Counterfactuals

Tag

Auditing LMs with counterfactual search: a tool for control and ELK

Jacob PfauFeb 20, 2024, 12:02 AM

28 points

6 comments10 min readLW link

Causality and determinism in social science—An investigation using Pearl’s causal ladder

tailcalledJan 3, 2022, 5:51 PM

12 points

10 comments9 min readLW link

Some thoughts on “The Nature of Counterfactuals”

tailcalledJan 16, 2022, 6:12 PM

20 points

11 comments11 min readLW link

Probability Theory Fundamentals 102: Territory that Probability is in the Map of

Ape in the coatMar 26, 2025, 6:40 AM

10 points

5 comments9 min readLW link

Circular Counterfactuals “Only that which Happens is Possible”

SebastianG Mar 23, 2022, 2:40 PM

4 points

15 comments9 min readLW link

Results: Circular Dependency of Counterfactuals Prize

Chris_LeongApr 5, 2022, 6:29 AM

19 points

0 comments1 min readLW link

Four factors that moderate the intensity of emotions

RubyNov 24, 2018, 8:40 PM

63 points

11 comments8 min readLW link

Getting Unstuck on Counterfactuals

Chris_LeongJul 20, 2022, 5:31 AM

7 points

1 comment2 min readLW link

Applying the Counterfactual Prisoner’s Dilemma to Logical Uncertainty

Chris_LeongSep 16, 2020, 10:34 AM

9 points

5 comments2 min readLW link

Counterfactuals from ensembles of peers

David JohnstonJan 4, 2022, 7:01 AM

3 points

4 comments7 min readLW link

The Many Faces of Infra-Beliefs

DiffractorApr 6, 2021, 10:43 AM

30 points

6 comments63 min readLW link

My Current Take on Counterfactuals

abramdemskiApr 9, 2021, 5:51 PM

54 points

57 comments25 min readLW link

The Nature of Counterfactuals

Chris_LeongJun 5, 2021, 9:18 AM

16 points

18 comments4 min readLW link

Agency and the unreliable autonomous car

Alex FlintJul 7, 2021, 2:58 PM

29 points

24 comments10 min readLW link

Counterfactual Contracts

harsimonySep 16, 2021, 3:20 PM

10 points

4 comments9 min readLW link

(harsimony.wordpress.com)

Decisions: Ontologically Shifting to Determinism

Chris_LeongDec 21, 2022, 12:41 PM

8 points

11 comments6 min readLW link

Counterfactuals are Confusing because of an Ontological Shift

Chris_LeongAug 5, 2022, 7:03 PM

17 points

35 comments2 min readLW link

Counterfactuals for Perfect Predictors

Chris_LeongAug 6, 2018, 12:24 PM

12 points

17 comments6 min readLW link

Counterfactual Induction

DiffractorDec 17, 2019, 5:03 AM

22 points

7 comments6 min readLW link

Counterfactual Reprogramming Decision Theory

lukeprogSep 10, 2012, 1:35 AM

18 points

8 comments1 min readLW link

Counterfactual Calculation and Observational Knowledge

Vladimir_NesovJan 31, 2011, 4:28 PM

20 points

188 comments1 min readLW link

Counterfactuals as a matter of Social Convention

Chris_LeongNov 30, 2019, 10:35 AM

10 points

4 comments2 min readLW link

Counterfactual trade

owencbMar 9, 2015, 1:23 PM

22 points

19 comments3 min readLW link

Counterfactual Mugging and Logical Uncertainty

Vladimir_NesovSep 5, 2009, 10:31 PM

16 points

21 comments3 min readLW link

Counterfactuals: Smoking Lesion vs. Newcomb’s

Chris_LeongDec 8, 2019, 9:02 PM

9 points

24 comments3 min readLW link

Counterfactually uninfluenceable agents

Stuart_ArmstrongJun 2, 2017, 4:17 PM

11 points

0 comments2 min readLW link

Counterfactuals and reflective oracles

NisanSep 5, 2018, 8:54 AM

9 points

0 comments6 min readLW link

Counterfactual Induction (Algorithm Sketch, Fixpoint proof)

DiffractorDec 17, 2019, 5:04 AM

5 points

2 comments7 min readLW link

[Question] Counterfactual Mugging: Why should you pay?

