All20052006200720082009201020112012201320142015201620172018201920202021202220232024
AllJanFebMarAprMayJunJulAugSepOctNovDec
All123456789101112131415161718192021222324252627282930

Book Re­view: De­sign Prin­ci­ples of Biolog­i­cal Circuits

johnswentworth5 Nov 2019 6:49 UTC
209 points
24 comments12 min readLW link1 review

Chris Olah’s views on AGI safety

evhub1 Nov 2019 20:13 UTC
207 points
38 comments12 min readLW link2 reviews

Evolu­tion of Modularity

johnswentworth14 Nov 2019 6:49 UTC
174 points
12 comments2 min readLW link1 review

Gears-Level Models are Cap­i­tal Investments

johnswentworth22 Nov 2019 22:41 UTC
171 points
28 comments7 min readLW link1 review

RAISE post-mortem

null24 Nov 2019 16:19 UTC
161 points
12 comments5 min readLW link

Men­tal Mountains

Scott Alexander27 Nov 2019 5:30 UTC
144 points
14 comments15 min readLW link1 review
(slatestarcodex.com)

A mechanis­tic model of meditation

Kaj_Sotala6 Nov 2019 21:37 UTC
130 points
11 comments21 min readLW link

The Curse Of The Counterfactual

pjeby1 Nov 2019 18:34 UTC
124 points
34 comments19 min readLW link1 review

AlphaS­tar: Im­pres­sive for RL progress, not for AGI progress

orthonormal2 Nov 2019 1:50 UTC
113 points
58 comments2 min readLW link1 review

What I’ll be do­ing at MIRI

evhub12 Nov 2019 23:19 UTC
112 points
6 comments1 min readLW link

Uber Self-Driv­ing Crash

jefftk7 Nov 2019 15:00 UTC
110 points
1 comment2 min readLW link
(www.jefftk.com)

The LessWrong 2018 Review

Raemon21 Nov 2019 2:50 UTC
101 points
91 comments7 min readLW link

In­stant stone (just add wa­ter!)

jasoncrawford13 Nov 2019 22:33 UTC
99 points
27 comments4 min readLW link3 reviews
(rootsofprogress.org)

To­tal horse takeover

KatjaGrace5 Nov 2019 0:10 UTC
98 points
14 comments6 min readLW link1 review
(meteuphoric.com)

The Credit As­sign­ment Problem

abramdemski8 Nov 2019 2:50 UTC
98 points
40 comments17 min readLW link1 review

Rele­vance Norms; Or, Gricean Im­pli­ca­ture Queers the De­cou­pling/​Con­tex­tu­al­iz­ing Binary

Zack_M_Davis22 Nov 2019 6:18 UTC
94 points
30 comments3 min readLW link3 reviews

Could some­one please start a bright home light­ing com­pany?

lincolnquirk26 Nov 2019 19:20 UTC
91 points
41 comments6 min readLW link
(www.lincolnquirk.com)

But ex­actly how com­plex and frag­ile?

KatjaGrace3 Nov 2019 18:20 UTC
87 points
32 comments3 min readLW link1 review
(meteuphoric.com)

Neu­ral An­neal­ing: Toward a Neu­ral The­ory of Every­thing (cross­post)

Michael Edward Johnson29 Nov 2019 17:31 UTC
86 points
28 comments40 min readLW link3 reviews

Wrinkles

johnswentworth19 Nov 2019 22:59 UTC
81 points
14 comments4 min readLW link

Autism And In­tel­li­gence: Much More Than You Wanted To Know

Scott Alexander14 Nov 2019 5:30 UTC
76 points
12 comments7 min readLW link1 review
(slatestarcodex.com)

Matthew Walker’s “Why We Sleep” Is Rid­dled with Scien­tific and Fac­tual Errors

habryka16 Nov 2019 20:27 UTC
72 points
14 comments2 min readLW link
(guzey.com)

Self-Keep­ing Secrets

lsusr10 Nov 2019 7:59 UTC
72 points
9 comments2 min readLW link

[Team Up­date] Why we spent Q3 op­ti­miz­ing for karma

Ruby7 Nov 2019 23:39 UTC
70 points
27 comments10 min readLW link

Can you elimi­nate memetic scarcity, in­stead of fight­ing?

