RSS

Subagents

Tag

Why Subagents?

johnswentworthAug 1, 2019, 10:17 PM
175 points
48 comments7 min readLW link1 review

Multi-agent pre­dic­tive minds and AI alignment

Jan_KulveitDec 12, 2018, 11:48 PM
63 points
18 comments10 min readLW link

Build­ing up to an In­ter­nal Fam­ily Sys­tems model

Kaj_SotalaJan 26, 2019, 12:25 PM
289 points
86 comments28 min readLW link2 reviews

A non-mys­ti­cal ex­pla­na­tion of in­sight med­i­ta­tion and the three char­ac­ter­is­tics of ex­is­tence: in­tro­duc­tion and preamble

Kaj_SotalaMay 5, 2020, 7:09 PM
134 points
40 comments12 min readLW link

Men­tal Mountains

Scott AlexanderNov 27, 2019, 5:30 AM
156 points
14 comments15 min readLW link1 review
(slatestarcodex.com)

Book Sum­mary: Con­scious­ness and the Brain

Kaj_SotalaJan 16, 2019, 2:43 PM
179 points
20 comments26 min readLW link1 review

Forc­ing your­self to keep your iden­tity small is self-harm

Gordon Seidoh WorleyApr 3, 2021, 2:03 PM
40 points
10 comments2 min readLW link

Re­solv­ing in­ter­nal con­flicts re­quires listen­ing to what parts want

Richard_NgoMay 19, 2023, 12:04 AM
71 points
0 comments4 min readLW link

My cur­rent take on In­ter­nal Fam­ily Sys­tems “parts”

Kaj_SotalaJun 26, 2022, 5:40 PM
96 points
11 comments3 min readLW link
(kajsotala.fi)

The hos­tile telepaths problem

ValentineOct 27, 2024, 3:26 PM
383 points
89 comments15 min readLW link

Quick thoughts on the im­pli­ca­tions of multi-agent views of mind on AI takeover

Kaj_SotalaDec 11, 2023, 6:34 AM
47 points
14 comments4 min readLW link

Si­mu­late and Defer To More Ra­tional Selves

LoganStrohlSep 17, 2014, 6:11 PM
216 points
114 comments5 min readLW link

[Question] How effec­tive are tul­pas?

EvenflairMar 9, 2020, 5:35 PM
40 points
60 comments2 min readLW link

Subagents, trauma and rationality

Kaj_SotalaAug 14, 2019, 1:14 PM
113 points
4 comments19 min readLW link

Subagents, akra­sia, and co­her­ence in humans

Kaj_SotalaMar 25, 2019, 2:24 PM
141 points
31 comments16 min readLW link

Subagents, neu­ral Tur­ing ma­chines, thought se­lec­tion, and blindspots

Kaj_SotalaAug 6, 2019, 9:15 PM
87 points
3 comments12 min readLW link

In­te­grat­ing dis­agree­ing subagents

Kaj_SotalaMay 14, 2019, 2:06 PM
147 points
15 comments21 min readLW link

Subagents, in­tro­spec­tive aware­ness, and blending

Kaj_SotalaMar 2, 2019, 12:53 PM
110 points
19 comments9 min readLW link

[Question] How to se­lect a long-term goal and al­ign my mind to­wards it?

AlexanderDec 24, 2021, 11:40 AM
19 points
8 comments2 min readLW link

Book sum­mary: Un­lock­ing the Emo­tional Brain

Kaj_SotalaOct 8, 2019, 7:11 PM
332 points
48 comments21 min readLW link3 reviews

Com­plex Be­hav­ior from Sim­ple (Sub)Agents

moridinamaelMay 10, 2019, 9:44 PM
113 points
14 comments9 min readLW link1 review

Shoulder Ad­vi­sors 101

Duncan Sabien (Deactivated)Oct 9, 2021, 5:30 AM
202 points
124 comments14 min readLW link2 reviews