Chris_LeongDec 17, 2019, 10:16 PM

7 points

59 comments3 min readLW link

Counterfactual mugging: alien abduction edition

EmileSep 28, 2010, 9:25 PM

4 points

18 comments1 min readLW link

Counterfactual Induction (Lemma 4)

DiffractorDec 17, 2019, 5:05 AM

4 points

0 comments7 min readLW link

Counterfactual do-what-I-mean

Stuart_ArmstrongOct 27, 2016, 1:54 PM

5 points

3 comments1 min readLW link

Counterfactual Mugging v. Subjective Probability

MBlumeJul 20, 2009, 4:31 PM

4 points

32 comments1 min readLW link

Counterfactuals on POMDP

Stuart_ArmstrongJun 2, 2017, 4:30 PM

2 points

0 comments2 min readLW link

Counterfactual self-defense

MrMindNov 23, 2012, 10:15 AM

2 points

9 comments1 min readLW link

Counterfactual do-what-I-mean

Stuart_ArmstrongOct 27, 2016, 1:53 PM

0 points

3 comments1 min readLW link

Logical Counterfactuals and Proposition graphs, Part 1

Donald HobsonAug 22, 2019, 10:06 PM

20 points

0 comments3 min readLW link

Logical Counterfactuals are low-res

ShmiOct 15, 2018, 3:36 AM

23 points

14 comments1 min readLW link

(donerkebabphilosophy.wordpress.com)

The Counterfactual Prisoner’s Dilemma

Chris_LeongDec 21, 2019, 1:44 AM

21 points

17 comments3 min readLW link

Logical Counterfactuals & the Cooperation Game

Chris_LeongAug 14, 2018, 2:00 PM

16 points

26 comments2 min readLW link

Logical Counterfactuals and Proposition graphs, Part 2

Donald HobsonAug 31, 2019, 8:58 PM

13 points

0 comments3 min readLW link

Can Counterfactuals Be True?

Eliezer YudkowskyJul 24, 2008, 4:40 AM

33 points

47 comments4 min readLW link

A counterfactual and hypothetical note on AI safety design

Stuart_ArmstrongMar 11, 2015, 4:20 PM

13 points

1 comment1 min readLW link

Logical Counterfactuals and Proposition graphs, Part 3

Donald HobsonSep 5, 2019, 3:03 PM

6 points

0 comments4 min readLW link

Extremely Counterfactual Mugging or: the gist of Transparent Newcomb

BongoFeb 9, 2011, 3:20 PM

10 points

79 comments1 min readLW link

Provability Counterfactuals vs Three Axioms of Galles and Pearl

IAFF-User-52Aug 30, 2015, 2:48 AM

6 points

0 comments1 min readLW link

(epsilonofdoom.blogspot.com)

Logical counterfactuals for random algorithms

Vanessa KosoyJan 6, 2016, 1:29 PM

5 points

0 comments10 min readLW link

[LINK] Counterfactual Strategies

StrilancJun 17, 2014, 7:29 PM

5 points

14 comments1 min readLW link

Logical Counterfactuals Consistent Under Self-Modification

abramdemskiDec 15, 2015, 6:38 AM

3 points

2 comments8 min readLW link

Logical counterfactuals and differential privacy

NisanFeb 4, 2018, 12:17 AM

1 point

1 comment5 min readLW link

What makes counterfactuals comparable?

Chris_LeongApr 24, 2020, 10:47 PM

11 points

6 comments3 min readLW link

The odd counterfactuals of playing chicken

Benya_FallensteinFeb 2, 2015, 7:15 AM

6 points

0 comments8 min readLW link

Hazing as Counterfactual Mugging?

SilasBartaOct 11, 2010, 2:17 PM

5 points

8 comments1 min readLW link

Third-person counterfactuals

Benya_FallensteinFeb 3, 2015, 1:13 AM

4 points

4 comments6 min readLW link

The many counterfactuals of counterfactual mugging

Scott GarrabrantApr 12, 2016, 8:04 PM

2 points

3 comments2 min readLW link

Stabilizing logical counterfactuals by pseudorandomization

Vanessa KosoyMay 25, 2016, 12:05 PM

1 point

2 comments8 min readLW link

Un-manipulable counterfactuals

Stuart_ArmstrongFeb 12, 2015, 7:51 PM

1 point

5 comments1 min readLW link

Orthogonality: action counterfactuals

Stuart_ArmstrongFeb 17, 2015, 9:04 PM

0 points

0 comments1 min readLW link

Newcomblike problem: Counterfactual Informant

ClippyApr 12, 2012, 8:25 PM

−3 points

24 comments1 min readLW link

[Question] Would solving logical counterfactuals solve anthropics?

