Meta-prefer­ences are weird

16 Jul 2020 23:03 UTC
13 points
2 comments5 min readLW link

Sun­day July 19, 1pm (PDT) — talks by Rae­mon, ricraz, mr-hire, Jame­son Quinn

16 Jul 2020 20:04 UTC
26 points
6 comments1 min readLW link

[Question] What should be the topic of my LW mini-talk this Sun­day (July 18th)?

Jameson Quinn16 Jul 2020 16:32 UTC
7 points
3 comments1 min readLW link

Covid 7/​16: Be­com­ing the Mask

Zvi16 Jul 2020 12:40 UTC
82 points
20 comments15 min readLW link
(thezvi.wordpress.com)

Why as­so­ci­a­tive op­er­a­tions?

Sunny from QAD16 Jul 2020 12:36 UTC
6 points
7 comments1 min readLW link
(questionsanddaylight.com)

[Question] How big of an is­sue are patent trolls to the av­er­age startup?

ChristianKl16 Jul 2020 11:31 UTC
12 points
4 comments1 min readLW link

[AN #107]: The con­ver­gent in­stru­men­tal sub­goals of goal-di­rected agents

Rohin Shah16 Jul 2020 6:47 UTC
13 points
1 comment8 min readLW link
(mailchi.mp)

[AN #108]: Why we should scru­ti­nize ar­gu­ments for AI risk

Rohin Shah16 Jul 2020 6:47 UTC
19 points
6 comments12 min readLW link
(mailchi.mp)

Align­ment pro­pos­als and com­plex­ity classes

evhub16 Jul 2020 0:27 UTC
40 points
26 comments13 min readLW link

[Question] How should AI de­bate be judged?

abramdemski15 Jul 2020 22:20 UTC
49 points
26 comments6 min readLW link

Au­to­mat­i­cally Turn­ing Off Com­puter at Night

Raemon15 Jul 2020 20:42 UTC
19 points
13 comments2 min readLW link

[Question] Public Figures Con­tract­ing COVID-19 as Pos­i­tive Event

mc15 Jul 2020 19:56 UTC
−11 points
2 comments1 min readLW link

Diver­gence causes iso­lated de­mands for rigor

George3d615 Jul 2020 18:59 UTC
14 points
4 comments7 min readLW link
(blog.cerebralab.com)

[Question] What do we now know about long-term con­se­quences of a COVID-19 in­fec­tion?

ChristianKl15 Jul 2020 14:42 UTC
14 points
1 comment1 min readLW link

New pa­per: AGI Agent Safety by Iter­a­tively Im­prov­ing the Utility Function

Koen.Holtman15 Jul 2020 14:05 UTC
21 points
2 comments6 min readLW link

Ed­u­ca­tion 2.0 — A brand new ed­u­ca­tion system

aryan15 Jul 2020 10:09 UTC
−8 points
3 comments6 min readLW link

Clas­sifi­ca­tion of AI al­ign­ment re­search: de­con­fu­sion, “good enough” non-su­per­in­tel­li­gent AI al­ign­ment, su­per­in­tel­li­gent AI alignment

philip_b14 Jul 2020 22:48 UTC
35 points
25 comments3 min readLW link

Mazes and Duality

14 Jul 2020 19:54 UTC
62 points
10 comments6 min readLW link

The Gold­bach con­jec­ture is prob­a­bly cor­rect; so was Fer­mat’s last theorem

Stuart_Armstrong14 Jul 2020 19:30 UTC
82 points
28 comments4 min readLW link

Dremeling

Czynski14 Jul 2020 19:23 UTC
63 points
8 comments1 min readLW link

Cal­ibra­tion Prac­tice: Retro­d­ic­tions on Metaculus

Raemon14 Jul 2020 18:35 UTC
34 points
2 comments1 min readLW link

AI Benefits Post 4: Out­stand­ing Ques­tions on Select­ing Benefits

Cullen14 Jul 2020 17:26 UTC
4 points
4 comments5 min readLW link

Ra­tion­al­ity Vienna Meetup July 2020

Laszlo_Treszkai14 Jul 2020 13:06 UTC
2 points
2 comments1 min readLW link

Limits of Cur­rent US Pre­dic­tion Mar­kets (Pre­dic­tIt Case Study)

aphyer14 Jul 2020 7:24 UTC
210 points
50 comments7 min readLW link

Al­gorith­mic In­tent: A Han­so­nian Gen­er­al­ized Anti-Zom­bie Principle

Zack_M_Davis14 Jul 2020 6:03 UTC
50 points
19 comments12 min readLW link

[Question] What are the mostly likely ways AGI will emerge?

