My least fa­vorite thing

sudo14 Apr 2022 22:33 UTC
51 points
31 comments3 min readLW link

Early 2022 Paper Round-up

jsteinhardt14 Apr 2022 20:50 UTC
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?

iamthouthouarti14 Apr 2022 20:28 UTC
10 points
7 comments1 min readLW link

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

14 Apr 2022 16:57 UTC
29 points
0 comments1 min readLW link

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

Zvi14 Apr 2022 16:10 UTC
26 points
1 comment7 min readLW link
(thezvi.wordpress.com)

Only Ask­ing Real Questions

jefftk14 Apr 2022 15:50 UTC
128 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?

ChristianKl14 Apr 2022 12:23 UTC
29 points
29 comments1 min readLW link

Lies Told To Children

Eliezer Yudkowsky14 Apr 2022 11:25 UTC
370 points
94 comments7 min readLW link1 review

[Question] Un­change­able Code pos­si­ble ?

AntonTimmer14 Apr 2022 11:17 UTC
7 points
9 comments1 min readLW link

Emacs Re­cen­ter­ing With Context

jefftk14 Apr 2022 1:20 UTC
17 points
1 comment1 min readLW link
(www.jefftk.com)

Fea­tures that make a re­port es­pe­cially helpful to me

lukeprog14 Apr 2022 1:12 UTC
40 points
0 comments2 min readLW link

Ex­plor­ing toy neu­ral nets un­der node re­moval. Sec­tion 1.

Donald Hobson13 Apr 2022 23:30 UTC
12 points
7 comments8 min readLW link

Make a Movie Show­ing Align­ment Failures

Logan Riggs13 Apr 2022 21:54 UTC
75 points
11 comments2 min readLW link

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

Pablo Repetto13 Apr 2022 19:46 UTC
9 points
0 comments3 min readLW link
(pabloernesto.github.io)

A Quick Guide to Con­fronting Doom

Ruby13 Apr 2022 19:30 UTC
240 points
33 comments2 min readLW link

De­sign, Im­ple­ment and Verify

rwallace13 Apr 2022 18:14 UTC
32 points
13 comments4 min readLW link

Take­off speeds have a huge effect on what it means to work on AI x-risk

Buck13 Apr 2022 17:38 UTC
139 points
27 comments2 min readLW link2 reviews

Bu­dapest Meetup

Richard Horvath13 Apr 2022 17:23 UTC
2 points
0 comments1 min readLW link

[Question] What to in­clude in a guest lec­ture on ex­is­ten­tial risks from AI?

Aryeh Englander13 Apr 2022 17:03 UTC
20 points
9 comments1 min readLW link

Com­mon Knowl­edge is a Cir­cle Game for Toddlers

ryan_b13 Apr 2022 15:24 UTC
58 points
1 comment1 min readLW link

Another list of the­o­ries of im­pact for interpretability

Beth Barnes13 Apr 2022 13:29 UTC
33 points
1 comment5 min readLW link

The Cage of the Language

Martin Sustrik13 Apr 2022 5:20 UTC
53 points
19 comments2 min readLW link

[Question] What’s a good prob­a­bil­ity dis­tri­bu­tion fam­ily (e.g. “log-nor­mal”) to use for AGI timelines?

David Scott Krueger (formerly: capybaralet)13 Apr 2022 4:45 UTC
9 points
11 comments1 min readLW link

How dath ilan co­or­di­nates around solv­ing alignment

Thomas Kwa13 Apr 2022 4:22 UTC
64 points
45 comments5 min readLW link

What more com­pute does for brain-like mod­els: re­sponse to Rohin

Nathan Helm-Burger13 Apr 2022 3:40 UTC
22 points
14 comments12 min readLW link

[Question] “Frag­ility of Value” vs. LLMs

Not Relevant13 Apr 2022 2:02 UTC
34 points
33 comments1 min readLW link

The Peerless

Tamsin Leake13 Apr 2022 1:07 UTC
18 points
2 comments1 min readLW link
(carado.moe)

