Coherence Arguments

Tag

There are no coherence theorems

Dan H and EJT

20 Feb 2023 21:25 UTC

145 points

125 comments19 min readLW link 1 review

Coherent decisions imply consistent utilities

Eliezer Yudkowsky12 May 2019 21:33 UTC

149 points

81 comments26 min readLW link 3 reviews

Coherence arguments do not entail goal-directed behavior

Rohin Shah3 Dec 2018 3:26 UTC

133 points

69 comments7 min readLW link 3 reviews

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

sunwillrise1 Jun 2024 9:37 UTC

123 points

35 comments6 min readLW link

Coherence arguments imply a force for goal-directed behavior

KatjaGrace26 Mar 2021 16:10 UTC

91 points

25 comments11 min readLW link 1 review

(aiimpacts.org)

Coherence of Caches and Agents

johnswentworth1 Apr 2024 23:04 UTC

76 points

9 comments11 min readLW link

A Simple Toy Coherence Theorem

johnswentworth and David Lorell

2 Aug 2024 17:47 UTC

74 points

20 comments7 min readLW link

When Most VNM-Coherent Preference Orderings Have Convergent Instrumental Incentives

TurnTrout9 Aug 2021 17:22 UTC

53 points

4 comments5 min readLW link

Counting-down vs. counting-up coherence

TsviBT27 Feb 2023 14:59 UTC

29 points

4 comments13 min readLW link

Contra “Strong Coherence”

DragonGod4 Mar 2023 20:05 UTC

39 points

24 comments1 min readLW link

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

DragonGod11 Apr 2023 6:22 UTC

23 points

25 comments2 min readLW link

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

Dalcy16 Aug 2024 4:16 UTC

23 points

6 comments1 min readLW link

The Impossibility of a Rational Intelligence Optimizer

Nicolas Villarreal6 Jun 2024 16:14 UTC

−9 points

5 comments14 min readLW link

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

Wei Dai5 Mar 2019 21:52 UTC

65 points

3 comments3 min readLW link

Comment on Coherence arguments do not imply goal directed behavior

Ronny Fernandez6 Dec 2019 9:30 UTC

30 points

8 comments5 min readLW link

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

Tetraspace29 Jun 2021 19:14 UTC

4 points

20 comments1 min readLW link

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

Jonathan Yan10 Mar 2023 0:20 UTC

47 points

21 comments1 min readLW link

(sohl-dickstein.github.io)

Deriving Conditional Expected Utility from Pareto-Efficient Decisions

Thomas Kwa5 May 2022 3:21 UTC

24 points

1 comment6 min readLW link

The “Measuring Stick of Utility” Problem

johnswentworth25 May 2022 16:17 UTC

74 points

25 comments3 min readLW link

[Question] Why The Focus on Expected Utility Maximisers?

DragonGod27 Dec 2022 15:49 UTC

116 points

84 comments3 min readLW link

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

johnswentworth25 Apr 2022 17:01 UTC

22 points

14 comments2 min readLW link

Measuring Coherence and Goal-Directedness in RL Policies

dx2622 Apr 2024 18:26 UTC

10 points

0 comments7 min readLW link

Coherent behaviour in the real world is an incoherent concept

Richard_Ngo11 Feb 2019 17:00 UTC

51 points

17 comments9 min readLW link

Let’s look for coherence theorems

Valdes7 May 2023 14:45 UTC

25 points

18 comments6 min readLW link

[Linkpost] Will AI avoid exploitation?

cdkg6 Aug 2023 14:28 UTC

22 points

1 comment1 min readLW link

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

KatjaGrace30 Jun 2021 5:50 UTC

46 points

5 comments4 min readLW link

(worldspiritsockpuppet.com)

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

Austin Witte31 Mar 2023 7:21 UTC

20 points

5 comments4 min readLW link

No comments.

Co­her­ence Arguments

Coherence Arguments