Ur­gent & im­por­tant: How (not) to do your to-do list

bfinnFeb 1, 2019, 5:44 PM
51 points
20 comments13 min readLW link

Who wants to be a Million­aire?

BuckyFeb 1, 2019, 2:02 PM
30 points
1 comment11 min readLW link

What is Wrong?

InyukiFeb 1, 2019, 12:02 PM
1 point
2 comments2 min readLW link

Drexler on AI Risk

PeterMcCluskeyFeb 1, 2019, 5:11 AM
35 points
10 comments9 min readLW link
(www.bayesianinvestor.com)

Boundaries—A map and ter­ri­tory ex­per­i­ment. [post-ra­tio­nal­ity]

EloFeb 1, 2019, 2:08 AM
−18 points
14 comments2 min readLW link

[Question] Why is this util­i­tar­ian calcu­lus wrong? Or is it?

EconomicModelJan 31, 2019, 11:57 PM
15 points
21 comments1 min readLW link

Small hope for less bias and more practability

ArthurLidiaJan 31, 2019, 10:09 PM
0 points
0 comments1 min readLW link

Reli­a­bil­ity am­plifi­ca­tion

paulfchristianoJan 31, 2019, 9:12 PM
24 points
3 comments7 min readLW link

Cam­bridge (UK) SSC meetup

thisheavenlyconjugationJan 31, 2019, 11:45 AM
1 point
0 comments1 min readLW link

The role of epistemic vs. aleatory un­cer­tainty in quan­tify­ing AI-Xrisk

David Scott Krueger (formerly: capybaralet)Jan 31, 2019, 6:13 AM
15 points
6 comments2 min readLW link

[Question] Ap­plied Ra­tion­al­ity pod­cast—feed­back?

Bae's TheoremJan 31, 2019, 1:46 AM
11 points
12 comments1 min readLW link

Wire­head­ing is in the eye of the beholder

Stuart_ArmstrongJan 30, 2019, 6:23 PM
26 points
10 comments1 min readLW link

Mas­culine Virtues

Jacob FalkovichJan 30, 2019, 4:03 PM
52 points
32 comments13 min readLW link

De­con­fus­ing Log­i­cal Counterfactuals

Chris_LeongJan 30, 2019, 3:13 PM
28 points
16 comments11 min readLW link

Book Tril­ogy Re­view: Re­mem­brance of Earth’s Past (The Three Body Prob­lem)

ZviJan 30, 2019, 1:10 AM
50 points
15 comments40 min readLW link
(thezvi.wordpress.com)

Align­ment Newslet­ter #43

Rohin ShahJan 29, 2019, 9:10 PM
14 points
2 comments13 min readLW link
(mailchi.mp)

The Ques­tion Of Perception

The ArkonJan 29, 2019, 8:59 PM
0 points
18 comments5 min readLW link

[Question] Which text­book would you recom­mend to learn de­ci­sion the­ory?

supermartingaleJan 29, 2019, 8:48 PM
28 points
6 comments1 min readLW link

Towards equil­ibria-break­ing methods

ryan_bJan 29, 2019, 4:19 PM
22 points
3 comments2 min readLW link

Can there be an in­de­scrib­able hel­l­world?

Stuart_ArmstrongJan 29, 2019, 3:00 PM
39 points
19 comments2 min readLW link

How much can value learn­ing be dis­en­tan­gled?

Stuart_ArmstrongJan 29, 2019, 2:17 PM
22 points
30 comments2 min readLW link

Tech­niques for op­ti­miz­ing worst-case performance

paulfchristianoJan 28, 2019, 9:29 PM
23 points
12 comments8 min readLW link

[Link] Did AlphaS­tar just click faster?

aogJan 28, 2019, 8:23 PM
4 points
14 comments1 min readLW link

“Gift­ed­ness” and Ge­nius, Cru­cial Differences

ArthurLidiaJan 28, 2019, 8:22 PM
6 points
0 comments29 min readLW link

Quan­tum Neu­ral Net and You

ScrubbyBubblesJan 28, 2019, 6:42 PM
1 point
4 comments1 min readLW link

A small ex­am­ple of one-step hypotheticals

Stuart_ArmstrongJan 28, 2019, 4:12 PM
14 points
1 comment2 min readLW link

[Question] How would one go about defin­ing the ideal per­son­al­ity com­pat­i­bil­ity test?

