7 traps that (we think) new al­ign­ment re­searchers of­ten fall into

Sep 27, 2022, 11:13 PM
176 points
10 comments4 min readLW link

Failure modes in a shard the­ory al­ign­ment plan

Thomas KwaSep 27, 2022, 10:34 PM
26 points
2 comments7 min readLW link

[Question] Is a PhD nec­es­sary to con­tribute mean­ingfully to a field?

TrudosKudosSep 27, 2022, 9:27 PM
4 points
7 comments1 min readLW link

Why we’re not found­ing a hu­man-data-for-al­ign­ment org

Sep 27, 2022, 8:14 PM
88 points
6 comments29 min readLW link
(forum.effectivealtruism.org)

A Poorly Planned Loft Bed

jefftkSep 27, 2022, 5:50 PM
9 points
2 comments1 min readLW link
(www.jefftk.com)

Wise Crowd & Demo­cratic Spirit

Hristo ZaykovSep 27, 2022, 5:45 PM
1 point
0 comments2 min readLW link
(www.hristo.blog)

Soft skills for meetups

mingyuanSep 27, 2022, 5:26 PM
49 points
3 comments5 min readLW link

[Question] En­rich­ing Youtube con­tent recommendations

Martín SotoSep 27, 2022, 4:54 PM
8 points
4 comments1 min readLW link

The Onion Test for Per­sonal and In­sti­tu­tional Honesty

Sep 27, 2022, 3:26 PM
163 points
31 comments3 min readLW link3 reviews

Book re­view: “The Heart of the Brain: The Hy­potha­la­mus and Its Hor­mones”

Steven ByrnesSep 27, 2022, 1:20 PM
65 points
3 comments18 min readLW link

My Thoughts on the ML Safety Course

zeshenSep 27, 2022, 1:15 PM
50 points
3 comments17 min readLW link

Sum­mary of ML Safety Course

zeshenSep 27, 2022, 1:05 PM
7 points
0 comments6 min readLW link

Prob­a­bil­is­tic rea­son­ing for de­scrip­tion and experience

Q HomeSep 27, 2022, 10:57 AM
0 points
0 comments26 min readLW link

A Prince, a Pau­per, Power, Panama

Alok SinghSep 27, 2022, 7:10 AM
10 points
0 comments1 min readLW link
(alok.github.io)

Dou­ble As­teroid Redi­rec­tion Test succeeds

sanxiynSep 27, 2022, 6:37 AM
19 points
5 comments1 min readLW link
(twitter.com)

[Question] How would I know if a PhD is the right ca­reer path?

Bob GuranSep 27, 2022, 5:49 AM
4 points
4 comments1 min readLW link

Re­view of Ex­am­ine.com’s vi­tamin write-ups

Sep 26, 2022, 11:40 PM
60 points
1 comment5 min readLW link
(acesounderglass.com)

D&D.Sci Septem­ber 2022 Eval­u­a­tion and Ruleset

abstractapplicSep 26, 2022, 10:19 PM
30 points
5 comments3 min readLW link

[MLSN #5]: Prize Compilation

Dan HSep 26, 2022, 9:55 PM
15 points
1 comment2 min readLW link

Loss of Align­ment is not the High-Order Bit for AI Risk

yieldthoughtSep 26, 2022, 9:16 PM
14 points
18 comments2 min readLW link

In­verse Scal­ing Prize: Round 1 Winners

Sep 26, 2022, 7:57 PM
93 points
16 comments4 min readLW link
(irmckenzie.co.uk)

[Question] Does the ex­is­tence of shared hu­man val­ues im­ply al­ign­ment is “easy”?

