15 Nov 2018 19:49 UTC

201 points

17 comments54 min readLW link

Switching hosting providers today, there probably will be some hiccups

habryka15 Nov 2018 19:45 UTC

12 points

0 comments1 min readLW link

Clarifying “AI Alignment”

paulfchristiano15 Nov 2018 14:41 UTC

66 points

84 comments3 min readLW link 2 reviews

The Inspection Paradox is Everywhere

Chris_Leong15 Nov 2018 10:55 UTC

24 points

3 comments1 min readLW link

(allendowney.blogspot.com)

SSC Atlanta Meetup Number 3

Steve French15 Nov 2018 5:19 UTC

2 points

0 comments1 min readLW link

Explore/Exploit for Conversations

Hazard15 Nov 2018 4:11 UTC

38 points

2 comments5 min readLW link

Washington, DC LW Meetup

rusalkii15 Nov 2018 2:13 UTC

1 point

0 comments1 min readLW link

Stoicism: Cautionary Advice

VivaLaPanda14 Nov 2018 23:18 UTC

40 points

17 comments3 min readLW link

Mandatory Obsessions

Jacob Falkovich14 Nov 2018 18:19 UTC

77 points

14 comments6 min readLW link

Pub meetup: Developmental Milestones

Giles14 Nov 2018 4:18 UTC

6 points

0 comments1 min readLW link

Deck Guide: Burning Drakes

Zvi13 Nov 2018 19:40 UTC

8 points

0 comments12 min readLW link

(thezvi.wordpress.com)

Acknowledging Human Preference Types to Support Value Learning

Nandi13 Nov 2018 18:57 UTC

34 points

4 comments9 min readLW link

The Steering Problem

paulfchristiano13 Nov 2018 17:14 UTC

43 points

12 comments7 min readLW link

Post-Rationality and Rationality, A Dialogue

agilecaveman13 Nov 2018 5:55 UTC

2 points

2 comments10 min readLW link

Laughing Away the Little Miseries

Rossin13 Nov 2018 3:31 UTC

11 points

7 comments2 min readLW link

Kelly bettors

DanielFilan13 Nov 2018 0:40 UTC

24 points

3 comments10 min readLW link

(danielfilan.com)

Wireheading as a Possible Contributor to Civilizational Decline

avturchin12 Nov 2018 20:33 UTC

3 points

6 comments1 min readLW link

(forum.effectivealtruism.org)

Alignment Newsletter #32

Rohin Shah12 Nov 2018 17:20 UTC

18 points

0 comments12 min readLW link

(mailchi.mp)

AI development incentive gradients are not uniformly terrible

rk12 Nov 2018 16:27 UTC

21 points

12 comments6 min readLW link

What is being?

Andrew Bindon12 Nov 2018 15:33 UTC

−14 points

20 comments7 min readLW link

Aligned AI, The Scientist

Shmi12 Nov 2018 6:36 UTC

12 points

2 comments1 min readLW link

Combat vs Nurture: Cultural Genesis

Ruby12 Nov 2018 2:11 UTC

35 points

12 comments6 min readLW link

Rationality Is Not Systematized Winning

namespace11 Nov 2018 22:05 UTC

36 points

20 comments1 min readLW link

(www.thelastrationalist.com)

“She Wanted It”

sarahconstantin11 Nov 2018 22:00 UTC

120 points

21 comments7 min readLW link

(srconstantin.wordpress.com)

Future directions for ambitious value learning

Rohin Shah11 Nov 2018 15:53 UTC

48 points

9 comments4 min readLW link

Reconciling Left and Right, from the Bottom-Up

jesseduffield11 Nov 2018 8:36 UTC

14 points

2 comments15 min readLW link

Competitive Markets as Distributed Backprop

johnswentworth10 Nov 2018 16:47 UTC

59 points

10 comments4 min readLW link 1 review

Productivity: Instrumental Rationality

frdk66610 Nov 2018 14:58 UTC

6 points

7 comments1 min readLW link

Preface to the sequence on iterated amplification

paulfchristiano10 Nov 2018 13:24 UTC

44 points

8 comments3 min readLW link

Specification gaming examples in AI

Samuel Rødal10 Nov 2018 12:00 UTC

24 points

6 comments1 min readLW link

(docs.google.com)

Real-time hiring with prediction markets

ryan_b9 Nov 2018 22:10 UTC

17 points

9 comments1 min readLW link

Current AI Safety Roles for Software Engineers

ozziegooen9 Nov 2018 20:57 UTC

70 points

9 comments4 min readLW link

Model Mis-specification and Inverse Reinforcement Learning

Owain_Evans and jsteinhardt

9 Nov 2018 15:33 UTC

34 points

3 comments16 min readLW link

Open AI: Can we rule out near-term AGI?

ShardPhoenix9 Nov 2018 12:16 UTC

13 points

1 comment1 min readLW link

(www.youtube.com)

Prediction-Augmented Evaluation Systems

ozziegooen9 Nov 2018 10:55 UTC

44 points

12 comments8 min readLW link

Update the best textbooks on every subject list

ryan_b8 Nov 2018 20:54 UTC

92 points

14 comments1 min readLW link

Multi-Agent Overoptimization, and Embedded Agent World Models

Davidmanheim8 Nov 2018 20:33 UTC

8 points

3 comments3 min readLW link

Help Me Refactor Myself I am Lost

Pausecafe8 Nov 2018 20:18 UTC

12 points

20 comments2 min readLW link

Embedded Curiosities

Scott Garrabrant and abramdemski

8 Nov 2018 14:19 UTC

91 points

1 comment2 min readLW link

On first looking into Russell’s History

Richard_Ngo8 Nov 2018 11:20 UTC

23 points

6 comments5 min readLW link

(thinkingcomplete.blogspot.com)

Is Copenhagen or Many Worlds true? An experiment. What? Yes.

Jonathanm8 Nov 2018 10:10 UTC

11 points

3 comments1 min readLW link

(arxiv.org)

The new Effective Altruism forum just launched

habryka8 Nov 2018 1:59 UTC

27 points

6 comments1 min readLW link

What are Universal Inductors, Again?

Diffractor7 Nov 2018 22:32 UTC

14 points

0 comments7 min readLW link

Burnout: What it is and how to Treat it.

Elizabeth7 Nov 2018 22:02 UTC

50 points

0 comments1 min readLW link

(forum.effectivealtruism.org)

Bayes Questions

Bucky7 Nov 2018 16:54 UTC

21 points

13 comments2 min readLW link

Latent Variables and Model Mis-Specification

jsteinhardt7 Nov 2018 14:48 UTC

24 points

8 comments9 min readLW link

Paris SSC Meetup

fbreton7 Nov 2018 10:04 UTC

1 point

0 comments1 min readLW link

Reframing a Crush: Distilling the “like” out of “like like”

squidious7 Nov 2018 2:50 UTC

6 points

0 comments3 min readLW link

(opalsandbonobos.blogspot.com)

Rationality of demonstrating & voting

bfinn7 Nov 2018 0:09 UTC

24 points

21 comments8 min readLW link

Triangle SSC Meetup

willbobaggins6 Nov 2018 22:43 UTC

1 point

0 comments1 min readLW link