AGI Ruin: A List of Lethalities

Eliezer Yudkowsky5 Jun 2022 22:05 UTC
901 points
690 comments30 min readLW link3 reviews

Teach­ing all things to all peo­ple in all ways

Anonymous5 Jun 2022 21:38 UTC
1 point
2 comments10 min readLW link

Noisy en­vi­ron­ment reg­u­late util­ity maximizers

Niclas Kupper5 Jun 2022 18:48 UTC
4 points
0 comments7 min readLW link

Ex­pected Value vs. Ex­pected Growth

tom-pollak5 Jun 2022 18:48 UTC
3 points
1 comment2 min readLW link

North­boro Air Qual­ity Measurement

jefftk5 Jun 2022 17:50 UTC
9 points
0 comments1 min readLW link
(www.jefftk.com)

New co­op­er­a­tion mechanism—quadratic fund­ing with­out a match­ing pool

Filip Sondej5 Jun 2022 13:55 UTC
11 points
0 comments5 min readLW link

The Fourth Arena 2: New be­ings in time

Bill Benzon5 Jun 2022 13:30 UTC
1 point
0 comments2 min readLW link

Rus­sian x-risks newslet­ter May 2022 + short his­tory of “method­ol­o­gists”

avturchin5 Jun 2022 11:50 UTC
23 points
4 comments2 min readLW link

Some ques­tions I’ve been pon­der­ing...

Dalton Mabery5 Jun 2022 4:21 UTC
1 point
3 comments1 min readLW link

Rein­vent­ing the wheel

jasoncrawford4 Jun 2022 22:39 UTC
78 points
13 comments2 min readLW link
(rootsofprogress.org)

What do you do to de­liber­ately prac­tice?

hath4 Jun 2022 22:20 UTC
25 points
9 comments2 min readLW link

Quick Look: Asymp­tomatic Her­pes Shedding

Elizabeth4 Jun 2022 21:40 UTC
37 points
4 comments2 min readLW link
(acesounderglass.com)

Meetup in SF, June 11: Progress Stud­ies + Effec­tive Altruism

4 Jun 2022 21:30 UTC
7 points
0 comments1 min readLW link

How to pur­sue a ca­reer in tech­ni­cal AI alignment

Charlie Rogers-Smith4 Jun 2022 21:11 UTC
68 points
1 comment39 min readLW link

Open & Wel­come Thread—June 2022

MondSemmel4 Jun 2022 19:27 UTC
9 points
30 comments1 min readLW link

The Fourth Arena: What’s Up in the world these days? We’re mov­ing to a new, a new what?

Bill Benzon4 Jun 2022 19:07 UTC
2 points
0 comments3 min readLW link

Towards a For­mal­i­sa­tion of Re­turns on Cog­ni­tive Rein­vest­ment (Part 1)

DragonGod4 Jun 2022 18:42 UTC
17 points
11 comments13 min readLW link

[Question] Does quan­tum me­chan­ics pre­dict all the effects of rel­a­tivity ex­cept grav­ity?

EniScien4 Jun 2022 13:52 UTC
4 points
2 comments1 min readLW link

Deep Learn­ing Sys­tems Are Not Less In­ter­pretable Than Logic/​Prob­a­bil­ity/​Etc

johnswentworth4 Jun 2022 5:41 UTC
142 points
53 comments2 min readLW link1 review

An­nounc­ing the Align­ment of Com­plex Sys­tems Re­search Group

4 Jun 2022 4:10 UTC
91 points
20 comments5 min readLW link

Eter­nal youth as eter­nal suffering

shminux4 Jun 2022 1:48 UTC
7 points
2 comments1 min readLW link

D&D.Sci June 2022: A God­dess Tried To Rein­car­nate Me Into A Fan­tasy World, But I In­sisted On Us­ing Data Science To Select An Op­ti­mal Com­bi­na­tion Of Cheat Skills!

abstractapplic4 Jun 2022 1:28 UTC
39 points
22 comments3 min readLW link

The Bur­den of Worldbuilding

lsusr4 Jun 2022 1:15 UTC
27 points
12 comments1 min readLW link

[Question] Longter­mist Con­se­quences of a New Dark Age?

