Me­tac­u­lus Launches 2023/​2024 FluSight Challenge Sup­port­ing CDC, $5K in Prizes

ChristianWilliamsSep 27, 2023, 9:35 PM
5 points
0 comments1 min readLW link
(www.metaculus.com)

Pro­jects I would like to see (pos­si­bly at AI Safety Camp)

Linda LinseforsSep 27, 2023, 9:27 PM
22 points
12 comments4 min readLW link

Towards Bet­ter Mile­stones for Mon­i­tor­ing AI Capabilities

snewmanSep 27, 2023, 9:18 PM
11 points
0 comments14 min readLW link

[Question] Is Bjorn Lom­borg roughly right about cli­mate change policy?

yhoisethSep 27, 2023, 8:06 PM
29 points
14 comments2 min readLW link
(www.sciencedirect.com)

Com­mon­sense Good, Creative Good

jefftkSep 27, 2023, 7:50 PM
44 points
11 comments3 min readLW link
(www.jefftk.com)

Petrov Day [Spoiler Warn­ing]

lsusrSep 27, 2023, 7:20 PM
6 points
6 comments1 min readLW link

The Hid­den Com­plex­ity of Wishes—The Animation

WriterSep 27, 2023, 5:59 PM
33 points
0 comments1 min readLW link
(youtu.be)

MMLU’s Mo­ral Sce­nar­ios Bench­mark Doesn’t Mea­sure What You Think it Measures

corey morrisSep 27, 2023, 5:54 PM
18 points
3 comments4 min readLW link
(medium.com)

[Question] What’s your stan­dard for good work perfor­mance?

Chi NguyenSep 27, 2023, 4:58 PM
30 points
3 comments1 min readLW link

The Role of Groups in the Pro­gres­sion of Hu­man Understanding

Chris_LeongSep 27, 2023, 3:09 PM
11 points
0 comments2 min readLW link

The Great Disembedding

rogersbaconSep 27, 2023, 2:53 PM
16 points
6 comments16 min readLW link
(www.secretorum.life)

[Question] how do short-timelin­ers rea­son about the differ­ences be­tween brain and AI?

JavierCCSep 27, 2023, 8:13 AM
2 points
11 comments1 min readLW link

[Question] Is there a widely ac­cepted met­ric for ‘gen­uine­ness’ in in­ter­per­sonal com­mu­ni­ca­tion?

M. Y. ZuoSep 27, 2023, 5:30 AM
6 points
3 comments1 min readLW link

Bari­a­tric surgery seems like a no-brainer for most mor­bidly obese people

lcSep 27, 2023, 1:05 AM
12 points
12 comments3 min readLW link

Ja­cob on the Precipice

Richard_NgoSep 26, 2023, 9:16 PM
46 points
8 comments11 min readLW link
(narrativeark.substack.com)

Text Posts from the Kids Group: 2022

jefftkSep 26, 2023, 8:40 PM
33 points
2 comments7 min readLW link
(www.jefftk.com)

GPT-4 for per­sonal pro­duc­tivity: on­line dis­trac­tion blocker

SergiiSep 26, 2023, 5:41 PM
66 points
13 comments2 min readLW link
(grgv.xyz)

ARENA 2.0 - Im­pact Report

CallumMcDougallSep 26, 2023, 5:13 PM
35 points
5 comments13 min readLW link

Mechanis­tic In­ter­pretabil­ity Read­ing group

Sep 26, 2023, 4:26 PM
15 points
0 comments1 min readLW link

An­nounc­ing the CNN In­ter­pretabil­ity Competition

scasperSep 26, 2023, 4:21 PM
22 points
0 comments4 min readLW link

Mak­ing AIs less likely to be spiteful

Sep 26, 2023, 2:12 PM
118 points
7 comments10 min readLW link

[Linkpost] Mark Zucker­berg con­fronted about Meta’s Llama 2 AI’s abil­ity to give users de­tailed guidance on mak­ing an­thrax—Busi­ness Insider

micSep 26, 2023, 12:05 PM
18 points
11 comments2 min readLW link
(www.businessinsider.com)

En­forc­ing Far-Fu­ture Con­tracts for Governments

FCCCSep 26, 2023, 4:26 AM
−7 points
49 comments3 min readLW link

Car­i­oca Petrov Day

GiskardSep 26, 2023, 12:30 AM
1 point
0 comments1 min readLW link

[Question] A few Align­ment ques­tions: util­ity op­ti­miz­ers, SLT, sharp left turn and identifiability

Igor TimofeevSep 26, 2023, 12:27 AM
6 points
1 comment2 min readLW link

Im­pact sto­ries for model in­ter­nals: an ex­er­cise for in­ter­pretabil­ity researchers

jennySep 25, 2023, 11:15 PM
29 points
3 comments7 min readLW link

Au­to­nomic Sanity

SableSep 25, 2023, 10:37 PM
20 points
9 comments4 min readLW link
(affablyevil.substack.com)

[Question] What is wrong with this “util­ity switch but­ton prob­lem” ap­proach?