Craig Quiter14 Jul 2020 0:58 UTC
3 points
7 comments1 min readLW link

[Question] How to per­suade peo­ple/​groups out of sunk cost fal­lacy?

vernamcipher13 Jul 2020 22:51 UTC
3 points
2 comments1 min readLW link

Life Through Quan­tum An­neal­ing: How a quan­tum com­put­ing tech­nique could shape existence

ChrisM13 Jul 2020 22:48 UTC
2 points
1 comment16 min readLW link

[Question] 3-P Group op­ti­mal for dis­cus­sion?

AiresJL13 Jul 2020 22:23 UTC
3 points
0 comments1 min readLW link

Book Re­view: Fooled by Randomness

Sherrinford13 Jul 2020 21:02 UTC
33 points
10 comments5 min readLW link

Roll for Sanity

eapache13 Jul 2020 16:39 UTC
16 points
2 comments4 min readLW link

Null-box­ing New­comb’s Problem

Yitz13 Jul 2020 16:32 UTC
33 points
9 comments4 min readLW link

2020 LessWrong De­mo­graph­ics Sur­vey Results

B Jacobs13 Jul 2020 13:53 UTC
18 points
7 comments1 min readLW link

What You Are

Jarred Filmer13 Jul 2020 11:35 UTC
2 points
3 comments1 min readLW link

Up­date more slowly!

Davidmanheim13 Jul 2020 7:10 UTC
51 points
4 comments2 min readLW link

In praise of con­tribut­ing ex­am­ples, analo­gies and lingo

Adam Zerner13 Jul 2020 6:43 UTC
37 points
3 comments1 min readLW link

Six eco­nomics mis­con­cep­tions of mine which I’ve re­solved over the last few years

Buck13 Jul 2020 3:01 UTC
196 points
59 comments9 min readLW link

[Question] What is the cur­rent state of knowl­edge around COVID-19 at-home reme­dies?

Dorikka12 Jul 2020 22:50 UTC
10 points
7 comments1 min readLW link

What counts as defec­tion?

TurnTrout12 Jul 2020 22:03 UTC
81 points
21 comments5 min readLW link1 review

Pos­si­ble new pneu­mo­nia in Kazahk­stan (July 2020)

Jay12 Jul 2020 20:41 UTC
2 points
0 comments1 min readLW link

School Has It Backwards

proshowersinger12 Jul 2020 19:24 UTC
31 points
10 comments2 min readLW link

[Question] What is the cur­rent pro­cess for in­creases test­ing?

jmh12 Jul 2020 17:21 UTC
5 points
1 comment1 min readLW link

Bu­dapest meetup Mar­git Sz­iget, 7/​19 2pm

Timothy Underwood12 Jul 2020 14:07 UTC
3 points
2 comments1 min readLW link

Science eats its young

George3d612 Jul 2020 12:32 UTC
14 points
13 comments10 min readLW link
(cerebralab.com)

Gödel In­com­plete­ness: For Dummies

jollybard12 Jul 2020 9:13 UTC
9 points
6 comments3 min readLW link

Covid-19: Anal­y­sis of Mor­tal­ity Data

Zvi11 Jul 2020 21:30 UTC
32 points
12 comments12 min readLW link
(thezvi.wordpress.com)

[Question] How well can the GPT ar­chi­tec­ture solve the par­ity task?

FactorialCode11 Jul 2020 19:02 UTC
19 points
3 comments1 min readLW link

Canon­i­cal forms

sen11 Jul 2020 18:53 UTC
8 points
1 comment1 min readLW link
(www.fimfiction.net)

Lurk­ing More Be­fore Join­ing Com­plex Conversations

Raemon11 Jul 2020 17:11 UTC
42 points
11 comments3 min readLW link

Meta Pro­gram­ming GPT: A route to Su­per­in­tel­li­gence?

dmtea11 Jul 2020 14:51 UTC
10 points
7 comments4 min readLW link