MorpheusSep 26, 2022, 6:01 PM
7 points
15 comments1 min readLW link

Meetup: Madi­son, WI (Oct 8)

svfritzSep 26, 2022, 5:55 PM
1 point
0 comments1 min readLW link

Am­bi­guity in Pre­dic­tion Mar­ket Re­s­olu­tion is Harmful

aphyerSep 26, 2022, 4:22 PM
69 points
17 comments5 min readLW link

Framery Phone Booth CO2 Accumulation

jefftkSep 26, 2022, 4:10 PM
25 points
0 comments1 min readLW link
(www.jefftk.com)

[Question] How can I re­move the launch but­ton from my LW home page?

sudoSep 26, 2022, 3:15 PM
8 points
4 comments1 min readLW link

Brief Notes on Transformers

Adam JermynSep 26, 2022, 2:46 PM
48 points
3 comments2 min readLW link

You are Un­der­es­ti­mat­ing The Like­li­hood That Con­ver­gent In­stru­men­tal Sub­goals Lead to Aligned AGI

Mark NeyerSep 26, 2022, 2:22 PM
3 points
6 comments3 min readLW link

Cli­mate-con­tin­gent Fi­nance, and A Gen­er­al­ized Mechanism for X-Risk Re­duc­tion Financing

John NaySep 26, 2022, 1:23 PM
0 points
2 commentsLW link

Self-Con­trol Se­crets of the Pu­ri­tan Masters

David Hugh-JonesSep 26, 2022, 9:04 AM
67 points
3 comments5 min readLW link
(wyclif.substack.com)

How I buy things when Light­cone wants them fast

Bird ConceptSep 26, 2022, 5:02 AM
224 points
21 comments8 min readLW link

Oren’s Field Guide of Bad AGI Outcomes

Eris DiscordiaSep 26, 2022, 4:06 AM
0 points
0 comments1 min readLW link

On Generality

Eris DiscordiaSep 26, 2022, 4:06 AM
2 points
0 comments5 min readLW link

Plan­ning ca­pac­ity and daemons

lemonhopeSep 26, 2022, 12:15 AM
2 points
0 comments5 min readLW link

Plan­ning a Loft Bed

jefftkSep 26, 2022, 12:10 AM
15 points
15 comments2 min readLW link
(www.jefftk.com)

Be­com­ing Black Boxish

vitaliyaSep 25, 2022, 11:35 PM
16 points
0 comments2 min readLW link

An­nounc­ing Balsa Research

ZviSep 25, 2022, 10:50 PM
235 points
64 comments2 min readLW link1 review
(thezvi.wordpress.com)

[Question] How to learn: Strug­gle VS Lookup-Table?

Nicholas / Heather KrossSep 25, 2022, 9:58 PM
15 points
2 comments2 min readLW link

An Un­ex­pected GPT-3 De­ci­sion in a Sim­ple Gam­ble

casualphysicsenjoyerSep 25, 2022, 4:46 PM
8 points
4 comments1 min readLW link

“Agency” needs nuance

Evie CottrellSep 25, 2022, 7:40 AM
23 points
1 comment14 min readLW link

Ac­cep­tance and Com­mit­ment Ther­apy (ACT) 101

Evie CottrellSep 25, 2022, 7:25 AM
7 points
2 comments8 min readLW link

Bath­room Con­struc­tion Cost Comparison

jefftkSep 25, 2022, 2:30 AM
11 points
0 comments2 min readLW link
(www.jefftk.com)

Pri­ori­tiz­ing the Arts in re­sponse to AI automation

CaseySep 25, 2022, 2:25 AM
18 points
11 comments2 min readLW link

UI/​UX From the Dark Ages

ShmiSep 25, 2022, 1:53 AM
25 points
15 comments2 min readLW link

P(mis­al­ign­ment x-risk|AGI) is small #[Fu­ture Fund wor­ld­view prize]

Dibbu DibbuSep 24, 2022, 11:54 PM
−18 points
0 comments4 min readLW link

[Question] Papers to start get­ting into NLP-fo­cused al­ign­ment research

FeraidoonSep 24, 2022, 11:53 PM
6 points
0 comments1 min readLW link

Whose Fault?

MarkoviaSep 24, 2022, 11:53 PM
1 point
0 commentsLW link

Brain-over-body bi­ases, and the em­bod­ied value prob­lem in AI alignment

geoffreymillerSep 24, 2022, 10:24 PM
10 points
6 comments25 min readLW link

Opt out from the Funni

CoafosSep 24, 2022, 10:07 PM
8 points
1 comment2 min readLW link

AI coöper­a­tion is more pos­si­ble than you think

423175Sep 24, 2022, 9:26 PM
7 points
0 comments2 min readLW link