Cri­tiquing “What failure looks like”

Grue_Slinky27 Dec 2019 23:59 UTC
35 points
6 comments3 min readLW link

More on po­lio and ran­dom­ized clini­cal trials

jasoncrawford27 Dec 2019 21:07 UTC
18 points
1 comment3 min readLW link
(rootsofprogress.org)

Vac­cine… Help? De­pro­gram­ming? Some­thing?

Golden Delicious27 Dec 2019 20:27 UTC
4 points
27 comments1 min readLW link

[Question] Ex­pected util­ity and re­peated choices

Marco Discendenti27 Dec 2019 20:26 UTC
9 points
6 comments1 min readLW link

We need to re­visit AI rewrit­ing its source code

ryan_b27 Dec 2019 18:27 UTC
11 points
5 comments1 min readLW link

Firm­ing Up Not-Ly­ing Around Its Edge-Cases Is Less Broadly Use­ful Than One Might Ini­tially Think

Zack_M_Davis27 Dec 2019 5:09 UTC
122 points
43 comments8 min readLW link2 reviews

[Question] What spiritual ex­pe­riences have you had?

Gordon Seidoh Worley27 Dec 2019 3:41 UTC
22 points
23 comments1 min readLW link

Nam­ing Rooms

jefftk27 Dec 2019 2:40 UTC
8 points
1 comment1 min readLW link
(www.jefftk.com)

Link: Does the fol­low­ing seem like a rea­son­able brief sum­mary of the key dis­agree­ments re­gard­ing AI risk?

Davidmanheim26 Dec 2019 20:14 UTC
11 points
2 comments1 min readLW link

New pa­per: (When) is Truth-tel­ling Fa­vored in AI de­bate?

VojtaKovarik26 Dec 2019 19:59 UTC
32 points
7 comments5 min readLW link
(medium.com)

[Question] Find­ing a quote: “proof by con­tra­dic­tion is the clos­est math comes to irony”

Hazard26 Dec 2019 17:40 UTC
8 points
2 comments1 min readLW link

Defin­ing “An­timeme”

lsusr26 Dec 2019 9:35 UTC
17 points
10 comments1 min readLW link

Talk­ing Through A Fear of Death

jesseduffield26 Dec 2019 5:23 UTC
6 points
0 comments6 min readLW link

Gortha Ick

jefftk26 Dec 2019 3:20 UTC
9 points
0 comments1 min readLW link
(www.jefftk.com)

[AN #78] For­mal­iz­ing power and in­stru­men­tal con­ver­gence, and the end-of-year AI safety char­ity comparison

Rohin Shah26 Dec 2019 1:10 UTC
26 points
10 comments9 min readLW link
(mailchi.mp)

Get a Life

Stanislav Kozlovski26 Dec 2019 0:51 UTC
0 points
5 comments6 min readLW link

Values As­simila­tion Premortem

wolverdude26 Dec 2019 0:30 UTC
16 points
10 comments4 min readLW link

Un­der­stand­ing Ma­chine Learn­ing (III)

Rafael Harth25 Dec 2019 18:55 UTC
16 points
2 comments11 min readLW link

12020: a fine fu­ture for these holidays

Stuart_Armstrong25 Dec 2019 15:01 UTC
38 points
6 comments1 min readLW link

Ab­solutely Win­ning Bridge Hands

jefftk25 Dec 2019 2:50 UTC
9 points
4 comments3 min readLW link
(www.jefftk.com)

Another AI Win­ter?

PeterMcCluskey25 Dec 2019 0:58 UTC
47 points
14 comments4 min readLW link
(www.bayesianinvestor.com)

Some Com­ments on “Good­hart Tax­on­omy”

Grue_Slinky24 Dec 2019 23:59 UTC
9 points
1 comment4 min readLW link

ESC Pro­cess Notes: Claim Eval­u­a­tion vs. Syntheses

Elizabeth24 Dec 2019 17:00 UTC
19 points
4 comments2 min readLW link
(acesounderglass.com)

[Question] Should I floss?

willbradshaw24 Dec 2019 16:06 UTC
24 points
11 comments3 min readLW link

Funk-tunul’s Le­gacy; Or, The Le­gend of the Ex­tor­tion War

Zack_M_Davis24 Dec 2019 9:29 UTC
13 points
6 comments4 min readLW link

What are you read­ing?

eigen24 Dec 2019 0:11 UTC
7 points
12 comments1 min readLW link

Might hu­mans not be the most in­tel­li­gent an­i­mals?