Com­men­su­rable Scien­tific Paradigms; or, com­putable induction

samshap13 Apr 2022 0:01 UTC
14 points
0 comments5 min readLW link

Con­vinc­ing Peo­ple of Align­ment with Street Epistemology

Logan Riggs12 Apr 2022 23:43 UTC
54 points
4 comments3 min readLW link

Use­ful Vices for Wicked Problems

HoldenKarnofsky12 Apr 2022 19:30 UTC
64 points
2 comments17 min readLW link1 review
(www.cold-takes.com)

SSC/​ACX, San Diego, Schel­ling Point, Mee­tups Everywhere

CitizenTen12 Apr 2022 18:50 UTC
2 points
0 comments1 min readLW link

SSC/​ACX San Diego Rock Climbing

CitizenTen12 Apr 2022 18:46 UTC
2 points
0 comments1 min readLW link

[Question] Does the ra­tio­nal­ist com­mu­nity have a mem­ber­ship fun­nel?

Alex_Altair12 Apr 2022 18:44 UTC
37 points
17 comments1 min readLW link

A Small Nega­tive Re­sult on Debate

Sam Bowman12 Apr 2022 18:19 UTC
42 points
11 comments1 min readLW link

US Taxes: Ad­just With­hold­ing When Donat­ing?

jefftk12 Apr 2022 15:50 UTC
15 points
1 comment1 min readLW link
(www.jefftk.com)

In­tro­duc­ing Effec­tive Self-Help

Ben Williamson12 Apr 2022 15:01 UTC
18 points
0 comments16 min readLW link

Ukraine Post #10: Next Phase

Zvi12 Apr 2022 13:40 UTC
45 points
13 comments14 min readLW link
(thezvi.wordpress.com)

Is tech­ni­cal AI al­ign­ment re­search a net pos­i­tive?

cranberry_bear12 Apr 2022 13:07 UTC
6 points
2 comments2 min readLW link

[Question] What is your ad­vice for el­der care, par­tic­u­larly tak­ing care of de­men­tia pa­tients?

JohannWolfgang12 Apr 2022 11:33 UTC
4 points
6 comments1 min readLW link

Re­ward model hack­ing as a challenge for re­ward learning

Erik Jenner12 Apr 2022 9:39 UTC
25 points
1 comment9 min readLW link

How I use Anki: ex­pand­ing the scope of SRS

CallumMcDougall12 Apr 2022 8:28 UTC
36 points
8 comments19 min readLW link

[Question] What do you think will most prob­a­bly hap­pen to our con­scious­ness when our simu­la­tion ends?

ArtMi12 Apr 2022 8:23 UTC
1 point
5 comments1 min readLW link

Fa­vorites & Performers

Soma12 Apr 2022 5:50 UTC
9 points
0 comments1 min readLW link

A broad basin of at­trac­tion around hu­man val­ues?

Wei Dai12 Apr 2022 5:15 UTC
109 points
17 comments2 min readLW link

AI gov­er­nance stu­dent hackathon on Satur­day, April 23: reg­ister now!

mic12 Apr 2022 4:48 UTC
14 points
0 comments1 min readLW link

The Pla­ton­ist’s Dilemma: A Remix on the Pri­soner’s.

James Camacho12 Apr 2022 3:49 UTC
5 points
2 comments5 min readLW link

[Question] Three ques­tions about mesa-optimizers

Eric Neyman12 Apr 2022 2:58 UTC
24 points
5 comments3 min readLW link

The Amish

PeterMcCluskey12 Apr 2022 2:54 UTC
49 points
5 comments6 min readLW link
(www.bayesianinvestor.com)

Ra­tion­al­ist Should Win. Not Dy­ing with Dig­nity and Fund­ing WBE.

CitizenTen12 Apr 2022 2:14 UTC
32 points
14 comments5 min readLW link

[Question] How can I de­ter­mine that Elicit is not some weak AGI’s at­tempt at tak­ing over the world ?

Lucie Philippon12 Apr 2022 0:54 UTC
5 points
3 comments1 min readLW link