Could Ad­vanced AI Drive Ex­plo­sive Eco­nomic Growth?

Matthew Barnett30 Jun 2021 22:17 UTC
15 points
4 comments2 min readLW link
(www.openphilanthropy.org)

Thoughts on safety in pre­dic­tive learning

Steven Byrnes30 Jun 2021 19:17 UTC
19 points
17 comments19 min readLW link

Mus­ings on gen­eral sys­tems alignment

Alex Flint30 Jun 2021 18:16 UTC
31 points
11 comments3 min readLW link

[AN #154]: What eco­nomic growth the­ory has to say about trans­for­ma­tive AI

Rohin Shah30 Jun 2021 17:20 UTC
12 points
0 comments9 min readLW link
(mailchi.mp)

Progress on Causal In­fluence Diagrams

tom4everitt30 Jun 2021 15:34 UTC
73 points
6 comments9 min readLW link

Si­mu­lacrum Levels of Trust

alkexr30 Jun 2021 10:14 UTC
21 points
1 comment3 min readLW link

[Question] Is it true that most stud­ies in Kah­ne­man’s ‘Think­ing fast and slow’ are not repli­ca­ble and the book is largely not sup­ported by ev­i­dence?

Davy Jones30 Jun 2021 7:14 UTC
17 points
13 comments1 min readLW link

Do in­co­her­ent en­tities have stronger rea­son to be­come more co­her­ent than less?

KatjaGrace30 Jun 2021 5:50 UTC
46 points
5 comments4 min readLW link
(worldspiritsockpuppet.com)

[Question] How do the iver­mectin meta-re­views come to so differ­ent con­clu­sions?

ChristianKl29 Jun 2021 22:34 UTC
39 points
24 comments1 min readLW link

D&D.Sci(-Fi) June 2021 Eval­u­a­tion and Ruleset

abstractapplic29 Jun 2021 21:02 UTC
30 points
5 comments3 min readLW link

Search by abstraction

p.b.29 Jun 2021 20:56 UTC
5 points
0 comments1 min readLW link

Why did we wait so long for the thresh­ing ma­chine?

jasoncrawford29 Jun 2021 19:55 UTC
104 points
20 comments12 min readLW link1 review
(rootsofprogress.org)

[Question] Is there a “co­her­ent de­ci­sions im­ply con­sis­tent util­ities”-style ar­gu­ment for non-lex­i­co­graphic prefer­ences?

Tetraspace29 Jun 2021 19:14 UTC
4 points
20 comments1 min readLW link

Try­ing to ap­prox­i­mate Statis­ti­cal Models as Scor­ing Tables

Jsevillamol29 Jun 2021 17:20 UTC
18 points
2 comments9 min readLW link

[Question] How will OpenAI + GitHub’s Copi­lot af­fect pro­gram­ming?

smountjoy29 Jun 2021 16:42 UTC
55 points
24 comments1 min readLW link

Opinionated Uncertainty

DirectedEvolution29 Jun 2021 0:11 UTC
10 points
1 comment11 min readLW link

In­tro to Debt Crises

Connor_Flexman28 Jun 2021 23:50 UTC
59 points
5 comments10 min readLW link

A quan­ti­ta­tive in­tro­duc­tion to churning

electroswing28 Jun 2021 22:21 UTC
19 points
4 comments9 min readLW link

[Question] How much in­ter­est would there be in a fringe the­o­ries wiki?

Matthew Barnett28 Jun 2021 21:03 UTC
14 points
19 comments1 min readLW link

How teams went about their re­search at AI Safety Camp edi­tion 5

Remmelt28 Jun 2021 15:15 UTC
24 points
0 comments6 min readLW link

Epony­mous Laws Part 2: Laws of Pro­gram­ming and Soft­ware Development

rogersbacon28 Jun 2021 12:46 UTC
3 points
3 comments1 min readLW link

Voic­ing Voice

Willa28 Jun 2021 4:29 UTC
6 points
16 comments4 min readLW link

Op­ti­mism about So­cial Technology

mike_hawke27 Jun 2021 23:35 UTC
23 points
7 comments1 min readLW link

In­ten­tion­ally Mak­ing Close Friends

Neel Nanda27 Jun 2021 23:06 UTC
280 points
35 comments18 min readLW link1 review
(www.neelnanda.io)

Brute force search­ing for alignment

Donald Hobson27 Jun 2021 21:54 UTC
23 points
3 comments2 min readLW link

[Question] What pre­cau­tions should fully-vac­ci­nated peo­ple still be tak­ing?