digitalcaffeineJan 28, 2019, 3:02 AM
1 point
4 comments1 min readLW link

Solomonoff in­duc­tion and be­lief in God

Berkeley BeetleJan 28, 2019, 3:01 AM
0 points
3 comments1 min readLW link
(randalrauser.com)

Prac­ti­cal Con­sid­er­a­tions Re­gard­ing Poli­ti­cal Polarization

joshuabeckerJan 27, 2019, 10:26 PM
2 points
0 comments1 min readLW link

“The Un­bi­ased Map”

SebastianG Jan 27, 2019, 7:08 PM
14 points
1 comment1 min readLW link

Pre­dic­tion Con­test 2018: Scores and Retrospective

jbeshirJan 27, 2019, 5:20 PM
28 points
5 comments1 min readLW link

Freely Com­ply­ing With the Ideal: A The­ory of Hap­piness

SolnassantJan 27, 2019, 12:28 PM
20 points
2 comments5 min readLW link

Con­fes­sions of an Ab­strac­tion Hater

Martin SustrikJan 27, 2019, 5:50 AM
12 points
4 comments2 min readLW link
(250bpm.com)

Río Grande: judg­ment calls

KatjaGraceJan 27, 2019, 3:50 AM
25 points
5 comments2 min readLW link
(worldlypositions.tumblr.com)

“Fore­cast­ing Trans­for­ma­tive AI: An Ex­pert Sur­vey”, Gruet­zemacher et al 2019

gwernJan 27, 2019, 2:34 AM
16 points
0 comments1 min readLW link
(arxiv.org)

Build­ing up to an In­ter­nal Fam­ily Sys­tems model

Kaj_SotalaJan 26, 2019, 12:25 PM
291 points
86 comments28 min readLW link2 reviews

Fu­ture di­rec­tions for nar­row value learning

Rohin ShahJan 26, 2019, 2:36 AM
12 points
4 comments4 min readLW link

[Question] For what do we need Su­per­in­tel­li­gent AI?

avturchinJan 25, 2019, 3:01 PM
14 points
18 comments1 min readLW link

“AlphaS­tar: Mas­ter­ing the Real-Time Strat­egy Game StarCraft II”, Deep­Mind [won 10 of 11 games against hu­man pros]

gwernJan 24, 2019, 8:49 PM
62 points
52 comments1 min readLW link
(deepmind.com)

Thoughts on re­ward en­g­ineer­ing

paulfchristianoJan 24, 2019, 8:15 PM
30 points
30 comments11 min readLW link

From Per­sonal to Pri­son Gangs: En­forc­ing Proso­cial Behavior

johnswentworthJan 24, 2019, 6:07 PM
153 points
26 comments5 min readLW link2 reviews

[Question] Is Agent Si­mu­lates Pre­dic­tor a “fair” prob­lem?

Chris_LeongJan 24, 2019, 1:18 PM
22 points
19 comments1 min readLW link

[Question] In what way has the gen­er­a­tion af­ter us “gone too far”?

EloJan 24, 2019, 10:22 AM
8 points
3 comments1 min readLW link

The hu­man side of interaction

Rohin ShahJan 24, 2019, 10:14 AM
19 points
5 comments4 min readLW link

South Bay Meetup

David FriedmanJan 24, 2019, 5:29 AM
1 point
0 commentsLW link

Allow­ing a for­mal proof sys­tem to self im­prove while avoid­ing Lo­bian ob­sta­cles.

Donald HobsonJan 23, 2019, 11:04 PM
6 points
4 comments2 min readLW link

Ra­tion­al­ity Café No. 9 - The Se­quences, Part 1; Sec­tion C b

thegreatnickJan 23, 2019, 10:41 PM
1 point
0 comments1 min readLW link

Ed­in­burgh SSC meetup ϛ

Hamish Peter ToddJan 23, 2019, 6:36 PM
1 point
0 commentsLW link

S-Curves for Trend Forecasting

Matt GoldenbergJan 23, 2019, 6:17 PM
113 points
23 comments7 min readLW link4 reviews

One-step hy­po­thet­i­cal preferences

Stuart_ArmstrongJan 23, 2019, 3:14 PM
10 points
6 comments4 min readLW link