Towards an em­piri­cal in­ves­ti­ga­tion of in­ner alignment

evhub23 Sep 2019 20:43 UTC
44 points
9 comments6 min readLW link

Ther­apy vs emo­tional support

squidious23 Sep 2019 19:00 UTC
15 points
2 comments4 min readLW link
(opalsandbonobos.blogspot.com)

[AN #65]: Learn­ing use­ful skills by watch­ing hu­mans “play”

Rohin Shah23 Sep 2019 17:30 UTC
11 points
0 comments9 min readLW link
(mailchi.mp)

Don’t clean your glasses

jefftk23 Sep 2019 15:20 UTC
−2 points
4 comments1 min readLW link
(www.jefftk.com)

The Inad­e­quacy of Cur­rent Science (Novum Or­ganum Book 1: 1-37)

Francis Bacon23 Sep 2019 2:53 UTC
38 points
3 comments9 min readLW link

Value Impact

TurnTrout23 Sep 2019 0:47 UTC
70 points
10 comments1 min readLW link

The Power to Teach Con­cepts Better

Liron23 Sep 2019 0:21 UTC
89 points
22 comments8 min readLW link1 review

SSC meetup 10/​12: Light­ing talks and board games

Drake Thomas22 Sep 2019 15:23 UTC
1 point
0 comments1 min readLW link

Five Minute Beans

jefftk22 Sep 2019 13:10 UTC
7 points
7 comments1 min readLW link
(www.jefftk.com)

Timer Toxicities

Zvi22 Sep 2019 12:10 UTC
39 points
4 comments15 min readLW link
(thezvi.wordpress.com)

Tax­ing in­vest­ment in­come is complicated

paulfchristiano22 Sep 2019 1:30 UTC
32 points
20 comments2 min readLW link
(sideways-view.com)

Prince­ton EA/​SSC Meeting

[Error communicating with LW2 server]21 Sep 2019 23:25 UTC
9 points
1 comment1 min readLW link

Mee­tups: Climb­ing up­hill, flow­ing down­hill, and the Un­canny Summit

Raemon21 Sep 2019 22:48 UTC
23 points
5 comments4 min readLW link

[Question] What are the differ­ences be­tween all the iter­a­tive/​re­cur­sive ap­proaches to AI al­ign­ment?

riceissa21 Sep 2019 2:09 UTC
30 points
14 comments2 min readLW link

Find­ing Cruxes

Logan Riggs20 Sep 2019 23:54 UTC
18 points
25 comments5 min readLW link

Refram­ing Impact

TurnTrout20 Sep 2019 19:03 UTC
96 points
15 comments3 min readLW link1 review

Syn­the­sis of sub­agents: exercise

Julija Kobrinovich20 Sep 2019 17:24 UTC
10 points
2 comments14 min readLW link

Every­day be­lief in diminish­ing re­turns is re­sis­tant to diminish­ing returns

aaq20 Sep 2019 13:44 UTC
10 points
3 comments1 min readLW link

The Zet­telkas­ten Method

abramdemski20 Sep 2019 13:15 UTC
216 points
90 comments42 min readLW link3 reviews

Re­la­bel­ings vs. Ex­ter­nal References

Chris_Leong20 Sep 2019 2:20 UTC
12 points
4 comments3 min readLW link

Novum Or­ganum: Preface

Francis Bacon19 Sep 2019 22:51 UTC
54 points
5 comments7 min readLW link

Novum Or­ganum: Introduction

Ruby19 Sep 2019 22:34 UTC
86 points
5 comments6 min readLW link

In­ter­view with Aella, Part I

Jacob Falkovich19 Sep 2019 14:05 UTC
13 points
2 comments16 min readLW link

Gears vs Behavior

johnswentworth19 Sep 2019 6:50 UTC
107 points
13 comments7 min readLW link1 review

SSC Mee­tups Every­where: Darm­stadt, Germany

mingyuan19 Sep 2019 0:53 UTC
5 points
0 comments1 min readLW link

Don’t de­pend on oth­ers to ask for explanations

Wei Dai18 Sep 2019 19:12 UTC
77 points
10 comments1 min readLW link

[Question] What tech­ni­cal pre­reqs would I need in or­der to un­der­stand Stu­art Arm­strong’s re­search agenda?