Raemon25 Nov 2019 2:07 UTC
69 points
11 comments4 min readLW link

The Bus Ticket The­ory of Genius

Vaniver23 Nov 2019 22:12 UTC
63 points
11 comments1 min readLW link
(www.paulgraham.com)

Ways that China is sur­pass­ing the US

Wei Dai4 Nov 2019 9:45 UTC
60 points
20 comments2 min readLW link
(palladiummag.com)

How I do research

TurnTrout19 Nov 2019 20:31 UTC
59 points
26 comments3 min readLW link

Build­ing In­tu­itions On Non-Em­piri­cal Ar­gu­ments In Science

Scott Alexander7 Nov 2019 6:50 UTC
56 points
27 comments11 min readLW link
(slatestarcodex.com)

My Anki patterns

agentydragon26 Nov 2019 6:27 UTC
55 points
17 comments5 min readLW link

3 Cul­tural In­fras­truc­ture Ideas from MAPLE

Unreal26 Nov 2019 18:56 UTC
53 points
15 comments9 min readLW link

Antimemes

lsusr26 Nov 2019 5:58 UTC
52 points
27 comments1 min readLW link

[1911.08265] Mas­ter­ing Atari, Go, Chess and Shogi by Plan­ning with a Learned Model | Arxiv

DragonGod21 Nov 2019 1:18 UTC
52 points
4 comments1 min readLW link
(arxiv.org)

The new dot com bub­ble is here: it’s called on­line advertising

Gordon Seidoh Worley18 Nov 2019 22:05 UTC
50 points
17 comments2 min readLW link
(thecorrespondent.com)

Skill and leverage

KatjaGrace3 Nov 2019 21:10 UTC
49 points
8 comments2 min readLW link
(meteuphoric.com)

[Question] How com­mon is it for one en­tity to have a 3+ year tech­nolog­i­cal lead on its near­est com­peti­tor?

Daniel Kokotajlo17 Nov 2019 15:23 UTC
49 points
20 comments1 min readLW link

AI Align­ment Re­search Overview (by Ja­cob Stein­hardt)

Ben Pace6 Nov 2019 19:24 UTC
44 points
0 comments7 min readLW link
(docs.google.com)

Speak­ing up pub­li­cly is heroic

jefftk2 Nov 2019 12:00 UTC
43 points
2 comments1 min readLW link
(www.jefftk.com)

Will trans­parency help catch de­cep­tion? Per­haps not

Matthew Barnett4 Nov 2019 20:52 UTC
43 points
5 comments7 min readLW link

[Question] What are the re­quire­ments for be­ing “citable?”

Raemon28 Nov 2019 21:24 UTC
42 points
8 comments1 min readLW link

Pie­ces of time

KatjaGrace11 Nov 2019 7:00 UTC
42 points
8 comments2 min readLW link
(meteuphoric.com)

The Power to Draw Better

Liron18 Nov 2019 3:06 UTC
39 points
7 comments2 min readLW link

[AN #75]: Solv­ing Atari and Go with learned game mod­els, and thoughts from a MIRI employee

Rohin Shah27 Nov 2019 18:10 UTC
38 points
1 comment10 min readLW link
(mailchi.mp)

[Question] His­tor­i­cal fore­cast­ing: Are there ways I can get lots of data, but only up to a cer­tain date?

Eli Tyre21 Nov 2019 17:16 UTC
38 points
10 comments1 min readLW link

Cy­ber­netic dreams: Beer’s pond brain

Yuxi_Liu19 Nov 2019 12:48 UTC
37 points
3 comments6 min readLW link

“em­bed­ded self-jus­tifi­ca­tion,” or some­thing like that

nostalgebraist3 Nov 2019 3:20 UTC
37 points
14 comments5 min readLW link
(nostalgebraist.tumblr.com)

Self polic­ing for self doubt

KatjaGrace7 Nov 2019 23:10 UTC
36 points
3 comments2 min readLW link
(meteuphoric.com)

Elon Musk is wrong: Rob­o­taxis are stupid. We need stan­dard­ized rented au­tonomous tugs to move cus­tomized owned un­pow­ered wag­ons.

chaosmage4 Nov 2019 14:04 UTC
36 points
35 comments2 min readLW link

Lazy Com­post is Worse Than Landfill

jefftk15 Nov 2019 16:20 UTC
35 points
0 comments2 min readLW link
(www.jefftk.com)

Ul­tra-sim­plified re­search agenda

Stuart_Armstrong22 Nov 2019 14:29 UTC
34 points
4 comments1 min readLW link