Code Gen­er­a­tion as an AI risk setting

Not RelevantApr 17, 2022, 10:27 PM
91 points
16 comments2 min readLW link

South Bay ACX/​SSC Spring Schel­ling Meetup

ISApr 17, 2022, 9:44 PM
3 points
0 comments1 min readLW link

ACX Bi­an­nual Meetup (with Van­cou­ver ra­tio­nal­ity & EA)

togApr 17, 2022, 9:06 PM
7 points
0 comments1 min readLW link

Stupid Rea­sons to Have More Kids

SebastianG Apr 17, 2022, 8:05 PM
24 points
22 comments5 min readLW link

Org an­nounce­ment: [AC]RC

Vivek HebbarApr 17, 2022, 5:24 PM
82 points
11 comments1 min readLW link

ACX Schel­ling Meetup

ForensicOceanographyApr 17, 2022, 4:55 PM
2 points
0 comments1 min readLW link

Fuck Your Mir­a­cle Year

rogersbaconApr 17, 2022, 4:10 PM
8 points
19 comments8 min readLW link
(rogersbacon.substack.com)

What is causal­ity to an ev­i­den­tial de­ci­sion the­o­rist?

paulfchristianoApr 17, 2022, 4:00 PM
45 points
26 comments5 min readLW link
(sideways-view.com)

Learn­ing as clos­ing feed­back loops

ambigramApr 17, 2022, 9:50 AM
9 points
0 comments17 min readLW link

Am­s­ter­dam ACX Schel­ling Meetup

Pierre VandenbergheApr 17, 2022, 9:40 AM
2 points
0 comments1 min readLW link

Coven­try ACX Schel­ling Meetup

Thomas ReadApr 17, 2022, 9:05 AM
2 points
0 comments1 min readLW link

Align­ment and Deep Learning

AiyenApr 17, 2022, 12:02 AM
44 points
36 comments8 min readLW link

Modect Englich Cpel­ling Reformc

Gordon Seidoh WorleyApr 16, 2022, 11:38 PM
5 points
38 comments2 min readLW link

[Question] Do uni­ver­si­ties have an in­cen­tive to ig­nore data ethics as more small sam­ple bias is brought to light?

casualphysicsenjoyerApr 16, 2022, 8:32 PM
1 point
1 comment1 min readLW link

Fic­tion: My al­ter­nate earth story.

Donald HobsonApr 16, 2022, 7:06 PM
25 points
3 comments5 min readLW link

Con­scious­ness: A Com­pres­sion-Based Approach

intersticeApr 16, 2022, 4:40 PM
18 points
14 comments6 min readLW link

Pop Cul­ture Align­ment Re­search and Taxes

JanApr 16, 2022, 3:45 PM
16 points
14 comments11 min readLW link
(universalprior.substack.com)

[Question] Did OpenAI let GPT out of the box?

ChristianKlApr 16, 2022, 2:56 PM
4 points
12 comments1 min readLW link

In­tro­duc­ing Mnosis

EvenflairApr 16, 2022, 2:35 PM
15 points
3 comments1 min readLW link
(guildoftherose.org)

[Question] What re­cent aca­demic ar­eas of study have a sam­ple size that is ‘too small’?

casualphysicsenjoyerApr 16, 2022, 1:52 PM
2 points
4 comments1 min readLW link

Clem’s Memo

abstractapplicApr 16, 2022, 11:59 AM
98 points
8 comments3 min readLW link

Stock­holm ACX meetup [Mee­tups Every­where Spring Edi­tion]

sallatikApr 16, 2022, 10:41 AM
1 point
0 comments1 min readLW link

Con­tra Alexan­der on the Virtue of Silence

benjaminaltApr 16, 2022, 8:15 AM
32 points
7 comments5 min readLW link

[Question] Con­strain­ing nar­row AI in a cor­po­rate setting

MaximumLibertyApr 15, 2022, 10:36 PM
28 points
4 comments1 min readLW link

Sum­mary: “How to Read Books and Write Es­says” by OSP’s Blue

Pablo RepettoApr 15, 2022, 9:17 PM
8 points
2 comments4 min readLW link
(pabloernesto.github.io)