Sameerishere27 Jun 2021 19:10 UTC
32 points
48 comments9 min readLW link

[Question] What are some claims or opinions about multi-multi del­e­ga­tion you’ve seen in the meme­plex that you think de­serve scrutiny?

Quinn27 Jun 2021 17:44 UTC
17 points
6 comments2 min readLW link

Finite Fac­tored Sets: LW tran­script with run­ning commentary

27 Jun 2021 16:02 UTC
30 points
0 comments51 min readLW link

Nu­clear Strat­egy in a Semi-Vuln­er­a­ble World

Jackson Wagner27 Jun 2021 8:17 UTC
7 points
1 comment17 min readLW link

The Un­ex­pected Hang­ing Paradox

Chris_Leong27 Jun 2021 6:17 UTC
17 points
11 comments4 min readLW link

Sam Alt­man and Ezra Klein on the AI Revolution

Zack_M_Davis27 Jun 2021 4:53 UTC
38 points
17 comments1 min readLW link
(www.nytimes.com)

The Lan­guage of Bird

johnswentworth27 Jun 2021 4:44 UTC
45 points
9 comments2 min readLW link

Deep limi­ta­tions? Ex­am­in­ing ex­pert dis­agree­ment over deep learning

Richard_Ngo27 Jun 2021 0:55 UTC
18 points
6 comments1 min readLW link
(link.springer.com)

[Question] What will be the af­ter­math of the US in­tel­li­gence lab leak re­port?

ChristianKl26 Jun 2021 20:33 UTC
20 points
33 comments1 min readLW link

[AN #153]: Ex­per­i­ments that demon­strate failures of ob­jec­tive robustness

Rohin Shah26 Jun 2021 17:10 UTC
25 points
1 comment8 min readLW link
(mailchi.mp)

Im­prov­ing par­li­a­men­tary in­for­ma­tion processing

victorsintnicolaas26 Jun 2021 16:11 UTC
2 points
0 comments4 min readLW link

Cliffnotes to Craft of Re­search parts I, II, and III

Quinn26 Jun 2021 14:00 UTC
7 points
1 comment17 min readLW link

Why you should try a live read­ing session

Nihal M26 Jun 2021 8:30 UTC
13 points
2 comments4 min readLW link

An­throp­ics and Embed­ded Agency

dadadarren26 Jun 2021 1:45 UTC
7 points
2 comments2 min readLW link

In­ter­nal In­for­ma­tion Cascades

JenniferRM25 Jun 2021 16:35 UTC
45 points
8 comments10 min readLW link

An­nounc­ing the Re­plac­ing Guilt audiobook

gianlucatruda25 Jun 2021 13:38 UTC
65 points
1 comment1 min readLW link

I Will Or­ga­nize Mee­tups in Norfolk, Virginia [Hamp­ton Roads Metro Area]

Willa25 Jun 2021 2:41 UTC
12 points
4 comments1 min readLW link

A Some­what Ra­tion­al­ist Baptism

ZorbaTHut25 Jun 2021 0:39 UTC
12 points
0 comments2 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

[Question] How do the side effects of No­vavax com­pare to other COVID-19 vac­cines?

ChristianKl24 Jun 2021 16:36 UTC
14 points
7 comments1 min readLW link

War on Cancer II

ChristianKl24 Jun 2021 14:59 UTC
36 points
12 comments14 min readLW link

Covid 6/​24: The Span­ish Prisoner

Zvi24 Jun 2021 14:40 UTC
43 points
30 comments9 min readLW link
(thezvi.wordpress.com)

[Question] ELI12: how do liber­tar­i­ans want wages to work?

TekhneMakre24 Jun 2021 7:00 UTC
3 points
57 comments2 min readLW link

Two non-ob­vi­ous les­sons from micro­covid.org

catherio24 Jun 2021 2:35 UTC
195 points
4 comments1 min readLW link

Dis­cus­sion: Ob­jec­tive Ro­bust­ness and In­ner Align­ment Terminology

23 Jun 2021 23:25 UTC
73 points
7 comments9 min readLW link