Coherence Arguments

Tag

Coherent decisions imply consistent utilities

Eliezer YudkowskyMay 12, 2019, 9:33 PM

149 points

83 comments26 min readLW link 3 reviews

There are no coherence theorems

Feb 20, 2023, 9:25 PM

149 points

130 comments19 min readLW link 1 review

A Simple Toy Coherence Theorem

johnswentworth and David Lorell

Aug 2, 2024, 5:47 PM

74 points

22 comments7 min readLW link

[Question] Why The Focus on Expected Utility Maximisers?

DragonGodDec 27, 2022, 3:49 PM

118 points

84 comments3 min readLW link

[Question] What do coherence arguments actually prove about agentic behavior?

sunwillriseJun 1, 2024, 9:37 AM

123 points

39 comments6 min readLW link

Coherence arguments do not entail goal-directed behavior

Rohin ShahDec 3, 2018, 3:26 AM

134 points

69 comments7 min readLW link 3 reviews

[Question] Is “Strong Coherence” Anti-Natural?

DragonGodApr 11, 2023, 6:22 AM

23 points

25 comments2 min readLW link

Coherence of Caches and Agents

johnswentworthApr 1, 2024, 11:04 PM

77 points

9 comments11 min readLW link

When Most VNM-Coherent Preference Orderings Have Convergent Instrumental Incentives

TurnTroutAug 9, 2021, 5:22 PM

53 points

4 comments5 min readLW link

Coherence arguments imply a force for goal-directed behavior

KatjaGraceMar 26, 2021, 4:10 PM

91 points

25 comments11 min readLW link 1 review

(aiimpacts.org)

Contra “Strong Coherence”

DragonGodMar 4, 2023, 8:05 PM

39 points

24 comments1 min readLW link

Counting-down vs. counting-up coherence

TsviBTFeb 27, 2023, 2:59 PM

29 points

4 comments13 min readLW link

Coherent behaviour in the real world is an incoherent concept

Richard_NgoFeb 11, 2019, 5:00 PM

51 points

17 comments9 min readLW link

Three ways that “Sufficiently optimized agents appear coherent” can be false

Wei DaiMar 5, 2019, 9:52 PM

65 points

3 comments3 min readLW link

[Question] Is there a “coherent decisions imply consistent utilities”-style argument for non-lexicographic preferences?

TetraspaceJun 29, 2021, 7:14 PM

4 points

20 comments1 min readLW link

[Linkpost] Will AI avoid exploitation?

cdkgAug 6, 2023, 2:28 PM

22 points

1 comment1 min readLW link

Measuring Coherence and Goal-Directedness in RL Policies

dx26Apr 22, 2024, 6:26 PM

10 points

0 comments7 min readLW link

Let’s look for coherence theorems

ValdesMay 7, 2023, 2:45 PM

25 points

18 comments6 min readLW link

[Request for Distillation] Coherence of Distributed Decisions With Different Inputs Implies Conditioning

johnswentworthApr 25, 2022, 5:01 PM

22 points

14 comments2 min readLW link

It Can’t Be Mesa-Optimizers All The Way Down (Or Else It Can’t Be Long-Term Supercoherence?)

Austin WitteMar 31, 2023, 7:21 AM

20 points

5 comments4 min readLW link

[Question] Money Pump Arguments assume Memoryless Agents. Isn’t this Unrealistic?

DalcyAug 16, 2024, 4:16 AM

26 points

6 comments1 min readLW link

Comment on Coherence arguments do not imply goal directed behavior

Ronny FernandezDec 6, 2019, 9:30 AM

30 points

8 comments5 min readLW link

The hot mess theory of AI misalignment: More intelligent agents behave less coherently

Jonathan YanMar 10, 2023, 12:20 AM

48 points

22 comments1 min readLW link

(sohl-dickstein.github.io)

Deriving Conditional Expected Utility from Pareto-Efficient Decisions

Thomas KwaMay 5, 2022, 3:21 AM

24 points

1 comment6 min readLW link

The “Measuring Stick of Utility” Problem

johnswentworthMay 25, 2022, 4:17 PM

74 points

25 comments3 min readLW link

Do incoherent entities have stronger reason to become more coherent than less?

KatjaGraceJun 30, 2021, 5:50 AM

46 points

5 comments4 min readLW link

(worldspiritsockpuppet.com)

The Impossibility of a Rational Intelligence Optimizer

Nicolas VillarrealJun 6, 2024, 4:14 PM

−9 points

5 comments14 min readLW link

No comments.