Cor­rigi­bil­ity as out­side view

TurnTrout8 May 2020 21:56 UTC
36 points
11 comments4 min readLW link

Les­sons from Isaac: Pit­falls of Reason

adamShimi8 May 2020 20:44 UTC
9 points
0 comments8 min readLW link

How to do re­mote co-working

SoerenMind8 May 2020 19:38 UTC
25 points
11 comments1 min readLW link

[Question] AI Box­ing for Hard­ware-bound agents (aka the China al­ign­ment prob­lem)

Logan Zoellner8 May 2020 15:50 UTC
11 points
27 comments10 min readLW link

Ra­tion­al­ity Vienna [Vir­tual] Meetup, May 2020

Viliam8 May 2020 15:03 UTC
10 points
3 comments1 min readLW link

Kids and Mo­ral Agency

jefftk8 May 2020 12:50 UTC
30 points
9 comments1 min readLW link
(www.jefftk.com)

Failures in tech­nol­ogy fore­cast­ing? A re­ply to Ord and Yudkowsky

MichaelA8 May 2020 12:41 UTC
44 points
19 comments11 min readLW link

A non-mys­ti­cal ex­pla­na­tion of “no-self” (three char­ac­ter­is­tics se­ries)

Kaj_Sotala8 May 2020 10:37 UTC
113 points
65 comments20 min readLW link1 review

[Question] What frac­tion of your life­time (0-80 years old) ego­ist bud­get would you (want to) spend on a pill that made you live for as long as you wanted (perfect in­vin­ci­bil­ity), as healthily as you wanted if you knew it would be­come available to you once you’re 80 years old (and that you would oth­er­wise ir­re­versibly die)?

Mati_Roy8 May 2020 8:50 UTC
4 points
4 comments1 min readLW link

[Question] What would you do differ­ently if you were less con­cerned with look­ing weird?

Mati_Roy7 May 2020 23:29 UTC
11 points
9 comments1 min readLW link

[Question] Why do you (not) use a pseudonym on LessWrong?

Mati_Roy7 May 2020 19:34 UTC
10 points
19 comments1 min readLW link

Covid-19 5/​7: Fight­ing Limbo

Zvi7 May 2020 19:00 UTC
27 points
7 comments10 min readLW link
(thezvi.wordpress.com)

Med­i­ta­tion skill: Sur­fing the Urge

Max Hodges7 May 2020 17:30 UTC
16 points
3 comments2 min readLW link

Kurzweil’s pre­dic­tions’ in­di­vi­d­ual scores

Stuart_Armstrong7 May 2020 17:10 UTC
17 points
0 comments1 min readLW link

Mul­ti­ple Ar­gu­ments, Mul­ti­ple Comments

lc7 May 2020 9:30 UTC
12 points
2 comments1 min readLW link

[link] How many hu­mans will have their brain pre­served? Fore­casts and trends

Mati_Roy7 May 2020 6:11 UTC
10 points
0 comments1 min readLW link

Pri­ori­tiz­ing COVID-19 in­ter­ven­tions & in­di­vi­d­ual donations

7 May 2020 1:44 UTC
11 points
0 comments20 min readLW link

Speci­fi­ca­tion gam­ing: the flip side of AI ingenuity

6 May 2020 23:51 UTC
66 points
9 comments6 min readLW link

[Question] Tips/​tricks/​notes on op­ti­miz­ing investments

Wei Dai6 May 2020 23:21 UTC
83 points
68 comments1 min readLW link

Cop­ing and Cultures

Spiracular6 May 2020 22:49 UTC
50 points
13 comments3 min readLW link

[Question] Does iso­lat­ing the high-risk sup­press COVID-19?

Fahad Alkhater6 May 2020 21:18 UTC
3 points
1 comment1 min readLW link

Covid-19: New York’s An­ti­body Tests 2

Zvi6 May 2020 17:40 UTC
16 points
0 comments10 min readLW link
(thezvi.wordpress.com)

[AN #98]: Un­der­stand­ing neu­ral net train­ing by see­ing which gra­di­ents were helpful

Rohin Shah6 May 2020 17:10 UTC
22 points
3 comments9 min readLW link
(mailchi.mp)

In­tro­duc­tion to fore­cast­ing work­sheet

edoarad6 May 2020 13:54 UTC
13 points
0 comments1 min readLW link
(www.foretold.io)

Au­dioWorklet La­tency: Fire­fox vs Chrome

jefftk6 May 2020 13:50 UTC
8 points
2 comments2 min readLW link
(www.jefftk.com)

Assess­ing Kurzweil pre­dic­tions about 2019: the results

Stuart_Armstrong6 May 2020 13:36 UTC
146 points
22 comments4 min readLW link

[Question] How should po­ten­tial AI al­ign­ment re­searchers gauge whether the field is right for them?

