RSS

Nat­u­ral Abstraction

TagLast edit: Oct 10, 2022, 5:45 PM by Raemon

The Natural Abstraction hypothesis says that:

Our physical world abstracts well: for most systems, the information relevant “far away” from the system (in various senses) is much lower-dimensional than the system itself. These low-dimensional summaries are exactly the high-level abstract objects/​concepts typically used by humans.

These abstractions are “natural”: a wide variety of cognitive architectures will learn to use approximately the same high-level abstract objects/​concepts to reason about the world.

(from “Testing the Natural Abstraction Hypothesis”)

Nat­u­ral Ab­strac­tions: Key claims, The­o­rems, and Critiques

Mar 16, 2023, 4:37 PM
239 points
23 comments45 min readLW link3 reviews

Nat­u­ral La­tents: The Concepts

Mar 20, 2024, 6:21 PM
90 points
18 comments19 min readLW link

Nat­u­ral La­tents: The Math

Dec 27, 2023, 7:03 PM
123 points
40 comments12 min readLW link2 reviews

Align­ment By Default

johnswentworthAug 12, 2020, 6:54 PM
174 points
96 comments11 min readLW link2 reviews

Test­ing The Nat­u­ral Ab­strac­tion Hy­poth­e­sis: Pro­ject Intro

johnswentworthApr 6, 2021, 9:24 PM
168 points
41 comments6 min readLW link1 review

The Nat­u­ral Ab­strac­tion Hy­poth­e­sis: Im­pli­ca­tions and Evidence

CallumMcDougallDec 14, 2021, 11:14 PM
39 points
9 comments19 min readLW link

What is a Tool?

Jun 25, 2024, 11:40 PM
62 points
4 comments6 min readLW link

Con­tra­pos­i­tive Nat­u­ral Ab­strac­tion—Pro­ject Intro

Elliot CallenderJun 24, 2024, 6:37 PM
4 points
5 comments2 min readLW link

Public Static: What is Ab­strac­tion?

johnswentworthJun 9, 2020, 6:36 PM
97 points
18 comments11 min readLW link

Agency As a Nat­u­ral Abstraction

Thane RuthenisMay 13, 2022, 6:02 PM
55 points
9 comments13 min readLW link

Test­ing The Nat­u­ral Ab­strac­tion Hy­poth­e­sis: Pro­ject Update

johnswentworthSep 20, 2021, 3:44 AM
88 points
17 comments8 min readLW link1 review

Rele­vant to nat­u­ral ab­strac­tions: Eu­clidean Sym­me­try Equiv­ar­i­ant Ma­chine Learn­ing—Overview, Ap­pli­ca­tions, and Open Questions

the gears to ascensionDec 8, 2022, 6:01 PM
8 points
0 comments1 min readLW link
(youtu.be)

[ASoT] Nat­u­ral ab­strac­tions and AlphaZero

Ulisse MiniDec 10, 2022, 5:53 PM
33 points
1 comment1 min readLW link
(arxiv.org)

[Heb­bian Nat­u­ral Ab­strac­tions] Math­e­mat­i­cal Foundations

Dec 25, 2022, 8:58 PM
15 points
2 comments6 min readLW link
(www.snellessen.com)

Nat­u­ral Ab­strac­tion: Con­ver­gent Prefer­ences Over In­for­ma­tion Structures

paulomOct 14, 2023, 6:34 PM
13 points
1 comment36 min readLW link

AISafety.info: What is the “nat­u­ral ab­strac­tions hy­poth­e­sis”?