Con­sis­tently Inconsistent

Kaj_SotalaAug 4, 2011, 10:33 PM
81 points
25 comments5 min readLW link

City of Lights

AlicornMar 31, 2010, 11:30 PM
55 points
43 comments4 min readLW link

On the con­struc­tion of the self

Kaj_SotalaMay 29, 2020, 1:04 PM
77 points
18 comments17 min readLW link

Two Explorations

alkjashDec 16, 2020, 9:27 PM
63 points
8 comments9 min readLW link
(radimentary.wordpress.com)

Re­marks 1–18 on GPT (com­pressed)

Cleo NardoMar 20, 2023, 10:27 PM
145 points
35 comments31 min readLW link

In­ter­nal­iz­ing In­ter­nal Dou­ble Crux

TurnTroutApr 30, 2018, 6:23 PM
36 points
12 comments4 min readLW link

An­nounc­ing the Align­ment of Com­plex Sys­tems Re­search Group

Jan_Kulveit and technicalities
Jun 4, 2022, 4:10 AM
91 points
20 comments5 min readLW link

Neu­ral Ba­sis for Global Workspace Theory

HazardJun 22, 2020, 4:19 AM
31 points
9 comments8 min readLW link

A mechanis­tic model of meditation

Kaj_SotalaNov 6, 2019, 9:37 PM
136 points
12 comments21 min readLW link

In­trap­er­sonal negotiation

datadataeverywhereJan 23, 2011, 11:02 PM
34 points
42 comments4 min readLW link

Re­ward Is Not Enough

Steven ByrnesJun 16, 2021, 1:52 PM
124 points
19 comments10 min readLW link1 review

Wild­fire of strategicness

TsviBTJun 5, 2023, 1:59 PM
38 points
19 comments1 min readLW link

Embed­ded Agency via Abstraction

johnswentworthAug 26, 2019, 11:03 PM
42 points
20 comments11 min readLW link

The Game of Masks

SlimepriestessApr 27, 2022, 6:03 PM
50 points
18 comments11 min readLW link
(hivewired.wordpress.com)

What Value Subagents?

Gordon Seidoh WorleyJul 20, 2017, 7:19 PM
7 points
1 comment4 min readLW link
(mapandterritory.org)

Men­tal sub­agent im­pli­ca­tions for AI Safety

moridinamaelJan 3, 2021, 6:59 PM
11 points
0 comments3 min readLW link

A Master-Slave Model of Hu­man Preferences

Wei DaiDec 29, 2009, 1:02 AM
100 points
94 comments3 min readLW link

Se­quence in­tro­duc­tion: non-agent and mul­ti­a­gent mod­els of mind

Kaj_SotalaJan 7, 2019, 2:12 PM
125 points
16 comments7 min readLW link1 review

Game The­ory with­out Argmax [Part 2]

Cleo NardoNov 11, 2023, 4:02 PM
31 points
14 comments13 min readLW link

Good­hart’s Law in­side the hu­man mind

Kaj_SotalaApr 17, 2023, 1:48 PM
125 points
13 comments16 min readLW link

In­de­ci­sion and in­ter­nal­ized au­thor­ity figures

Kaj_SotalaJul 6, 2024, 10:10 AM
69 points
1 comment2 min readLW link
(kajsotala.fi)

Game The­ory with­out Argmax [Part 1]

Cleo NardoNov 11, 2023, 3:59 PM
70 points
18 comments19 min readLW link

Self-em­pa­thy as a source of “willpower”

AcademianOct 26, 2010, 2:20 PM
83 points
32 comments2 min readLW link

Many ther­apy schools work with in­ner mul­ti­plic­ity (not just IFS)

David Althaus and Ewelina Tur
Sep 17, 2022, 10:27 AM
52 points
16 comments18 min readLW link

The hor­ror of what must, yet can­not, be true

Kaj_SotalaJun 2, 2022, 10:20 AM
52 points
18 comments2 min readLW link
(kajsotala.fi)

A non-mys­ti­cal ex­pla­na­tion of “no-self” (three char­ac­ter­is­tics se­ries)

