Re­search Notes: What are we al­ign­ing for?

Shoshannah TekofskyJul 8, 2022, 10:13 PM
19 points
8 comments2 min readLW link

[Question] What New Desk­top Should I Buy?

ZviJul 8, 2022, 3:04 PM
15 points
19 comments1 min readLW link

Be­ing a donor for Fe­cal Micro­biota Trans­plants (FMT): Do good & earn easy money (up to 180k/​y)

EternallyBlissfulJul 8, 2022, 6:17 AM
36 points
26 comments8 min readLW link
(forum.effectivealtruism.org)

User re­search as a barom­e­ter of soft­ware design

Adam ZernerJul 8, 2022, 6:02 AM
31 points
13 comments3 min readLW link

Re­in­force­ment Learner Wireheading

Nate ShowellJul 8, 2022, 5:32 AM
8 points
2 comments3 min readLW link

Ex­po­si­tion as sci­ence: some ideas for how to make progress

riceissaJul 8, 2022, 1:29 AM
21 points
1 comment8 min readLW link

In Search of Strate­gic Clarity

james.lucassenJul 8, 2022, 12:52 AM
11 points
1 comment5 min readLW link
(jlucassen.com)

Un­bounded In­tel­li­gence Lottery

kmanJul 7, 2022, 11:28 PM
4 points
11 comments1 min readLW link

How to Be­come a World His­tor­i­cal Figure (Péladan’s Dream)

rogersbaconJul 7, 2022, 10:39 PM
21 points
3 comments30 min readLW link
(www.secretorum.life)

Safety con­sid­er­a­tions for on­line gen­er­a­tive modeling

Sam MarksJul 7, 2022, 6:31 PM
42 points
9 comments14 min readLW link

Hu­man val­ues & bi­ases are in­ac­cessible to the genome

TurnTroutJul 7, 2022, 5:29 PM
94 points
54 comments6 min readLW link1 review

Co­op­er­a­tion with and be­tween AGI\’s

PeterMcCluskeyJul 7, 2022, 4:45 PM
10 points
3 comments10 min readLW link
(www.bayesianinvestor.com)

Aver­sion Factoring

CFAR!DuncanJul 7, 2022, 4:09 PM
79 points
1 comment8 min readLW link

Gen­ders Discrimination

Jacob FalkovichJul 7, 2022, 3:20 PM
10 points
16 comments4 min readLW link

Con­sider Multiclassing

JustisMillsJul 7, 2022, 2:54 PM
17 points
1 comment3 min readLW link

Covid 7/​7/​22: Paxlovid at the Pharmacy

ZviJul 7, 2022, 2:30 PM
34 points
11 comments12 min readLW link
(thezvi.wordpress.com)

Babysit­ting as Par­ent­ing Trial?

jefftkJul 7, 2022, 1:20 PM
46 points
19 comments3 min readLW link
(www.jefftk.com)

When Giv­ing Peo­ple Money Doesn’t Help

ZviJul 7, 2022, 1:00 PM
58 points
12 comments10 min readLW link
(thezvi.wordpress.com)

Wealth as a source of tech­nolog­i­cal stag­na­tion?

alyssavanceJul 7, 2022, 5:46 AM
21 points
1 comment3 min readLW link

Race Along Rashomon Ridge

Jul 7, 2022, 3:20 AM
50 points
15 comments8 min readLW link

[Question] What one pa­per would you show to some­one to get them ex­cited about your field?

oh54321Jul 7, 2022, 2:55 AM
10 points
1 comment1 min readLW link

Prin­ci­ples for Align­ment/​Agency Projects

johnswentworthJul 7, 2022, 2:07 AM
122 points
20 comments4 min readLW link

Con­fu­sions in My Model of AI Risk

peterbarnettJul 7, 2022, 1:05 AM
22 points
9 comments5 min readLW link

​Some Ad­ven­tures of a Cu­ri­ous Richard Feynman

Dalton MaberyJul 6, 2022, 11:11 PM
10 points
0 comments3 min readLW link

Cog­ni­tive Dis­so­nance on Cog­ni­tive Capability

niedermanJul 6, 2022, 10:53 PM
6 points
0 comments1 min readLW link
(maxniederman.com)

Outer vs in­ner mis­al­ign­ment: three framings

Richard_NgoJul 6, 2022, 7:46 PM
51 points
5 comments9 min readLW link

Tar­nished Guy who Puts a Num on it

Jacob FalkovichJul 6, 2022, 6:05 PM
44 points
11 comments4 min readLW link

Deep neu­ral net­works are not opaque.

jem-mosigJul 6, 2022, 6:03 PM
22 points
14 comments3 min readLW link

How hu­man­ity would re­spond to slow take­off, with take­aways from the en­tire COVID-19 pan­demic

Noosphere89Jul 6, 2022, 5:52 PM
4 points
1 comment2 min readLW link

[Question] Should you write un­der a blog or your own name?