AlgonOct 5, 2024, 12:31 PM
38 points
2 comments3 min readLW link
(aisafety.info)

Towards the Oper­a­tional­iza­tion of Philos­o­phy & Wisdom

Thane RuthenisOct 28, 2024, 7:45 PM
20 points
2 comments33 min readLW link
(aiimpacts.org)

Min­i­mal Mo­ti­va­tion of Nat­u­ral Latents

Oct 14, 2024, 10:51 PM
46 points
14 comments3 min readLW link

Disen­tan­gling Rep­re­sen­ta­tions through Multi-task Learning

Bogdan Ionut CirsteaNov 24, 2024, 1:10 PM
14 points
1 comment1 min readLW link
(arxiv.org)

Nat­u­ral ab­strac­tions are ob­server-de­pen­dent: a con­ver­sa­tion with John Wentworth

Martín SotoFeb 12, 2024, 5:28 PM
39 points
13 comments7 min readLW link

AGI will be made of het­ero­ge­neous com­po­nents, Trans­former and Selec­tive SSM blocks will be among them

Roman LeventovDec 27, 2023, 2:51 PM
33 points
9 comments4 min readLW link

The Plan − 2023 Version

johnswentworthDec 29, 2023, 11:34 PM
151 points
40 comments31 min readLW link1 review

From Con­cep­tual Spaces to Quan­tum Con­cepts: For­mal­is­ing and Learn­ing Struc­tured Con­cep­tual Models

Roman LeventovFeb 6, 2024, 10:18 AM
8 points
1 comment4 min readLW link
(arxiv.org)

Ab­stract Math­e­mat­i­cal Con­cepts vs. Ab­strac­tions Over Real-World Systems

Thane RuthenisFeb 18, 2025, 6:04 PM
11 points
1 comment4 min readLW link

Nat­u­ral La­tents Are Not Ro­bust To Tiny Mixtures

Jun 7, 2024, 6:53 PM
61 points
8 comments5 min readLW link

AlignedCut: Vi­sual Con­cepts Dis­cov­ery on Brain-Guided Univer­sal Fea­ture Space

Bogdan Ionut CirsteaSep 14, 2024, 11:23 PM
17 points
1 comment1 min readLW link
(arxiv.org)

Val­i­dat­ing /​ find­ing al­ign­ment-rele­vant con­cepts us­ing neu­ral data

Bogdan Ionut CirsteaSep 20, 2024, 9:12 PM
7 points
0 comments1 min readLW link
(docs.google.com)

Ideal­ized Agents Are Ap­prox­i­mate Causal Mir­rors (+ Rad­i­cal Op­ti­mism on Agent Foun­da­tions)

Thane RuthenisDec 22, 2023, 8:19 PM
74 points
14 comments6 min readLW link

What Does The Nat­u­ral Ab­strac­tion Frame­work Say About ELK?

johnswentworthFeb 15, 2022, 2:27 AM
35 points
0 comments6 min readLW link

[Heb­bian Nat­u­ral Ab­strac­tions] Introduction

Nov 21, 2022, 8:34 PM
34 points
3 comments4 min readLW link
(www.snellessen.com)

Select Agent Speci­fi­ca­tions as Nat­u­ral Abstractions

lukemarksApr 7, 2023, 11:16 PM
19 points
3 comments5 min readLW link

A rough and in­com­plete re­view of some of John Went­worth’s research

So8resMar 28, 2023, 6:52 PM
175 points
18 comments18 min readLW link

The Light­cone The­o­rem: A Bet­ter Foun­da­tion For Nat­u­ral Ab­strac­tion?

johnswentworthMay 15, 2023, 2:24 AM
69 points
25 comments6 min readLW link

$500 Bounty/​Prize Prob­lem: Chan­nel Ca­pac­ity Us­ing “Insen­si­tive” Functions

johnswentworthMay 16, 2023, 9:31 PM
40 points
11 comments2 min readLW link

Ab­strac­tion is Big­ger than Nat­u­ral Abstraction

Nicholas / Heather KrossMay 31, 2023, 12:00 AM
18 points
0 comments5 min readLW link
(www.thinkingmuchbetter.com)

Nat­u­ral Cat­e­gories Update

Logan ZoellnerOct 10, 2022, 3:19 PM
33 points
6 comments2 min readLW link

Com­put­ing Nat­u­ral Ab­strac­tions: Lin­ear Approximation

johnswentworthApr 15, 2021, 5:47 PM
41 points
22 comments7 min readLW link

AXRP Epi­sode 15 - Nat­u­ral Ab­strac­tions with John Wentworth

DanielFilanMay 23, 2022, 5:40 AM
34 points
1 comment58 min readLW link

The Core of the Align­ment Prob­lem is...