Every­thing I Need To Know About Take­off Speeds I Learned From Air Con­di­tioner Rat­ings On Amazon

johnswentworthApr 15, 2022, 7:05 PM
166 points
128 comments5 min readLW link

Fea­ture pro­posal: Close com­ment as resolved

ViliamApr 15, 2022, 5:54 PM
41 points
15 comments1 min readLW link

[Question] Con­vince me that hu­man­ity *isn’t* doomed by AGI

YitzApr 15, 2022, 5:26 PM
61 points
50 comments1 min readLW link

Fea­ture pro­posal: Short­form reset

ViliamApr 15, 2022, 3:25 PM
12 points
8 comments2 min readLW link

Some rea­sons why a pre­dic­tor wants to be a consequentialist

Lauro LangoscoApr 15, 2022, 3:02 PM
23 points
16 comments5 min readLW link

Why Go is a Bet­ter Game than Chess

monkymindApr 15, 2022, 1:32 PM
9 points
11 comments2 min readLW link

How to be­come an AI safety researcher

peterbarnettApr 15, 2022, 11:41 AM
25 points
0 comments14 min readLW link

An­nounc­ing the Fore­cast­ing Wiki

nikosApr 15, 2022, 9:52 AM
7 points
0 comments1 min readLW link

[Question] How path-de­pen­dent are hu­man val­ues?

Ege ErdilApr 15, 2022, 9:34 AM
14 points
13 comments2 min readLW link

Refine: An In­cu­ba­tor for Con­cep­tual Align­ment Re­search Bets

adamShimiApr 15, 2022, 8:57 AM
144 points
13 comments4 min readLW link

Pivotal acts from Math AIs

azsantoskApr 15, 2022, 12:25 AM
10 points
4 comments5 min readLW link

My least fa­vorite thing

sudoApr 14, 2022, 10:33 PM
52 points
31 comments3 min readLW link

Early 2022 Paper Round-up

jsteinhardtApr 14, 2022, 8:50 PM
80 points
4 comments3 min readLW link
(bounded-regret.ghost.io)

[Question] Can some­one ex­plain to me why MIRI is so pes­simistic of our chances of sur­vival?

iamthouthouartiApr 14, 2022, 8:28 PM
10 points
7 comments1 min readLW link

Red­wood Re­search is hiring for sev­eral roles (Oper­a­tions and Tech­ni­cal)

Apr 14, 2022, 4:57 PM
29 points
0 comments1 min readLW link

Covid 4/​14/​22: China Stays the Course

ZviApr 14, 2022, 4:10 PM
26 points
1 comment7 min readLW link
(thezvi.wordpress.com)

Only Ask­ing Real Questions

jefftkApr 14, 2022, 3:50 PM
130 points
45 comments2 min readLW link
(www.jefftk.com)

[Question] What is the most sig­nifi­cant way you have changed your mind in the last year?

ChristianKlApr 14, 2022, 12:23 PM
29 points
29 comments1 min readLW link

Lies Told To Children

Eliezer YudkowskyApr 14, 2022, 11:25 AM
381 points
94 comments7 min readLW link1 review

[Question] Un­change­able Code pos­si­ble ?

AntonTimmerApr 14, 2022, 11:17 AM
7 points
9 comments1 min readLW link

Emacs Re­cen­ter­ing With Context

jefftkApr 14, 2022, 1:20 AM
17 points
1 comment1 min readLW link
(www.jefftk.com)

Fea­tures that make a re­port es­pe­cially helpful to me

lukeprogApr 14, 2022, 1:12 AM
40 points
0 comments2 min readLW link

Ex­plor­ing toy neu­ral nets un­der node re­moval. Sec­tion 1.

Donald HobsonApr 13, 2022, 11:30 PM
12 points
7 comments8 min readLW link

Make a Movie Show­ing Align­ment Failures

Logan RiggsApr 13, 2022, 9:54 PM
75 points
11 comments2 min readLW link

Sum­mary: “How to Do Re­search” by OSP’s Red

Pablo RepettoApr 13, 2022, 7:46 PM
9 points
0 comments3 min readLW link
(pabloernesto.github.io)