David Udell3 Jun 2022 23:00 UTC
7 points
3 comments1 min readLW link

Just Say No to Utilitarianism

Arjun Panickssery3 Jun 2022 22:59 UTC
3 points
0 comments1 min readLW link
(arjunpanickssery.substack.com)

The STEM Attractor

David Udell3 Jun 2022 22:21 UTC
12 points
0 comments2 min readLW link

Book Re­view: Talent

Zvi3 Jun 2022 20:10 UTC
70 points
19 comments79 min readLW link
(thezvi.wordpress.com)

On The Spec­trum, On The Guest List: (iii) Etiquette

party girl3 Jun 2022 18:44 UTC
7 points
1 comment8 min readLW link
(onthespectrumontheguestlist.substack.com)

Give the AI safe tools

Adam Jermyn3 Jun 2022 17:04 UTC
3 points
0 comments4 min readLW link

Ra­tion­al­ity camps in Oxford for 16-20 yo: Ap­ply by June 12th

Anna Gajdova3 Jun 2022 15:22 UTC
25 points
0 comments1 min readLW link

I’m try­ing out “as­ter­oid mind­set”

Alex_Altair3 Jun 2022 13:35 UTC
90 points
5 comments4 min readLW link

Monthly Shorts 5/​22

Celer3 Jun 2022 13:10 UTC
4 points
1 comment2 min readLW link
(keller.substack.com)

On effec­tive al­tru­ism, util­i­tar­i­anism and localness

David Hugh-Jones3 Jun 2022 10:34 UTC
14 points
2 comments5 min readLW link
(wyclif.substack.com)

[Linkpost] A Chi­nese AI op­ti­mized for killing

RomanS3 Jun 2022 9:17 UTC
−2 points
4 comments1 min readLW link

In­ter­gen­er­a­tional trauma im­ped­ing co­op­er­a­tive ex­is­ten­tial safety efforts

Andrew_Critch3 Jun 2022 8:13 UTC
128 points
29 comments3 min readLW link

Silliness

lsusr3 Jun 2022 4:59 UTC
18 points
0 comments1 min readLW link

Another Calming Example

jefftk3 Jun 2022 2:20 UTC
39 points
13 comments2 min readLW link
(www.jefftk.com)

[MLSN #4]: Many New In­ter­pretabil­ity Papers, Vir­tual Logit Match­ing, Ra­tion­al­iza­tion Helps Robustness

Dan H3 Jun 2022 1:20 UTC
18 points
0 comments4 min readLW link

A short con­cep­tual ex­plainer of Im­manuel Kant’s Cri­tique of Pure Reason

jessicata3 Jun 2022 1:06 UTC
57 points
12 comments16 min readLW link
(unstableontology.com)

Ad­ver­sar­ial train­ing, im­por­tance sam­pling, and anti-ad­ver­sar­ial train­ing for AI whistleblowing

Buck2 Jun 2022 23:48 UTC
37 points
0 comments3 min readLW link

The pro­to­typ­i­cal catas­trophic AI ac­tion is get­ting root ac­cess to its datacenter

Buck2 Jun 2022 23:46 UTC
164 points
13 comments2 min readLW link1 review

Con­fused why a “ca­pa­bil­ities re­search is good for al­ign­ment progress” po­si­tion isn’t dis­cussed more

Kaj_Sotala2 Jun 2022 21:41 UTC
129 points
27 comments4 min readLW link

An­nounc­ing a con­test: EA Crit­i­cism and Red Teaming

fin2 Jun 2022 20:27 UTC
17 points
1 comment14 min readLW link
(forum.effectivealtruism.org)

Fact post: pro­ject-based learning

dominicq2 Jun 2022 20:18 UTC
11 points
4 comments3 min readLW link

The case for us­ing the term ‘steel­man­ning’ in­stead of ‘prin­ci­ple of char­ity’

ChristianKl2 Jun 2022 19:24 UTC
26 points
7 comments3 min readLW link

Covid 6/​2/​22: De­clin­ing to Respond

Zvi2 Jun 2022 13:50 UTC
55 points
10 comments7 min readLW link
(thezvi.wordpress.com)

The hor­ror of what must, yet can­not, be true

Kaj_Sotala2 Jun 2022 10:20 UTC
52 points
18 comments2 min readLW link
(kajsotala.fi)

Paradigms of AI al­ign­ment: com­po­nents and enablers

Vika2 Jun 2022 6:19 UTC
53 points
4 comments8 min readLW link

The Bio An­chors Forecast

Ansh Radhakrishnan2 Jun 2022 1:32 UTC
12 points
0 comments3 min readLW link

**Venue Changed** ACX Mon­treal Meetup Jun 18 2022

Emmett2 Jun 2022 0:43 UTC
10 points
0 comments1 min readLW link