RSS

Co­her­ence Arguments

Tag

Co­her­ent de­ci­sions im­ply con­sis­tent utilities

Eliezer YudkowskyMay 12, 2019, 9:33 PM
149 points
81 comments26 min readLW link3 reviews

There are no co­her­ence theorems

Feb 20, 2023, 9:25 PM
147 points
130 comments19 min readLW link1 review

A Sim­ple Toy Co­her­ence Theorem

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

Co­her­ence ar­gu­ments do not en­tail goal-di­rected behavior

Rohin ShahDec 3, 2018, 3:26 AM
134 points
69 comments7 min readLW link3 reviews

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

sunwillriseJun 1, 2024, 9:37 AM
123 points
37 comments6 min readLW link

Co­her­ence of Caches and Agents

johnswentworthApr 1, 2024, 11:04 PM
77 points
9 comments11 min readLW link

Count­ing-down vs. count­ing-up coherence

TsviBTFeb 27, 2023, 2:59 PM
29 points
4 comments13 min readLW link

Con­tra “Strong Co­her­ence”

DragonGodMar 4, 2023, 8:05 PM
39 points
24 comments1 min readLW link

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

DragonGodApr 11, 2023, 6:22 AM
23 points
25 comments2 min readLW link

Co­her­ence ar­gu­ments im­ply a force for goal-di­rected behavior

KatjaGraceMar 26, 2021, 4:10 PM
91 points
25 comments11 min readLW link1 review
(aiimpacts.org)

When Most VNM-Co­her­ent Prefer­ence Order­ings Have Con­ver­gent In­stru­men­tal Incentives

TurnTroutAug 9, 2021, 5:22 PM
53 points
4 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
21 comments1 min readLW link
(sohl-dickstein.github.io)

Co­her­ent be­havi­our in the real world is an in­co­her­ent concept

Richard_NgoFeb 11, 2019, 5:00 PM
51 points
17 comments9 min readLW link

Mea­sur­ing Co­her­ence and Goal-Direct­ed­ness in RL Policies

dx26Apr 22, 2024, 6:26 PM
10 points
0 comments7 min readLW link

The Im­pos­si­bil­ity of a Ra­tional In­tel­li­gence Optimizer

Nicolas VillarrealJun 6, 2024, 4:14 PM
−9 points
5 comments14 min readLW link

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

DalcyAug 16, 2024, 4:16 AM
23 points
6 comments1 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

Let’s look for co­her­ence theorems

ValdesMay 7, 2023, 2:45 PM
25 points
18 comments6 min readLW link

[Linkpost] Will AI avoid ex­ploita­tion?

cdkgAug 6, 2023, 2:28 PM
22 points
1 comment1 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)

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

Com­ment on Co­her­ence ar­gu­ments do not im­ply goal di­rected behavior

Ronny FernandezDec 6, 2019, 9:30 AM
30 points
8 comments5 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

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

[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
No comments.