41
Bayesian view of scientific virtues
35
Report likelihoods, not p-values
29
Executable philosophy
24
Logarithm
22
Economics(529)
21
Distillation & Pedagogy(185)
21
Scholarship & Learning(352)
20
Gears-Level(66)
20
Logic & Mathematics (537)
20
Mechanism Design(157)
20
Philosophy of Language(208)
20
Simulacrum Levels(43)
19
Abstraction(102)
19
Anthropics(266)
19
Biology(247)
19
Causality(145)
19
Chemistry(25)
19
Consciousness(332)
19
Efficient Market Hypothesis(52)
19
Evolution(210)
19
Evolutionary Psychology(98)
19
Grabby Aliens(22)
19
IQ and g-factor(70)
19
Kolmogorov Complexity(50)
19
Law-Thinking(20)
19
Many-Worlds Interpretation(67)
19
Neuroscience(240)
19
Parfit's Hitchhiker
19
Physics(269)
19
Prediction Markets(166)
Load More (30/247)
World Optimization
59
Rescuing the utility function
26
Voting Theory(61)
20
Public Discourse(182)
20
Trust and Reputation(39)
19
Acute Risk Period(1)
19
Astronomical Waste(11)
19
Biosecurity(60)
19
Consequentialism(100)
19
Coordination / Cooperation(290)
19
Dath Ilan(36)
19
Heroic Responsibility(38)
19
Honesty(74)
19
Incentives(50)
19
Life Extension(96)
19
Moloch(80)
19
Moral Mazes(53)
19
Organizational Culture & Design(78)
19
Transhumanism(98)
17
Law and Legal systems(92)
11
Futurism(165)
10
Animal Ethics(74)
10
Black Swans(12)
10
Bureaucracy(20)
10
Copenhagen Interpretation of Ethics(4)
10
Crucial Considerations(9)
10
Ethics & Morality(601)
10
Exploratory Engineering(23)
10
Integrity(10)
10
Market Inefficiency(11)
10
Nuclear War(38)
Load More (30/144)
Practical
21
Deliberate Practice(28)
21
Introspection(77)
20
Emotions(211)
19
Akrasia(109)
19
Commitment Mechanisms(14)
19
Communication Cultures(154)
19
Cryonics(148)
19
Financial Investing(177)
19
Hamming Questions(27)
19
Happiness(70)
19
More Dakka(29)
19
Postmortems & Retrospectives(204)
19
Productivity(220)
19
Slack(41)
19
Writing (communication method)(198)
12
Guess/Ask/Tell Culture
11
Five minute timers(19)
10
Circling(10)
10
Exercise (Physical)(44)
10
Lighting(17)
10
Procrastination(44)
10
Sabbath(6)
10
Social Skills(52)
10
Trivial Inconvenience(6)
9
Air Quality(25)
9
Ambition(45)
9
Conversation (topic)(136)
9
Cooking(44)
9
Creativity(36)
9
Disagreement(134)
Load More (30/120)
Community
9
Bounties & Prizes (active)(88)
9
Grants & Fundraising Opportunities(108)
9
LessWrong Books(8)
9
Lightcone Infrastructure(15)
9
LW Moderation(34)
9
MATS Program(247)
9
Meetups & Local Communities (topic)(106)
9
Open Threads(481)
9
Petrov Day(49)
9
Rationalist Movement
9
Secular Solstice(88)
4
Our community should relocate to a country other than the US
3
LessWrong Jargon
0
Collections and Resources(26)
0
Community Outreach(58)
0
Community Page(155)
0
Criticisms of The Rationalist Movement(35)
0
Drama(30)
0
Less Wrong/Article Summaries
0
LessWrong Event Transcripts(26)
0
LessWrong Review(60)
0
Meetups (specific examples)(42)
0
Organization Updates(61)
0
The SF Bay Area(42)
0
Welcome Threads(6)
Site Meta
9
Intellectual Progress via LessWrong(31)
9
LW Team Announcements(17)
9
Moderation (topic)(26)
9
Wiki/Tagging(33)
0
GreaterWrong Meta(10)
Uncategorized
49
Waterfall diagram
49
Why waiting to donate harms charities
44
Frequency diagram
33
Arbital: Solving online explanations
32
Practicing Brevity
29
Arbital Blog
28
Improve comments by tagging claims
27
Arbital playpen
26
Uncountability
25
The current message of effective altruism heavily discourages creativity.
24
Guarded definition
23
Replacing Guilt
22
Extraordinary claims require extraordinary evidence
22
Some men just want to watch the world learn
21
Belief revision as probability elimination
20
Bayes' rule: Vector form
20
Exchange rates between digits
20
Why argument structure is important
19
Associativity vs commutativity
19
Bit
19
Mathematical induction
18
Fractional digits
18
Log as the change in the cost of communicating
18
What is a logarithm?
17
A whirlwind tour
17
Bayes' rule: Proportional form
17
Partially ordered set
17
Predictions For 2017
16
Conceivability
16
Group
Load More (30/1130)