Matthew Barnett23 Dec 2019 21:50 UTC
56 points
41 comments3 min readLW link

Offset Norms

jefftk23 Dec 2019 21:30 UTC
15 points
1 comment2 min readLW link
(www.jefftk.com)

Hu­mans Are Embed­ded Agents Too

johnswentworth23 Dec 2019 19:21 UTC
81 points
19 comments5 min readLW link

[Question] Autoexperiments

Ideopunk23 Dec 2019 16:53 UTC
10 points
4 comments1 min readLW link

Yet an­other Simp­son’s Para­dox Post

NaiveTortoise23 Dec 2019 14:20 UTC
7 points
2 comments5 min readLW link
(an1lam.github.io)

Con­ver­sa­tion about whether LW Moder­a­tors should ex­press in­di­vi­d­ual opinions about mod policy − 2019/​12/​22

Ruby23 Dec 2019 3:46 UTC
17 points
12 comments1 min readLW link

Freezer Contents

jefftk23 Dec 2019 2:40 UTC
4 points
0 comments2 min readLW link
(www.jefftk.com)

[Question] Can fear of the dark bias us more gen­er­ally?

TurnTrout22 Dec 2019 22:09 UTC
21 points
1 comment1 min readLW link

[Question] De­cis­sion The­ory and Quan­tum Self-Measurement

Alan Givré22 Dec 2019 19:16 UTC
2 points
4 comments1 min readLW link

Un­der­stand­ing Ma­chine Learn­ing (II)

Rafael Harth22 Dec 2019 18:28 UTC
24 points
4 comments10 min readLW link

How to Talk About Antimemes

lsusr22 Dec 2019 11:57 UTC
20 points
13 comments1 min readLW link

The Towel Cen­sus: A Method­ol­ogy for Iden­ti­fy­ing Or­phaned Ob­jects in Your Home

mingyuan22 Dec 2019 6:04 UTC
29 points
7 comments1 min readLW link

[Question] What could a World Unifi­ca­tion In­dex track to mea­sure how unified the world is, was, and is be­com­ing?

Mati_Roy22 Dec 2019 4:56 UTC
4 points
7 comments1 min readLW link

[Question] If Antarc­tic be­came hos­pitable to hu­mans, and con­se­quently re­ceived a mass mi­gra­tion, what are likely ways the Antarc­tic le­gal sys­tem could evolve?

Mati_Roy22 Dec 2019 4:31 UTC
4 points
4 comments1 min readLW link

Pixel 3a Review

jefftk22 Dec 2019 3:00 UTC
10 points
0 comments1 min readLW link
(www.jefftk.com)

Sec­tion 7: Foun­da­tions of Ra­tional Agency

JesseClifton22 Dec 2019 2:05 UTC
14 points
4 comments8 min readLW link

Tem­plates and videos for do­ing an­nual and daily re­views

peterslattery22 Dec 2019 0:48 UTC
16 points
6 comments1 min readLW link

The Ar­rows of Time

lsusr21 Dec 2019 11:42 UTC
5 points
6 comments3 min readLW link

Old and New Saw Blades

jefftk21 Dec 2019 2:00 UTC
14 points
0 comments1 min readLW link
(www.jefftk.com)

The Coun­ter­fac­tual Pri­soner’s Dilemma

Chris_Leong21 Dec 2019 1:44 UTC
21 points
17 comments3 min readLW link

Free Speech and Triskaideka­pho­bic Calcu­la­tors: A Re­ply to Hub­inger on the Rele­vance of Public On­line Dis­cus­sion to Ex­is­ten­tial Risk

Zack_M_Davis21 Dec 2019 0:49 UTC
75 points
25 comments2 min readLW link

Quadratic vot­ing for the 2018 Review

Ben Pace20 Dec 2019 22:59 UTC
39 points
42 comments5 min readLW link

Clar­ify­ing Power-Seek­ing and In­stru­men­tal Convergence

TurnTrout20 Dec 2019 19:59 UTC
42 points
7 comments3 min readLW link

Po­lio and the con­tro­versy over ran­dom­ized clini­cal trials

jasoncrawford20 Dec 2019 19:49 UTC
18 points
3 comments2 min readLW link
(rootsofprogress.org)