RSS

Abstraction

TagLast edit: 16 Aug 2020 16:40 UTC by adamShimi

An abstraction is a high-level concept that groups things together while not considering some of their differences.

(This is a stub, please rewrite if you have a better tag description).

[Question] What is ab­strac­tion?

Adam Zerner15 Dec 2018 8:36 UTC
25 points
11 comments4 min readLW link

What is Ab­strac­tion?

johnswentworth6 Dec 2019 20:30 UTC
35 points
8 comments5 min readLW link

Ab­strac­tion = In­for­ma­tion at a Distance

johnswentworth19 Mar 2020 0:19 UTC
28 points
1 comment3 min readLW link

Un­der­con­strained Abstractions

Eliezer Yudkowsky4 Dec 2008 13:58 UTC
11 points
27 comments5 min readLW link

Whence Your Ab­strac­tions?

Eliezer Yudkowsky20 Nov 2008 1:07 UTC
12 points
6 comments3 min readLW link

Ab­strac­tion, Causal­ity, and Embed­ded Maps: Here Be Monsters

johnswentworth18 Dec 2019 20:25 UTC
26 points
1 comment4 min readLW link

Causal Ab­strac­tion Intro

johnswentworth19 Dec 2019 22:01 UTC
24 points
6 comments1 min readLW link

Defi­ni­tions of Causal Ab­strac­tion: Re­view­ing Beck­ers & Halpern

johnswentworth7 Jan 2020 0:03 UTC
30 points
4 comments4 min readLW link

How to Throw Away In­for­ma­tion in Causal DAGs

johnswentworth8 Jan 2020 2:40 UTC
20 points
2 comments2 min readLW link

Ex­am­ple: Markov Chain

johnswentworth10 Jan 2020 20:19 UTC
15 points
1 comment4 min readLW link

Log­i­cal Rep­re­sen­ta­tion of Causal Models

johnswentworth21 Jan 2020 20:04 UTC
37 points
0 comments3 min readLW link

(A → B) → A in Causal DAGs

johnswentworth22 Jan 2020 18:22 UTC
48 points
11 comments2 min readLW link

For­mu­lat­ing Re­duc­tive Agency in Causal Models

johnswentworth23 Jan 2020 17:03 UTC
33 points
0 comments2 min readLW link

Trace README

johnswentworth11 Mar 2020 21:08 UTC
35 points
1 comment8 min readLW link

Me­di­a­tion From a Distance

johnswentworth20 Mar 2020 22:02 UTC
16 points
0 comments2 min readLW link

Noise Simplifies

johnswentworth15 Apr 2020 19:48 UTC
28 points
3 comments2 min readLW link

In­te­grat­ing Hid­den Vari­ables Im­proves Approximation

johnswentworth16 Apr 2020 21:43 UTC
15 points
4 comments1 min readLW link

In­tu­itions on Univer­sal Be­hav­ior of In­for­ma­tion at a Distance

johnswentworth20 Apr 2020 21:44 UTC
21 points
3 comments8 min readLW link

Mo­ti­vat­ing Ab­strac­tion-First De­ci­sion Theory

johnswentworth29 Apr 2020 17:47 UTC
42 points
16 comments5 min readLW link

Writ­ing Causal Models Like We Write Programs

johnswentworth5 May 2020 18:05 UTC
87 points
10 comments4 min readLW link

Point­ing to a Flower

johnswentworth18 May 2020 18:54 UTC
61 points
18 comments9 min readLW link

Public Static: What is Ab­strac­tion?

johnswentworth9 Jun 2020 18:36 UTC
95 points
18 comments12 min readLW link

Carte­sian Boundary as Ab­strac­tion Boundary

johnswentworth11 Jun 2020 17:38 UTC
35 points
3 comments5 min readLW link

Causal­ity Adds Up to Normality

johnswentworth15 Jun 2020 17:19 UTC
13 points
2 comments4 min readLW link

The In­dex­ing Problem

johnswentworth22 Jun 2020 19:11 UTC
36 points
2 comments4 min readLW link

Ab­strac­tion, Evolu­tion and Gears

johnswentworth24 Jun 2020 17:39 UTC
29 points
11 comments4 min readLW link

Trace: Goals and Principles

johnswentworth28 Feb 2020 23:50 UTC
14 points
3 comments8 min readLW link

Align­ment By Default

johnswentworth12 Aug 2020 18:54 UTC
173 points
94 comments11 min readLW link2 reviews

[Question] Prob­lems In­volv­ing Ab­strac­tion?

