2023 Align­ment Re­search Up­dates from FAR AI

AdamGleave4 Dec 2023 22:32 UTC
14 points
0 comments1 min readEA link
(far.ai)

What’s new at FAR AI

AdamGleave4 Dec 2023 21:18 UTC
68 points
0 comments1 min readEA link
(far.ai)

How the cricket feels and what the meal­worm has to say: The in­fluence of rear­ing en­vi­ron­ments on in­sect welfare in differ­ent food and feed pro­duc­tion systems

Group Organizer4 Dec 2023 21:16 UTC
14 points
0 comments1 min readEA link

Non-clas­sic sto­ries about schem­ing (Sec­tion 2.3.2 of “Schem­ing AIs”)

Joe_Carlsmith4 Dec 2023 18:44 UTC
12 points
1 comment1 min readEA link

Re­search Re­port: Us­ing Mass Me­dia to In­crease Care­giver Aware­ness in Sub-Sa­haran Africa

KT Hobbs4 Dec 2023 18:18 UTC
26 points
2 comments39 min readEA link

An ex­haus­tive list of cos­mic threats

JordanStone4 Dec 2023 17:59 UTC
74 points
19 comments6 min readEA link

Biolog­i­cal su­per­in­tel­li­gence: a solu­tion to AI safety

Yarrow B.4 Dec 2023 13:09 UTC
−1 points
6 comments1 min readEA link

Is the An­i­mal & Ve­gan Ad­vo­cacy (AVA) Sum­mit an EA Event?

Julia Reinelt4 Dec 2023 10:11 UTC
85 points
7 comments3 min readEA link

Link post: Euro­pean philan­thropy man­i­festo calls for a sin­gle mar­ket for philanthropy

Hedgie4 Dec 2023 9:36 UTC
−3 points
0 comments1 min readEA link

Taiwan’s mil­i­tary com­pla­cency.

JKitson4 Dec 2023 9:28 UTC
32 points
4 comments11 min readEA link

Why microplas­tics should mat­ter to EAs

BiancaCojocaru4 Dec 2023 9:27 UTC
3 points
1 comment3 min readEA link

ai-plans.com De­cem­ber Cri­tique-a-Thon

Kabir_Kumar4 Dec 2023 9:27 UTC
1 point
0 comments2 min readEA link

En­gag­ing UK Cen­tre-Right Types in Ex­is­ten­tial Risk

Max_Thilo4 Dec 2023 9:26 UTC
17 points
0 comments1 min readEA link

[Question] Is The Free­dom Fund still the best char­ity ad­dress­ing hu­man traf­fick­ing /​ mod­ern slav­ery, and why is this cause area not of more in­ter­est to EA?

Brain_in_a_Vat4 Dec 2023 9:24 UTC
24 points
2 comments1 min readEA link

En­gag­ing with AI in a Per­sonal Way

Spyder Rex4 Dec 2023 9:23 UTC
−9 points
0 comments1 min readEA link

Hash­marks: Pri­vacy-Pre­serv­ing Bench­marks for High-Stakes AI Evaluation

Paul Bricman4 Dec 2023 7:41 UTC
3 points
0 comments16 min readEA link
(arxiv.org)

[Question] What am I miss­ing re. open-source LLM’s?

another-anon-do-gooder4 Dec 2023 4:48 UTC
1 point
2 comments1 min readEA link

X% of your pur­chase goes to Y

dEAsign4 Dec 2023 4:14 UTC
17 points
7 comments2 min readEA link

All Tech is Hu­man <-> EA

tae3 Dec 2023 21:01 UTC
29 points
0 comments2 min readEA link

Does schem­ing lead to ad­e­quate fu­ture em­pow­er­ment? (Sec­tion 2.3.1.2 of “Schem­ing AIs”)

Joe_Carlsmith3 Dec 2023 18:32 UTC
6 points
1 comment1 min readEA link

On Sto­ries, their im­pact and how to im­prove them

Timon Renzelmann3 Dec 2023 15:58 UTC
35 points
4 comments16 min readEA link

The benefits and risks of op­ti­mism (about AI safety)

Karl von Wendt3 Dec 2023 12:45 UTC
3 points
5 comments1 min readEA link

[Question] ai safety ques­tion

David turner3 Dec 2023 12:42 UTC
−13 points
3 comments1 min readEA link

Best free we­bi­nars /​ videos for stu­dents to learn to con­duct cost-effec­tive­ness anal­y­sis?

freedomandutility3 Dec 2023 12:04 UTC
20 points
0 comments1 min readEA link

I donated $35 to offset my car­bon foot­print for this year

Luke Eure3 Dec 2023 9:46 UTC
40 points
16 comments2 min readEA link

Farewell mes­sages from the EA Philip­pines Core Team

Elmerei Cuevas3 Dec 2023 1:07 UTC
78 points
1 comment3 min readEA link

Quick takes on “AI is easy to con­trol”