Kaj_SotalaMay 8, 2020, 10:37 AM
120 points
65 comments20 min readLW link1 review

Con­di­tions un­der which mis­al­igned sub­agents can (not) arise in classifiers

anon1Jul 11, 2018, 1:52 AM
12 points
2 comments2 min readLW link

Sys­tem 2 as work­ing-mem­ory aug­mented Sys­tem 1 reasoning

Kaj_SotalaSep 25, 2019, 8:39 AM
110 points
23 comments16 min readLW link

Seven Shiny Stories

AlicornJun 1, 2010, 12:43 AM
145 points
34 comments7 min readLW link

Eight Defi­ni­tions of Observability

Scott GarrabrantNov 10, 2020, 11:37 PM
34 points
26 comments12 min readLW link

Ten­ta­tively con­sid­er­ing emo­tional sto­ries (IFS and “get­ting into Self”)

Kaj_SotalaNov 30, 2018, 7:40 AM
40 points
31 comments4 min readLW link
(kajsotala.fi)

Slack mat­ters more than any outcome

ValentineDec 31, 2022, 8:11 PM
164 points
56 comments19 min readLW link1 review

One: a story

Richard_NgoOct 10, 2023, 12:18 AM
30 points
0 comments4 min readLW link
(www.narrativeark.xyz)

Ro­bust Agency for Peo­ple and Organizations

RaemonJul 19, 2019, 1:18 AM
65 points
10 comments12 min readLW link

Con­flicts Between Men­tal Subagents: Ex­pand­ing Wei Dai’s Master-Slave Model

Scott AlexanderAug 4, 2010, 9:16 AM
71 points
81 comments10 min readLW link

Hier­ar­chi­cal Agency: A Miss­ing Piece in AI Alignment

Jan_KulveitNov 27, 2024, 5:49 AM
112 points
21 comments11 min readLW link

Why Pro­duc­tivity Sys­tems Don’t Stick

Matt GoldenbergJan 16, 2021, 5:45 PM
62 points
22 comments3 min readLW link

Embed­ded Agency (full-text ver­sion)

Scott Garrabrant and abramdemski
Nov 15, 2018, 7:49 PM
208 points
17 comments54 min readLW link

Shard The­ory: An Overview

David UdellAug 11, 2022, 5:44 AM
166 points
34 comments10 min readLW link

Three char­ac­ter­is­tics: impermanence

Kaj_SotalaJun 5, 2020, 7:48 AM
73 points
4 comments18 min readLW link

Crav­ing, suffer­ing, and pre­dic­tive pro­cess­ing (three char­ac­ter­is­tics se­ries)

Kaj_SotalaMay 15, 2020, 1:21 PM
96 points
56 comments19 min readLW link

In­ter­nal com­mu­ni­ca­tion framework

rosehadshar and Nora_Ammann
Nov 15, 2022, 12:41 PM
38 points
13 comments12 min readLW link

Re­solv­ing von Neu­mann-Mor­gen­stern In­con­sis­tent Preferences

niplavOct 22, 2024, 11:45 AM
38 points
5 comments58 min readLW link

Strate­gic ig­no­rance and plau­si­ble deniability

Kaj_SotalaAug 10, 2011, 9:30 AM
62 points
59 comments4 min readLW link

Ayn Rand’s model of “liv­ing money”; and an up­side of burnout

AnnaSalamonNov 16, 2024, 2:59 AM
227 points
58 comments5 min readLW link

[Question] Any­one been through IFS or co­her­ence ther­apy?

warrenjordanMar 15, 2021, 6:35 PM
5 points
3 comments1 min readLW link

Non-Co­er­cive Perfectionism

Matt GoldenbergJan 26, 2021, 4:53 PM
25 points
25 comments3 min readLW link

Syn­the­sis of sub­agents: exercise

Julija KobrinovichSep 20, 2019, 5:24 PM
10 points
2 comments14 min readLW link

On In­ter­nal Fam­ily Sys­tems and multi-agent minds: a re­ply to PJ Eby

Kaj_SotalaOct 29, 2019, 2:56 PM
41 points
31 comments25 min readLW link

Ac­tu­ally updating

SaraHaxAug 23, 2019, 5:46 PM
56 points
10 comments4 min readLW link

The self-un­al­ign­ment problem

Jan_Kulveit and rosehadshar
Apr 14, 2023, 12:10 PM
155 points
24 comments10 min readLW link