Aug 17, 2022, 8:07 PM
76 points
10 comments9 min readLW link

Causal Ab­strac­tion Toy Model: Med­i­cal Sensor

johnswentworthDec 11, 2019, 9:12 PM
34 points
6 comments6 min readLW link

The Plan − 2022 Update

johnswentworthDec 1, 2022, 8:43 PM
239 points
37 comments8 min readLW link1 review

Take 4: One prob­lem with nat­u­ral ab­strac­tions is there’s too many of them.

Charlie SteinerDec 5, 2022, 10:39 AM
37 points
4 comments1 min readLW link

Take 5: Another prob­lem for nat­u­ral ab­strac­tions is laz­i­ness.

Charlie SteinerDec 6, 2022, 7:00 AM
31 points
4 comments3 min readLW link

If Went­worth is right about nat­u­ral ab­strac­tions, it would be bad for alignment

Wuschel SchulzDec 8, 2022, 3:19 PM
29 points
5 comments4 min readLW link

The “Min­i­mal La­tents” Ap­proach to Nat­u­ral Abstractions

johnswentworthDec 20, 2022, 1:22 AM
53 points
24 comments12 min readLW link

Causal ab­strac­tions vs infradistributions

Pablo VillalobosDec 26, 2022, 12:21 AM
24 points
0 comments6 min readLW link

Si­mu­lacra are Things

janusJan 8, 2023, 11:03 PM
63 points
7 comments2 min readLW link

World-Model In­ter­pretabil­ity Is All We Need

Thane RuthenisJan 14, 2023, 7:37 PM
35 points
22 comments21 min readLW link

Why I’m not work­ing on {de­bate, RRM, ELK, nat­u­ral ab­strac­tions}

Steven ByrnesFeb 10, 2023, 7:22 PM
71 points
19 comments9 min readLW link

The con­cep­tual Dop­pelgänger problem

TsviBTFeb 12, 2023, 5:23 PM
12 points
5 comments4 min readLW link

[Question] Is In­struc­tGPT Fol­low­ing In­struc­tions in Other Lan­guages Sur­pris­ing?

DragonGodFeb 13, 2023, 11:26 PM
39 points
15 comments1 min readLW link

[Ap­pendix] Nat­u­ral Ab­strac­tions: Key Claims, The­o­rems, and Critiques

Mar 16, 2023, 4:38 PM
48 points
0 comments13 min readLW link

Wittgen­stein’s Lan­guage Games and the Cri­tique of the Nat­u­ral Ab­strac­tion Hypothesis

Chris_LeongMar 16, 2023, 7:56 AM
16 points
19 comments2 min readLW link

[Question] [DISC] Are Values Ro­bust?

DragonGodDec 21, 2022, 1:00 AM
12 points
9 comments2 min readLW link

Jonothan Go­rard:The ter­ri­tory is iso­mor­phic to an equiv­alence class of its maps

Daniel CSep 7, 2024, 10:04 AM
19 points
18 comments2 min readLW link
(x.com)

My AI Model Delta Com­pared To Yudkowsky

johnswentworthJun 10, 2024, 4:12 PM
277 points
103 comments4 min readLW link

Con­tra Steiner on Too Many Nat­u­ral Abstractions

DragonGodDec 24, 2022, 5:42 PM
10 points
6 comments1 min readLW link

Align­ment Tar­gets and The Nat­u­ral Ab­strac­tion Hypothesis

Stephen FowlerMar 8, 2023, 11:45 AM
10 points
0 comments3 min readLW link

[Linkpost] Con­cept Align­ment as a Pr­ereq­ui­site for Value Alignment

Bogdan Ionut CirsteaNov 4, 2023, 5:34 PM
27 points
0 comments1 min readLW link
(arxiv.org)