Donald HobsonSep 25, 2023, 9:36 PM
14 points
3 comments1 min readLW link

You should just smile at strangers a lot

chaosmageSep 25, 2023, 8:12 PM
14 points
10 comments1 min readLW link

The King and the Golem

Richard_NgoSep 25, 2023, 7:51 PM
191 points
19 comments5 min readLW link1 review
(narrativeark.substack.com)

Public Opinion on AI Safety: AIMS 2023 and 2021 Summary

Sep 25, 2023, 6:55 PM
3 points
2 comments3 min readLW link
(www.sentienceinstitute.org)

Wel­come to Ap­ply: The 2024 Vi­talik Bu­terin Fel­low­ships in AI Ex­is­ten­tial Safety by FLI!

Zhijing JinSep 25, 2023, 6:42 PM
5 points
2 comments2 min readLW link

Eval­u­at­ing hid­den di­rec­tions on the util­ity dataset: clas­sifi­ca­tion, steer­ing and removal

Sep 25, 2023, 5:19 PM
25 points
3 comments7 min readLW link

Linkpost: A model of bi­ases as aris­ing from meta-beliefs

JuanGarciaSep 25, 2023, 5:14 PM
5 points
0 comments1 min readLW link

[Question] What causes a de­ci­sion the­ory to be used?

DagonSep 25, 2023, 4:33 PM
8 points
2 comments1 min readLW link

Un­der­stand­ing strate­gic de­cep­tion and de­cep­tive alignment

Sep 25, 2023, 4:27 PM
64 points
16 comments7 min readLW link
(www.apolloresearch.ai)

The Mer­its of Con­trar­i­anism & Why I hate Chat­bots. [My Ex­pe­rience with the Ide­olog­i­cal Tur­ing Test @ a Less Wrong meetup]

Amina V.Sep 25, 2023, 4:13 PM
4 points
1 comment1 min readLW link
(bimbollectual.com)

In­side Views, Im­pos­tor Syn­drome, and the Great LARP

johnswentworthSep 25, 2023, 4:08 PM
336 points
53 comments5 min readLW link

“X dis­tracts from Y” as a thinly-dis­guised fight over group sta­tus /​ politics

Steven ByrnesSep 25, 2023, 3:18 PM
112 points
14 comments8 min readLW link

Ama­zon to in­vest up to $4 billion in Anthropic

Davis_KingsleySep 25, 2023, 2:55 PM
44 points
8 comments1 min readLW link
(twitter.com)

Should Effec­tive Altru­ists be Valuists in­stead of util­i­tar­i­ans?

Sep 25, 2023, 2:03 PM
1 point
3 comments6 min readLW link

Feedly Breaks MathML

jefftkSep 25, 2023, 1:40 PM
15 points
3 comments1 min readLW link
(www.jefftk.com)

[Question] How have you be­come more hard-work­ing?

Chi NguyenSep 25, 2023, 12:37 PM
82 points
42 comments1 min readLW link

Au­tomat­ing In­tel­li­gence: A Cur­sory Glance at How Au­toML Brings Pre­ci­sion to AI Development

RoscoHunterSep 25, 2023, 9:39 AM
3 points
0 comments3 min readLW link

In­ter­pret­ing OpenAI’s Whisper

EllenaRSep 24, 2023, 5:53 PM
116 points
13 comments7 min readLW link

Con­tra­dic­tion Ap­peal Bias

onurSep 24, 2023, 5:03 PM
3 points
2 comments1 min readLW link

RAIN: Your Lan­guage Models Can Align Them­selves with­out Fine­tun­ing—Microsoft Re­search 2023 - Re­duces the ad­ver­sar­ial prompt at­tack suc­cess rate from 94% to 19%!

Singularian2501Sep 24, 2023, 4:48 PM
5 points
0 comments1 min readLW link

Honor Sys­tem for Vac­ci­na­tion?

jefftkSep 24, 2023, 11:50 AM
17 points
22 comments1 min readLW link
(www.jefftk.com)

Far-Fu­ture Com­mit­ments as a Policy Con­sen­sus Strategy

FCCCSep 24, 2023, 6:34 AM
7 points
40 comments1 min readLW link

Five ne­glected work ar­eas that could re­duce AI risk

Sep 24, 2023, 2:03 AM
17 points
5 comments9 min readLW link