johnswentworth20 Oct 2020 16:49 UTC
30 points
12 comments1 min readLW link

Causal Ab­strac­tion Toy Model: Med­i­cal Sensor

johnswentworth11 Dec 2019 21:12 UTC
34 points
6 comments5 min readLW link

Ex­am­ples of Causal Abstraction

johnswentworth12 Dec 2019 22:54 UTC
24 points
7 comments4 min readLW link

Finite Fac­tored Sets

Scott Garrabrant23 May 2021 20:52 UTC
146 points
95 comments24 min readLW link1 review

The Flex­i­bil­ity of Ab­stract Concepts

lsusr2 Mar 2021 6:43 UTC
44 points
8 comments5 min readLW link

Distributed Decisions

johnswentworth29 May 2022 2:43 UTC
66 points
6 comments6 min readLW link

Re­duc­ing Agents: When ab­strac­tions break

Hazard31 Mar 2018 0:03 UTC
13 points
10 comments8 min readLW link

Neu­ral net­works as non-leaky math­e­mat­i­cal abstraction

George3d619 Dec 2019 12:23 UTC
14 points
11 comments8 min readLW link
(blog.cerebralab.com)

Ab­strac­tion is Big­ger than Nat­u­ral Abstraction

NicholasKross31 May 2023 0:00 UTC
18 points
0 comments5 min readLW link
(www.thinkingmuchbetter.com)

See­ing the Ma­trix, Switch­ing Ab­strac­tions, and Miss­ing Moods

Raemon4 Jun 2019 21:08 UTC
35 points
3 comments4 min readLW link

how 2 tell if ur in­put is out of dis­tri­bu­tion given only model weights

dkirmani5 Aug 2023 22:45 UTC
47 points
10 comments1 min readLW link

Func­tors and Coarse Worlds

Scott Garrabrant30 Oct 2020 15:19 UTC
52 points
3 comments8 min readLW link

Chaos In­duces Abstractions

johnswentworth18 Mar 2021 20:08 UTC
95 points
13 comments7 min readLW link

Sav­ing Time

Scott Garrabrant18 May 2021 20:11 UTC
151 points
20 comments4 min readLW link1 review

Finite Fac­tored Sets: In­tro­duc­tion and Factorizations

Scott Garrabrant4 Jun 2021 17:41 UTC
34 points
2 comments10 min readLW link

AXRP Epi­sode 9 - Finite Fac­tored Sets with Scott Garrabrant

DanielFilan24 Jun 2021 22:10 UTC
59 points
2 comments59 min readLW link

Finite Fac­tored Sets: Con­di­tional Orthogonality

Scott Garrabrant9 Jul 2021 6:01 UTC
27 points
2 comments7 min readLW link

Test­ing The Nat­u­ral Ab­strac­tion Hy­poth­e­sis: Pro­ject Update

johnswentworth20 Sep 2021 3:44 UTC
87 points
17 comments8 min readLW link1 review

What Does The Nat­u­ral Ab­strac­tion Frame­work Say About ELK?

johnswentworth15 Feb 2022 2:27 UTC
35 points
0 comments6 min readLW link

When to use “meta” vs “self-refer­ence”, “re­cur­sive”, etc.

Alex_Altair6 Apr 2022 4:57 UTC
20 points
5 comments5 min readLW link

AXRP Epi­sode 15 - Nat­u­ral Ab­strac­tions with John Wentworth

DanielFilan23 May 2022 5:40 UTC
34 points
1 comment58 min readLW link

Nat­u­ral La­tents: The Math

27 Dec 2023 19:03 UTC
114 points
31 comments14 min readLW link

As­sorted thoughts about ab­strac­tion

Adam Zerner5 Jul 2022 6:40 UTC
16 points
9 comments7 min readLW link

What Makes an Idea Un­der­stand­able? On Ar­chi­tec­turally and Cul­turally Nat­u­ral Ideas.

16 Aug 2022 2:09 UTC
21 points
2 comments16 min readLW link

Sapir-Whorf for Rationalists

[DEACTIVATED] Duncan Sabien25 Jan 2023 7:58 UTC
147 points
48 comments19 min readLW link

Re­marks 1–18 on GPT (com­pressed)

Cleo Nardo20 Mar 2023 22:27 UTC
146 points
34 comments31 min readLW link

Good on­tolo­gies in­duce com­mu­ta­tive diagrams

Erik Jenner9 Oct 2022 0:06 UTC
49 points
5 comments14 min readLW link

Do we have the right kind of math for roles, goals and mean­ing?

mrcbarbier22 Oct 2022 21:28 UTC
13 points
5 comments7 min readLW link

Trade­offs in com­plex­ity, ab­strac­tion, and generality

12 Dec 2022 15:55 UTC
32 points
0 comments2 min readLW link

The Nat­u­ral Ab­strac­tion Hy­poth­e­sis: Im­pli­ca­tions and Evidence

CallumMcDougall14 Dec 2021 23:14 UTC
37 points
8 comments19 min readLW link

No Ab­strac­tion Without a Goal

dkirmani10 Jan 2022 20:24 UTC
27 points
27 comments1 min readLW link

Ab­stract con­cepts and met­al­in­gual defi­ni­tion: Does ChatGPT un­der­stand jus­tice and char­ity?