Si­mu­la­tors In­crease the Like­li­hood of Align­ment by Default

Wuschel SchulzApr 30, 2023, 4:32 PM
13 points
1 comment5 min readLW link

«Boundaries/​Mem­branes» and AI safety compilation

ChipmonkMay 3, 2023, 9:41 PM
57 points
17 comments8 min readLW link

[Linkpost] MindEye2: Shared-Sub­ject Models En­able fMRI-To-Image With 1 Hour of Data

Bogdan Ionut CirsteaMar 10, 2024, 1:30 AM
10 points
0 comments1 min readLW link
(openreview.net)

[Question] Does the Tele­phone The­o­rem give us a free lunch?

NumendilFeb 15, 2023, 2:13 AM
11 points
2 comments1 min readLW link

Ab­strac­tion As Sym­me­try and Other Thoughts

NumendilFeb 1, 2023, 6:25 AM
28 points
9 comments2 min readLW link

Na­ture < Nur­ture for AIs

scottviteriJun 4, 2023, 8:38 PM
14 points
22 comments7 min readLW link

[Linkpost] Large Lan­guage Models Con­verge on Brain-Like Word Representations

Bogdan Ionut CirsteaJun 11, 2023, 11:20 AM
36 points
12 comments1 min readLW link

[Linkpost] Scal­ing laws for lan­guage en­cod­ing mod­els in fMRI

Bogdan Ionut CirsteaJun 8, 2023, 10:52 AM
30 points
0 comments1 min readLW link

[Linkpost] Map­ping Brains with Lan­guage Models: A Survey

Bogdan Ionut CirsteaJun 16, 2023, 9:49 AM
5 points
0 comments1 min readLW link

[Linkpost] Rosetta Neu­rons: Min­ing the Com­mon Units in a Model Zoo

Bogdan Ionut CirsteaJun 17, 2023, 4:38 PM
12 points
0 comments1 min readLW link

[Linkpost] A shared lin­guis­tic space for trans­mit­ting our thoughts from brain to brain in nat­u­ral conversations

Bogdan Ionut CirsteaJul 1, 2023, 1:57 PM
17 points
2 comments1 min readLW link

[Linkpost] Large lan­guage mod­els con­verge to­ward hu­man-like con­cept organization

Bogdan Ionut CirsteaSep 2, 2023, 6:00 AM
22 points
1 comment1 min readLW link

An em­bed­ding de­coder model, trained with a differ­ent ob­jec­tive on a differ­ent dataset, can de­code an­other model’s em­bed­dings sur­pris­ingly accurately

Logan ZoellnerSep 3, 2023, 11:34 AM
20 points
1 comment1 min readLW link

The util­ity of hu­mans within a Su­per Ar­tifi­cial In­tel­li­gence realm.

Marc MonroyOct 11, 2023, 5:30 PM
1 point
0 comments7 min readLW link

[Linkpost] Gen­er­al­iza­tion in diffu­sion mod­els arises from ge­om­e­try-adap­tive har­monic representation

Bogdan Ionut CirsteaOct 11, 2023, 5:48 PM
4 points
3 comments1 min readLW link

Towards build­ing blocks of ontologies

Feb 8, 2025, 4:03 PM
27 points
0 comments26 min readLW link

Univer­sal di­men­sions of vi­sual representation

Bogdan Ionut CirsteaAug 28, 2024, 10:38 AM
10 points
0 comments1 min readLW link
(arxiv.org)

Ab­strac­tions are not Natural

Alfred HarwoodNov 4, 2024, 11:10 AM
25 points
21 comments11 min readLW link
No comments.