Two Co­or­di­na­tion Styles

abramdemskiFeb 7, 2018, 9:00 AM
41 points
14 comments7 min readLW link

From self to crav­ing (three char­ac­ter­is­tics se­ries)

Kaj_SotalaMay 22, 2020, 12:16 PM
63 points
21 comments11 min readLW link

A Frame­work for In­ter­nal Debugging

Matt GoldenbergJan 16, 2019, 4:04 PM
44 points
3 comments5 min readLW link

Should ra­tio­nal­ists be spiritual /​ Spiritu­al­ity as over­com­ing delusion

Kaj_Sotala and romeostevensit
Mar 25, 2024, 4:48 PM
49 points
57 comments29 min readLW link

Com­mit­ting, As­sum­ing, Ex­ter­nal­iz­ing, and Internalizing

Scott GarrabrantNov 9, 2020, 4:59 PM
31 points
25 comments10 min readLW link

Subagents of Carte­sian Frames

Scott GarrabrantNov 2, 2020, 10:02 PM
53 points
6 comments8 min readLW link

Ad­di­tive and Mul­ti­plica­tive Subagents

Scott GarrabrantNov 6, 2020, 2:26 PM
20 points
7 comments12 min readLW link

Silence

alkjashMar 18, 2018, 4:10 AM
61 points
17 comments4 min readLW link
(radimentary.wordpress.com)

A Clearer Think­ing tool that teaches you to use In­ter­nal Fam­ily Sys­tems concepts

spencergApr 28, 2023, 1:42 PM
31 points
1 comment1 min readLW link
(programs.clearerthinking.org)

In­te­grat­ing Three Models of (Hu­man) Cognition

jbkjrNov 23, 2021, 1:06 AM
40 points
4 comments32 min readLW link

The Soli­taire Prin­ci­ple: Game The­ory for One

alkjashJan 17, 2018, 12:14 AM
25 points
8 comments9 min readLW link
(radimentary.wordpress.com)

Be­ware So­cial Cop­ing Strategies

LulieFeb 5, 2018, 4:48 AM
57 points
24 comments7 min readLW link

Make an ap­point­ment with your saner self

MalcolmOceanFeb 8, 2019, 5:05 AM
28 points
0 comments4 min readLW link

Which Parts Are “Me”?

Eliezer YudkowskyOct 22, 2008, 6:15 PM
69 points
117 comments5 min readLW link

Pro­saic mis­al­ign­ment from the Solomonoff Predictor

Cleo NardoDec 9, 2022, 5:53 PM
42 points
3 comments5 min readLW link

TDT for Humans

alkjashFeb 28, 2018, 5:40 AM
26 points
7 comments5 min readLW link
(radimentary.wordpress.com)

Reflec­tion of Hier­ar­chi­cal Re­la­tion­ship via Nuanced Con­di­tion­ing of Game The­ory Ap­proach for AI Devel­op­ment and Utilization

Kyoung-cheol KimJun 4, 2021, 7:20 AM
2 points
2 comments7 min readLW link

Selec­tion pro­cesses for subagents

Ryan KiddJun 30, 2022, 11:57 PM
36 points
2 comments9 min readLW link

A Cau­tion­ary Note on Un­lock­ing the Emo­tional Brain

eapacheFeb 8, 2020, 5:21 PM
55 points
20 comments2 min readLW link

Restricted Anti­na­tal­ism on Subagents

JosephineMay 13, 2021, 1:48 AM
3 points
1 comment2 min readLW link

Alien par­a­site tech­ni­cal guy

PhilGoetzJul 27, 2010, 4:51 PM
69 points
55 comments3 min readLW link

Self and No-Self

VaniverDec 29, 2019, 6:15 AM
48 points
3 comments2 min readLW link

Prune

alkjashJan 12, 2018, 10:50 PM
76 points
11 comments4 min readLW link
(radimentary.wordpress.com)

Species as Canon­i­cal Refer­ents of Su­per-Organisms

Yudhister KumarOct 18, 2024, 7:49 AM
15 points
8 comments2 min readLW link
(www.yudhister.me)
No comments.