Bill Benzon16 Dec 2022 21:01 UTC
2 points
0 comments13 min readLW link

To Be Par­tic­u­lar About Morality

AGO31 Dec 2022 19:58 UTC
6 points
2 comments7 min readLW link

Agency As a Nat­u­ral Abstraction

Thane Ruthenis13 May 2022 18:02 UTC
55 points
9 comments13 min readLW link

A Thor­ough In­tro­duc­tion to Abstraction

RohanS13 Jan 2023 0:30 UTC
9 points
1 comment18 min readLW link

Ab­strac­tions as mor­phisms be­tween (co)algebras

Erik Jenner14 Jan 2023 1:51 UTC
17 points
1 comment8 min readLW link

Towards Gears-Level Un­der­stand­ing of Agency

Thane Ruthenis16 Jun 2022 22:00 UTC
23 points
4 comments18 min readLW link

Break­ing Down Goal-Directed Behaviour

Oliver Sourbut16 Jun 2022 18:45 UTC
11 points
1 comment2 min readLW link

Ab­strac­tions as Re­dun­dant Information

johnswentworth13 Feb 2022 4:17 UTC
64 points
9 comments14 min readLW link

De­liber­a­tion, Re­ac­tions, and Con­trol: Ten­ta­tive Defi­ni­tions and a Res­tate­ment of In­stru­men­tal Convergence

Oliver Sourbut27 Jun 2022 17:25 UTC
11 points
0 comments11 min readLW link

One way to ma­nipu­late your level of ab­strac­tion re­lated to a task

Andy_McKenzie19 Aug 2013 5:47 UTC
36 points
5 comments1 min readLW link

Analog­i­cal Rea­son­ing and Creativity

jacob_cannell1 Jul 2015 20:38 UTC
38 points
15 comments14 min readLW link

[Question] Why would code/​English or low-ab­strac­tion/​high-ab­strac­tion sim­plic­ity or brevity cor­re­spond?

curi4 Sep 2020 19:46 UTC
2 points
15 comments1 min readLW link

A re­for­mu­la­tion of Finite Fac­tored Sets

Matthias G. Mayer24 Jul 2023 13:02 UTC
74 points
1 comment8 min readLW link

Iden­ti­fi­ca­tion of Nat­u­ral Modularity

Stephen Fowler25 Jun 2022 15:05 UTC
15 points
3 comments7 min readLW link

Schematic Think­ing: heuris­tic gen­er­al­iza­tion us­ing Korzyb­ski’s method

romeostevensit14 Oct 2019 19:29 UTC
27 points
7 comments3 min readLW link

Epistemic Mo­tif of Ab­stract-Con­crete Cy­cles & Do­main Expansion

Dalcy10 Oct 2023 3:28 UTC
23 points
2 comments3 min readLW link

State, Art, Identity

musq25 Jan 2021 20:22 UTC
1 point
0 comments2 min readLW link

A com­par­i­son of causal scrub­bing, causal ab­strac­tions, and re­lated methods

8 Jun 2023 23:40 UTC
72 points
3 comments22 min readLW link

The Prag­mas­cope Idea

johnswentworth4 Aug 2022 21:52 UTC
58 points
19 comments3 min readLW link

Embed­ded Agency via Abstraction

johnswentworth26 Aug 2019 23:03 UTC
40 points
20 comments11 min readLW link

[Question] What is an agent in re­duc­tion­ist ma­te­ri­al­ism?

Valentine13 Aug 2022 15:39 UTC
7 points
15 comments1 min readLW link

Ab­strac­tions and translation

Amir Bolous20 May 2021 2:45 UTC
5 points
1 comment2 min readLW link

The Fun­da­men­tal The­o­rem for mea­surable fac­tor spaces

Matthias G. Mayer12 Nov 2023 19:25 UTC
38 points
2 comments2 min readLW link

Re­search agenda: For­mal­iz­ing ab­strac­tions of computations

Erik Jenner2 Feb 2023 4:29 UTC
91 points
10 comments31 min readLW link
No comments.