Dalton MaberyJul 6, 2022, 3:26 PM
2 points
2 comments1 min readLW link

Car­ry­ing the Torch: A Re­sponse to Anna Sala­mon by the Guild of the Rose

moridinamaelJul 6, 2022, 2:20 PM
136 points
16 comments6 min readLW link

Pre­dict­ing Parental Emo­tional Changes?

jefftkJul 6, 2022, 1:50 PM
39 points
11 comments2 min readLW link
(www.jefftk.com)

Ber­lin AI Safety Open Meetup July 2022

pranomostroJul 6, 2022, 12:41 PM
6 points
0 comments1 min readLW link

Fore­cast­ing Through Fiction

YitzJul 6, 2022, 5:03 AM
5 points
2 comments8 min readLW link

In­tro­duc­ing the Fund for Align­ment Re­search (We’re Hiring!)

Jul 6, 2022, 2:07 AM
62 points
0 comments4 min readLW link

My vi­sion of a good fu­ture, part I

Jeffrey LadishJul 6, 2022, 1:23 AM
66 points
18 comments9 min readLW link

Im­pe­rial Rus­sia was do­ing fine with­out the Soviets

Davis KedroskyJul 5, 2022, 10:24 PM
6 points
3 comments14 min readLW link
(daviskedrosky.substack.com)

A Pat­tern Lan­guage For Rationality

VaniverJul 5, 2022, 7:08 PM
75 points
14 comments15 min readLW link

How to de­stroy the uni­verse with a hypercomputer

Trevor CappalloJul 5, 2022, 7:05 PM
2 points
3 comments1 min readLW link

The cu­ri­ous case of Pretty Good hu­man in­ner/​outer alignment

PavleMihaJul 5, 2022, 7:04 PM
41 points
45 comments4 min readLW link

When is it ap­pro­pri­ate to use statis­ti­cal mod­els and prob­a­bil­ities for de­ci­sion mak­ing ?

Younes KamelJul 5, 2022, 12:34 PM
10 points
7 comments4 min readLW link
(youneskamel.substack.com)

Goal Factoring

CFAR!DuncanJul 5, 2022, 7:10 AM
92 points
2 comments8 min readLW link

As­sorted thoughts about ab­strac­tion

Adam ZernerJul 5, 2022, 6:40 AM
16 points
9 comments7 min readLW link

[AN #172] Sorry for the long hi­a­tus!

Rohin ShahJul 5, 2022, 6:20 AM
54 points
0 comments3 min readLW link
(mailchi.mp)

Out­line: The Rec­tify­ing of Maps

hamnoxJul 5, 2022, 5:14 AM
7 points
0 comments2 min readLW link

[Question] Seek­ing opinions on the cur­rent and for­ward state of cryp­tocur­ren­cies.

jmhJul 5, 2022, 5:01 AM
6 points
6 comments1 min readLW link

ITT-pass­ing and ci­vil­ity are good; “char­ity” is bad; steel­man­ning is niche

Rob BensingerJul 5, 2022, 12:15 AM
163 points
36 comments6 min readLW link1 review

Please help us com­mu­ni­cate AI xrisk. It could save the world.

otto.bartenJul 4, 2022, 9:47 PM
4 points
7 comments2 min readLW link

Bench­mark for suc­cess­ful con­cept ex­trap­o­la­tion/​avoid­ing goal misgeneralization

Stuart_ArmstrongJul 4, 2022, 8:48 PM
82 points
12 comments4 min readLW link

Pro­ce­du­ral Ex­ec­u­tive Func­tion, Part 1

DaystarEldJul 4, 2022, 6:51 PM
50 points
8 comments14 min readLW link
(daystareld.com)