TurnTrout6 May 2020 12:24 UTC
20 points
5 comments1 min readLW link

[Question] How to quan­tify un­cer­tainty about a prob­a­bil­ity es­ti­mate?

mic6 May 2020 12:06 UTC
4 points
2 comments1 min readLW link

Maths writer/​cowrit­ter needed: how you can’t dis­t­in­guish early ex­po­nen­tial from early sigmoid

Stuart_Armstrong6 May 2020 9:41 UTC
41 points
13 comments1 min readLW link

How can non­prof­its gain the ad­van­tages of the for-profit model?

jasoncrawford6 May 2020 1:15 UTC
37 points
0 comments2 min readLW link
(rootsofprogress.org)

Model­ing nat­u­ral­ized de­ci­sion prob­lems in lin­ear logic

jessicata6 May 2020 0:15 UTC
14 points
2 comments6 min readLW link
(unstableontology.com)

The ways of knowing

aelwood5 May 2020 20:35 UTC
1 point
0 comments1 min readLW link
(pursuingreality.com)

A non-mys­ti­cal ex­pla­na­tion of in­sight med­i­ta­tion and the three char­ac­ter­is­tics of ex­is­tence: in­tro­duc­tion and preamble

Kaj_Sotala5 May 2020 19:09 UTC
134 points
40 comments12 min readLW link

Com­pet­i­tive safety via gra­dated curricula

Richard_Ngo5 May 2020 18:11 UTC
38 points
5 comments5 min readLW link

Writ­ing Causal Models Like We Write Programs

johnswentworth5 May 2020 18:05 UTC
90 points
10 comments4 min readLW link

“AI and Effi­ciency”, OA (44✕ im­prove­ment in CNNs since 2012)

gwern5 May 2020 16:32 UTC
48 points
0 comments1 min readLW link
(openai.com)

[Question] I’d Like To Max­i­miz­ing Profit and Hap­piness but My Hap­piness con­flicts a lot with mak­ing profit...

Master MintZ5 May 2020 5:54 UTC
2 points
2 comments1 min readLW link

[Question] Direct work vs. earn-to-give?

warrenjordan5 May 2020 5:52 UTC
1 point
0 comments1 min readLW link

[Question] How much money would you pay to get ac­cess to video footage of your sur­round­ings for a year of your choice (in the past)?

Mati_Roy5 May 2020 5:50 UTC
8 points
13 comments1 min readLW link

Con­struc­tive Definitions

Chris_Leong4 May 2020 23:50 UTC
15 points
2 comments3 min readLW link

In­di­vi­d­ual Ra­tion­al­ity Needn’t Gen­er­al­ize to Ra­tional Consensus

Akshat Mahajan4 May 2020 22:53 UTC
42 points
17 comments4 min readLW link

[Link] Ra­tion­al­ist Games—Face­book Group

Mati_Roy4 May 2020 22:13 UTC
5 points
0 comments1 min readLW link

COVID-19 from a differ­ent angle

jmh4 May 2020 17:58 UTC
8 points
6 comments1 min readLW link

In­sights from Eu­clid’s ‘Ele­ments’

TurnTrout4 May 2020 15:45 UTC
126 points
17 comments4 min readLW link

[Question] What in­for­ma­tion on (or rele­vant to) modal im­mor­tal­ity do you recom­mend?

Mati_Roy4 May 2020 11:30 UTC
11 points
3 comments1 min readLW link

Con­sis­tent Glo­ma­riza­tion should be feasible

Stuart_Armstrong4 May 2020 10:06 UTC
17 points
12 comments1 min readLW link

Scott Garrabrant’s prob­lem on re­cov­er­ing Brouwer as a corol­lary of Lawvere

Rupert4 May 2020 10:01 UTC
26 points
2 comments2 min readLW link

Named Distri­bu­tions as Artifacts

George3d64 May 2020 8:54 UTC
22 points
9 comments15 min readLW link
(blog.cerebralab.com)

How uniform is the neo­cor­tex?

zhukeepa4 May 2020 2:16 UTC
79 points
23 comments11 min readLW link1 review

Hate Crime Statistics

jefftk3 May 2020 22:30 UTC
21 points
6 comments1 min readLW link
(www.jefftk.com)