RSS

Definitions

TagLast edit: Jul 31, 2020, 6:48 AM by Yoav Ravid

Posts that attempt to Define or clarify the meaning of a concept, a word, phrase, or something else.

Log­i­cal Foun­da­tions of Govern­ment Policy

FCCCOct 10, 2020, 5:05 PM
2 points
0 comments17 min readLW link

Com­pact vs. Wide Models

VaniverJul 16, 2018, 4:09 AM
31 points
5 comments3 min readLW link

Su­per­po­si­tion is not “just” neu­ron polysemanticity

LawrenceCApr 26, 2024, 11:22 PM
66 points
4 comments13 min readLW link

Broadly hu­man level, cog­ni­tively com­plete AGI

p.b.Aug 6, 2024, 9:26 AM
7 points
0 comments1 min readLW link

What Do We Mean By “Ra­tion­al­ity”?

Eliezer YudkowskyMar 16, 2009, 10:33 PM
389 points
19 comments6 min readLW link

What’s So Bad About Ad-Hoc Math­e­mat­i­cal Defi­ni­tions?

johnswentworthMar 15, 2021, 9:51 PM
201 points
58 comments7 min readLW link

“AI Align­ment” is a Danger­ously Over­loaded Term

RokoDec 15, 2023, 2:34 PM
108 points
100 comments3 min readLW link

What Does “Sig­nal­ling” Mean?

abramdemskiSep 16, 2020, 9:19 PM
38 points
18 comments3 min readLW link

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

Alex_AltairApr 6, 2022, 4:57 AM
21 points
5 comments5 min readLW link

The Prob­lem With The Cur­rent State of AGI Definitions

YitzMay 29, 2022, 1:58 PM
40 points
22 comments8 min readLW link

What is au­ton­omy, and how does it lead to greater risk from AI?

DavidmanheimAug 1, 2023, 7:58 AM
30 points
0 comments6 min readLW link

Be­hav­ioral and mechanis­tic defi­ni­tions (of­ten con­fuse AI al­ign­ment dis­cus­sions)

LawrenceCFeb 20, 2023, 9:33 PM
33 points
5 comments6 min readLW link

Essen­tial Be­hav­iorism Terms

RivkaMar 17, 2023, 5:41 PM
15 points
1 comment10 min readLW link

What is in­stru­men­tal con­ver­gence?

Mar 12, 2025, 8:28 PM
2 points
0 comments2 min readLW link
(aisafety.info)

What are the differ­ences be­tween AGI, trans­for­ma­tive AI, and su­per­in­tel­li­gence?

Jan 23, 2025, 10:03 AM
10 points
3 comments3 min readLW link
(aisafety.info)

What is an al­ign­ment tax?

Mar 20, 2025, 1:06 PM
5 points
0 comments1 min readLW link
(aisafety.info)

What are the “no free lunch” the­o­rems?

Feb 4, 2025, 2:02 AM
19 points
4 comments1 min readLW link
(aisafety.info)

Why There Is No An­swer to Your Philo­soph­i­cal Question

Bryan FrancesMar 24, 2023, 11:22 PM
−12 points
10 comments12 min readLW link

The Use­ful Idea of Truth

Eliezer YudkowskyOct 2, 2012, 6:16 PM
194 points
545 comments14 min readLW link

What Bos­ton Can Teach Us About What a Wo­man Is

ymeskhoutMay 1, 2023, 3:34 PM
18 points
45 comments12 min readLW link

A point of clar­ifi­ca­tion on in­fo­haz­ard terminology

eukaryoteFeb 2, 2020, 5:43 PM
52 points
21 comments2 min readLW link
(eukaryotewritesblog.com)

Per­son­hood is a Reli­gious Belief

jan SijanMay 3, 2023, 4:16 PM
−41 points
28 comments6 min readLW link

Disam­biguat­ing “al­ign­ment” and re­lated no­tions

David Scott Krueger (formerly: capybaralet)Jun 5, 2018, 3:35 PM
22 points
21 comments2 min readLW link

Four kinds of problems

Bird ConceptAug 21, 2018, 11:01 PM
35 points
11 comments3 min readLW link

Note on Ter­minol­ogy: “Ra­tion­al­ity”, not “Ra­tion­al­ism”

Vladimir_NesovJan 14, 2011, 9:21 PM
40 points
51 comments1 min readLW link

An Agent is a Wor­ldline in Teg­mark V

komponistoJul 12, 2018, 5:12 AM
24 points
12 comments2 min readLW link

Flow­sheet Logic and Note­card Logic

moridinamaelSep 9, 2015, 4:42 PM
46 points
28 comments3 min readLW link

In fa­vor of taboo­ing the word “val­ues” and us­ing only “pri­ori­ties” instead

chaosmageOct 25, 2018, 10:28 PM
21 points
11 comments2 min readLW link

Defi­ni­tions are about effi­ciency and con­sis­tency with com­mon lan­guage.