Chris_LeongApr 5, 2019, 11:08 AM

20 points

52 comments1 min readLW link

Optimal and Causal Counterfactual Worlds

Scott GarrabrantMay 12, 2015, 3:16 AM

14 points

4 comments3 min readLW link

Sleeping Beauty gets counterfactually mugged

Stuart_ArmstrongMar 26, 2009, 11:44 AM

6 points

34 comments2 min readLW link

Causal graphs and counterfactuals

Stuart_ArmstrongAug 30, 2016, 4:12 PM

7 points

2 comments1 min readLW link

Transitive negotiations with counterfactual agents

Scott GarrabrantOct 20, 2016, 11:27 PM

4 points

0 comments1 min readLW link

Agents detecting agents: counterfactual versus influence

Stuart_ArmstrongSep 18, 2015, 4:17 PM

5 points

4 comments7 min readLW link

Humans get different counterfactuals

Stuart_ArmstrongMar 23, 2015, 2:54 PM

4 points

2 comments1 min readLW link

Causal graphs and counterfactuals

Stuart_ArmstrongAug 30, 2016, 4:06 PM

0 points

2 comments1 min readLW link

The Curse Of The Counterfactual

pjebyNov 1, 2019, 6:34 PM

140 points

35 comments19 min readLW link 1 review

Two Alternatives to Logical Counterfactuals

jessicataApr 1, 2020, 9:48 AM

39 points

61 comments5 min readLW link

(unstableontology.com)

Addressing three problems with counterfactual corrigibility: bad bets, defending against backstops, and overconfidence.

RyanCareyOct 21, 2018, 12:03 PM

23 points

1 comment6 min readLW link

Standard ML Oracles vs Counterfactual ones

Stuart_ArmstrongOct 10, 2018, 8:01 PM

18 points

5 comments6 min readLW link

An environment for studying counterfactuals

NisanJul 11, 2018, 12:14 AM

15 points

6 comments3 min readLW link

On the Role of Counterfactuals in Learning

Max KanwalJul 11, 2018, 2:45 AM

11 points

2 comments3 min readLW link

Does TDT pay in Counterfactual Mugging?

BongoNov 29, 2010, 9:31 PM

4 points

5 comments1 min readLW link

You have just been Counterfactually Mugged!

CronoDASAug 19, 2009, 10:24 PM

7 points

25 comments1 min readLW link

[Question] Decisions with Non-Logical Counterfactuals: request for input

reavowedOct 24, 2019, 5:23 PM

3 points

11 comments3 min readLW link

[Question] What are some concrete problems about logical counterfactuals?

Chris_LeongDec 16, 2018, 10:20 AM

25 points

4 comments1 min readLW link

I Was Not Almost Wrong But I Was Almost Right: Close-Call Counterfactuals and Bias

Kaj_SotalaMar 8, 2012, 5:39 AM

86 points

40 comments9 min readLW link

Divergence on Evidence Due to Differing Priors—A Political Case Study

DavidmanheimSep 16, 2019, 11:01 AM

27 points

3 comments3 min readLW link

A useful level distinction

Charlie SteinerFeb 24, 2018, 6:39 AM

8 points

4 comments2 min readLW link

JFK was not assassinated: prior probability zero events

Stuart_ArmstrongApr 27, 2016, 11:47 AM

38 points

38 comments3 min readLW link

Motivating a Semantics of Logical Counterfactuals

Sam_A_BarnettSep 22, 2017, 1:10 AM

22 points

3 comments2 min readLW link

Open Problems Regarding Counterfactuals: An Introduction For Beginners

DiffractorJul 18, 2017, 2:21 AM

21 points

6 comments1 min readLW link

(www.overleaf.com)