Vaughn Papenhausen18 Sep 2019 17:17 UTC
11 points
8 comments1 min readLW link

[Question] What are the stud­ies and liter­a­ture on the tra­di­tional medicine the­ory of hu­morism?

Rudi C18 Sep 2019 16:06 UTC
4 points
1 comment1 min readLW link

The un­ex­pected difficulty of com­par­ing AlphaS­tar to humans

Richard Korzekwa 18 Sep 2019 2:20 UTC
145 points
36 comments26 min readLW link
(aiimpacts.org)

Three Sto­ries for How AGI Comes Be­fore FAI

John_Maxwell17 Sep 2019 23:26 UTC
27 points
5 comments6 min readLW link

[Site Fea­ture] Link Previews

Raemon17 Sep 2019 23:03 UTC
33 points
14 comments1 min readLW link

False Dilem­mas w/​ exercises

Logan Riggs17 Sep 2019 22:35 UTC
15 points
9 comments5 min readLW link

PRINCIPLES OF PERCEPTION

Jason Ken17 Sep 2019 20:20 UTC
4 points
3 comments4 min readLW link

The YouTube Revolu­tion in Knowl­edge Transfer

Samo Burja17 Sep 2019 20:10 UTC
68 points
7 comments4 min readLW link
(medium.com)

Jane Street In­te­view Guide (Notes on Prob­a­bil­ity, Mar­kets, etc.)

lifelonglearner17 Sep 2019 5:28 UTC
22 points
0 comments1 min readLW link
(www.janestreet.com)

Mee­tups as In­sti­tu­tions for In­tel­lec­tual Progress

mingyuan17 Sep 2019 5:23 UTC
91 points
26 comments7 min readLW link

Modes of Petrov Day

Raemon17 Sep 2019 2:47 UTC
69 points
30 comments1 min readLW link

Bioinfohazards

Spiracular17 Sep 2019 2:41 UTC
87 points
14 comments18 min readLW link2 reviews

The Quan­tity/​Qual­ity of Re­searchers Has Dras­ti­cally In­creased Over the Centuries

Grue_Slinky17 Sep 2019 0:28 UTC
5 points
1 comment7 min readLW link

[Question] Is there an ex­ist­ing la­bel for the cat­e­gory of fal­la­cies ex­em­plified by “para­dox of tol­er­ance”?

slikts16 Sep 2019 20:33 UTC
8 points
11 comments1 min readLW link

Effec­tive Altru­ism and Every­day Decisions

jefftk16 Sep 2019 19:00 UTC
24 points
6 comments1 min readLW link
(www.jefftk.com)

A frame­work for speed reading

limerott16 Sep 2019 18:52 UTC
26 points
6 comments12 min readLW link
(limerott.com)

[AN #64]: Us­ing Deep RL and Re­ward Uncer­tainty to In­cen­tivize Prefer­ence Learning

Rohin Shah16 Sep 2019 17:10 UTC
11 points
8 comments7 min readLW link
(mailchi.mp)

The strat­egy-steal­ing assumption

paulfchristiano16 Sep 2019 15:23 UTC
86 points
53 comments12 min readLW link3 reviews

Ex­er­cises for Over­com­ing Akra­sia and Procrastination

Matt Goldenberg16 Sep 2019 11:53 UTC
27 points
6 comments1 min readLW link

Diver­gence on Ev­i­dence Due to Differ­ing Pri­ors—A Poli­ti­cal Case Study

Davidmanheim16 Sep 2019 11:01 UTC
27 points
3 comments3 min readLW link

De­ci­sion-Mak­ing for Im­pact: A Guide

Ian David Moss16 Sep 2019 5:12 UTC
2 points
0 comments9 min readLW link
(medium.com)

Real­ism and Rationality

bmgarfinkel16 Sep 2019 3:09 UTC
45 points
49 comments23 min readLW link

The Power to Be Emo­tion­ally Mature

Liron16 Sep 2019 2:41 UTC
34 points
2 comments4 min readLW link

[Question] Non-an­throp­i­cally, what makes us think hu­man-level in­tel­li­gence is pos­si­ble?

Grue_Slinky15 Sep 2019 23:30 UTC
9 points
3 comments3 min readLW link