Nacruno96Jul 10, 2023, 11:46 PM
1 point
0 comments4 min readLW link

Spaghetti Towers

eukaryoteDec 22, 2018, 5:29 AM
212 points
38 comments3 min readLW link1 review
(eukaryotewritesblog.com)

Tech­ni­cal model re­fine­ment formalism

Stuart_ArmstrongAug 27, 2020, 11:54 AM
19 points
0 comments6 min readLW link

Define Rationality

MarshallMar 5, 2009, 6:25 PM
1 point
14 comments1 min readLW link

Seek­ing bet­ter name for “Effec­tive Ego­ism”

DataPacRatNov 25, 2016, 10:31 PM
14 points
31 comments1 min readLW link

[Question] What Belongs in my Glos­sary?

ZviNov 2, 2020, 7:52 PM
14 points
8 comments1 min readLW link

Begin­ning at the Beginning

AnnoyanceMar 11, 2009, 7:23 PM
5 points
60 comments4 min readLW link

What’s in a name? That which we call a ra­tio­nal­ist…

badgerApr 24, 2009, 11:53 PM
8 points
92 comments1 min readLW link

Ra­tion­al­ity is win­ning—or is it?

tawMay 7, 2009, 2:51 PM
−8 points
10 comments1 min readLW link

My con­cerns about the term ‘ra­tio­nal­ist’

JamesColeJun 4, 2009, 3:31 PM
12 points
34 comments2 min readLW link

The two mean­ings of math­e­mat­i­cal terms

JamesColeJun 15, 2009, 2:30 PM
0 points
80 comments3 min readLW link

ESR’s com­ments on some EY:OB/​LW posts

Eliezer YudkowskyJun 20, 2009, 12:16 AM
7 points
16 comments1 min readLW link

Ra­tion­al­ists, Post-Ra­tion­al­ists, And Ra­tion­al­ist-Adjacents

orthonormalMar 13, 2020, 8:25 PM
80 points
43 comments3 min readLW link

Geno­cide isn’t Decolonization

robotelvisOct 20, 2023, 4:14 AM
33 points
19 comments5 min readLW link
(messyprogress.substack.com)

Ra­tion­al­ity Is Ex­per­tise With Reality

Horatio Von BeckerSep 2, 2021, 8:45 PM
−14 points
15 comments1 min readLW link

Sen­tience, Sapi­ence, Con­scious­ness & Self-Aware­ness: Defin­ing Com­plex Terms

LukeOnlineOct 20, 2021, 1:48 PM
10 points
8 comments4 min readLW link

Disen­tan­gling in­ner al­ign­ment failures

Erik JennerOct 10, 2022, 6:50 PM
23 points
5 comments4 min readLW link

Glos­sary of Futurology

mind_bomberAug 21, 2015, 5:51 AM
3 points
7 comments13 min readLW link

[Question] For­mal “left” and “right” definitions

Roman NastenkoMar 30, 2024, 11:42 PM
1 point
1 comment1 min readLW link

[Question] What are some posthu­man­ist/​more-than-hu­man ap­proaches to defi­ni­tions of in­tel­li­gence and agency? Par­tic­u­larly in ap­pli­ca­tion to AI re­search.

Eli HitonApr 9, 2024, 9:52 PM
1 point
0 comments1 min readLW link

ChatGPT defines 10 con­crete terms: gener­i­cally, for 5- and 11-year-olds, and for a sci­en­tist

Bill BenzonApr 11, 2024, 8:27 PM
3 points
9 comments6 min readLW link

“Open Source AI” is a lie, but it doesn’t have to be

jacobhaimesApr 30, 2024, 11:10 PM
18 points
5 comments6 min readLW link
(jacob-haimes.github.io)

Let’s Talk About Emergence

jacobhaimesJun 7, 2024, 7:18 PM
4 points
0 comments7 min readLW link
(www.odysseaninstitute.org)

Re­la­tion­ships among words, met­al­in­gual defi­ni­tion, and interpretability

Bill BenzonJun 7, 2024, 7:18 PM
2 points
0 comments5 min readLW link

What is space? What is time?

TahpJun 7, 2024, 10:15 PM
8 points
3 comments7 min readLW link

Com­mon Uses of “Ac­cep­tance”

Yi-YangJul 26, 2024, 11:18 AM
9 points
5 comments24 min readLW link

What is com­pute gov­er­nance?

Dec 23, 2024, 6:32 AM
6 points
0 comments2 min readLW link
(aisafety.info)

Clar­ify­ing Align­ment Fun­da­men­tals Through the Lens of Ontology

eternal/ephemeraOct 7, 2024, 8:57 PM
12 points
4 comments24 min readLW link

Ac­tive Re­call and Spaced Rep­e­ti­tion are Differ­ent Things

Saul MunnNov 8, 2024, 8:14 PM
48 points
2 comments3 min readLW link
(www.brasstacks.blog)

What are poly­se­man­tic neu­rons?

Jan 8, 2025, 7:35 AM
8 points
0 comments4 min readLW link
(aisafety.info)
No comments.