UDT might not pay a Counterfactual Mugger

winwonceNov 21, 2020, 11:27 PM

5 points

18 comments2 min readLW link

Counterfactual Planning in AGI Systems

Koen.HoltmanFeb 3, 2021, 1:54 PM

10 points

0 comments5 min readLW link

Graphical World Models, Counterfactuals, and Machine Learning Agents

Koen.HoltmanFeb 17, 2021, 11:07 AM

6 points

2 comments10 min readLW link

Creating AGI Safety Interlocks

Koen.HoltmanFeb 5, 2021, 12:01 PM

7 points

4 comments8 min readLW link

Safely controlling the AGI agent reward function

Koen.HoltmanFeb 17, 2021, 2:47 PM

8 points

0 comments5 min readLW link

What is a Counterfactual: An Elementary Introduction to the Causal Hierarchy

DarmaniJan 2, 2022, 3:46 AM

11 points

2 comments5 min readLW link

Initial Thoughts on Dissolving “Couldness”

DragonGodSep 22, 2022, 9:23 PM

6 points

1 comment3 min readLW link

[Sketch] Validity Criterion for Logical Counterfactuals

DragonGodOct 11, 2022, 1:31 PM

6 points

0 comments6 min readLW link

Against the normative realist’s wager

Joe CarlsmithOct 13, 2022, 4:35 PM

16 points

9 comments23 min readLW link

An Ontology for Strategic Epistemology

StrivingForLegibilityDec 28, 2023, 10:11 PM

9 points

0 comments5 min readLW link

Why are counterfactuals elusive?

Martín SotoMar 3, 2023, 8:13 PM

14 points

6 comments2 min readLW link

Distributed Strategic Epistemology

StrivingForLegibilityDec 28, 2023, 10:12 PM

11 points

0 comments3 min readLW link

Logical Line-Of-Sight Makes Games Sequential or Loopy

StrivingForLegibilityJan 19, 2024, 4:05 AM

40 points

0 comments7 min readLW link

Counterfactual Mechanism Networks

StrivingForLegibilityJan 30, 2024, 8:30 PM

4 points

0 comments5 min readLW link

To Boldly Code

StrivingForLegibilityJan 26, 2024, 6:25 PM

25 points

4 comments3 min readLW link

Incorporating Mechanism Design Into Decision Theory

StrivingForLegibilityJan 26, 2024, 6:25 PM

17 points

4 comments4 min readLW link

(Some) Humans do choose 5 dollars in the 5-and-10 problem

Akira PyinyaApr 7, 2025, 10:56 PM

−5 points

1 comment1 min readLW link

Timeless Control

Eliezer YudkowskyJun 7, 2008, 5:16 AM

47 points

69 comments9 min readLW link

Timeless Decision Theory and Meta-Circular Decision Theory

Eliezer YudkowskyAug 20, 2009, 10:07 PM

42 points

37 comments10 min readLW link

Counterfactuals, thick and thin

NisanJul 31, 2018, 3:43 PM

28 points

11 comments2 min readLW link

Deconfusing Logical Counterfactuals

Chris_LeongJan 30, 2019, 3:13 PM

27 points

16 comments11 min readLW link

Conditioning, Counterfactuals, Exploration, and Gears

DiffractorJul 10, 2018, 10:11 PM

28 points

1 comment5 min readLW link

Counterfactual Mugging Poker Game

Scott GarrabrantJun 13, 2018, 11:34 PM

122 points

3 comments1 min readLW link

Counterfactual Mugging

Vladimir_NesovMar 19, 2009, 6:08 AM

82 points

296 comments2 min readLW link

Counterfactual Oracles = online supervised learning with random selection of training episodes

Wei DaiSep 10, 2019, 8:29 AM

52 points

26 comments3 min readLW link

Counterfactual outcome state transition parameters

Anders_HJul 27, 2018, 9:13 PM

37 points

1 comment6 min readLW link

Counterfactual resiliency test for non-causal models

Stuart_ArmstrongAug 30, 2012, 5:30 PM

34 points

78 comments7 min readLW link

Counterfactuals versus the laws of physics

Stuart_ArmstrongFeb 18, 2020, 1:21 PM

16 points

0 comments1 min readLW link

Counterfactuals are an Answer, Not a Question

Chris_LeongSep 3, 2019, 3:36 PM

14 points

6 comments4 min readLW link

Victor Porton Sep 1, 2023, 8:21 AM
1 point
0
I always thought that counter-factual means some message that is not conforming to reality. Was my personal understanding of semantics of this word wrong? Or maybe, your definition and my intuitive understanding can be reconciled? Isn’t counter-factual as contrary to past decisions a special case of counter-factual as not conforming to reality? If yes, can the word be used in both senses, dependently on a context?