So8res2 Dec 2023 22:33 UTC
−12 points
4 comments1 min readEA link

What do we re­ally know about growth in LMICs? (Part 1: sec­toral trans­for­ma­tion)

Karthik Tadepalli2 Dec 2023 17:04 UTC
158 points
42 comments8 min readEA link

GWWC Lon­don Group Co-leads: Reflec­tions on our first event

Chris Rouse2 Dec 2023 15:34 UTC
39 points
2 comments2 min readEA link

The goal-guard­ing hy­poth­e­sis (Sec­tion 2.3.1.1 of “Schem­ing AIs”)

Joe_Carlsmith2 Dec 2023 15:20 UTC
6 points
1 comment1 min readEA link

Out-of-dis­tri­bu­tion Bioattacks

Jeff Kaufman2 Dec 2023 12:20 UTC
70 points
5 comments1 min readEA link

Aging should be effec­tive al­tru­ism’s 5th cause area

Yarrow B.2 Dec 2023 8:28 UTC
20 points
15 comments1 min readEA link

Can a ter­ror­ist at­tack cause hu­man ex­tinc­tion? Not on priors

Vasco Grilo2 Dec 2023 8:20 UTC
43 points
8 comments15 min readEA link

MATS Sum­mer 2023 Retrospective

Rocket2 Dec 2023 0:12 UTC
28 points
3 comments1 min readEA link

A New Paradigm For Emo­tional Work And Men­tal Health

Milli | Martin1 Dec 2023 22:12 UTC
7 points
0 comments1 min readEA link

Speci­fi­ca­tion Gam­ing: How AI Can Turn Your Wishes Against You [RA Video]

Writer1 Dec 2023 19:30 UTC
8 points
1 comment1 min readEA link
(youtu.be)

Tak­ing Into Ac­count Sen­tient Non-Hu­mans in AI Am­bi­tious Value Learn­ing: Sen­tien­tist Co­her­ent Ex­trap­o­lated Volition

Adrià Moret1 Dec 2023 18:01 UTC
38 points
2 comments42 min readEA link

Do­ing Good Effec­tively is Unusual

Richard Y Chappell1 Dec 2023 17:03 UTC
174 points
26 comments7 min readEA link
(rychappell.substack.com)

The 8-Week Mar­ket­ing Plan—A Real­is­tic and Prac­ti­cal Roadmap For EAs

Igor Scaldini1 Dec 2023 16:23 UTC
37 points
1 comment16 min readEA link

Why Did NEPA Peak in 2016?

Maxwell Tabarrok1 Dec 2023 16:18 UTC
11 points
1 comment3 min readEA link
(maximumprogress.substack.com)

Philoso­phers Against Malaria Fundraiser

mhendric1 Dec 2023 16:12 UTC
16 points
3 comments1 min readEA link

Well-Be­ing In­dex (WBI): Redefin­ing So­cietal Progress Together

Max Kusmierek1 Dec 2023 15:23 UTC
5 points
1 comment6 min readEA link

How can EA bring about the so­cial change it de­sires? An anal­y­sis of his­tor­i­cal so­cial change port­fo­lios

James Herbert1 Dec 2023 14:55 UTC
21 points
3 comments7 min readEA link

How use­ful for al­ign­ment-rele­vant work are AIs with short-term goals? (Sec­tion 2.2.4.3 of “Schem­ing AIs”)

Joe_Carlsmith1 Dec 2023 14:51 UTC
6 points
0 comments1 min readEA link

Ex­tend­ing Ex­ist­ing An­i­mal Pro­tec­tion Laws

Moritz Stumpe1 Dec 2023 14:44 UTC
43 points
2 comments35 min readEA link

[Linkpost] Lant Pritch­ett ‘The poli­ti­cal ac­cept­abil­ity of time-limited la­bor mo­bil­ity: Five lev­ers open­ing the Over­ton win­dow’

John G. Halstead1 Dec 2023 13:52 UTC
18 points
8 comments1 min readEA link

My Per­sonal Pri­ori­ties, Char­ity, Ju­daism, and Effec­tive Altruism

Davidmanheim1 Dec 2023 11:23 UTC
96 points
16 comments5 min readEA link

Cause area re­port: vaccines

Erwan Sallard1 Dec 2023 10:35 UTC
19 points
2 comments13 min readEA link

[Question] Hi Effec­tive Altru­ism com­mu­nity, Hav­ing ab­sorbed in­sights from “80,000 Hours,” a re­source pri­mar­ily tai­lored to the United States, I’m ea­ger to adapt its in­come and hap­piness con­sid­er­a­tions for In­dia. Can you please help me?

Mohit Gaur1 Dec 2023 10:35 UTC
15 points
0 comments1 min readEA link

So­lar4Africa Pro­ject #4 - Gen­eral In­ter­ven­tion Refine­ment and Cost-Effec­tive­ness Anal­y­sis of So­lar Elec­tric Cook­ing Sys­tems: Pro­ject Overview and Methodology

shanemurray1 Dec 2023 10:35 UTC
11 points
1 comment4 min readEA link