Fi­nal Day to Order LW Books by Christ­mas for US

Ben Pace9 Dec 2020 23:30 UTC
13 points
3 comments1 min readLW link

Sum­mary of AI Re­search Con­sid­er­a­tions for Hu­man Ex­is­ten­tial Safety (ARCHES)

peterbarnett9 Dec 2020 23:28 UTC
11 points
0 comments13 min readLW link

Sun­day De­cem­ber 13th, 12:00PM (PT) – Puz­zle Hunt

Ruby9 Dec 2020 23:28 UTC
9 points
0 comments1 min readLW link

[Question] Where does this com­mu­nity lean poli­ti­cally ?

Madeven13359 Dec 2020 21:08 UTC
−10 points
2 comments1 min readLW link

[Question] How do we know that the things we want have cred­i­bil­ity ?

Madeven13359 Dec 2020 21:08 UTC
−10 points
1 comment1 min readLW link

Switch­ing to Google Calendar

jefftk9 Dec 2020 20:10 UTC
8 points
0 comments1 min readLW link
(www.jefftk.com)

[AN #128]: Pri­ori­tiz­ing re­search on AI ex­is­ten­tial safety based on its ap­pli­ca­tion to gov­er­nance demands

Rohin Shah9 Dec 2020 18:20 UTC
16 points
2 comments10 min readLW link
(mailchi.mp)

Notes on Know-how

David Gross9 Dec 2020 17:21 UTC
10 points
1 comment4 min readLW link

Walk to a San Fran­cisco FedEx

KatjaGrace9 Dec 2020 8:50 UTC
27 points
0 comments4 min readLW link
(worldspiritsockpuppet.com)

Luna Love­g­ood and the Cham­ber of Se­crets—Part 6

lsusr9 Dec 2020 8:14 UTC
87 points
14 comments2 min readLW link

Quick Thoughts on Im­moral Mazes

abramdemski9 Dec 2020 1:21 UTC
86 points
47 comments5 min readLW link

Chance that “AI safety ba­si­cally [doesn’t need] to be solved, we’ll just solve it by de­fault un­less we’re com­pletely com­pletely care­less”

8 Dec 2020 21:08 UTC
27 points
0 comments5 min readLW link

Ve­loc­ity-sen­si­tive elec­tronic drum pedals

jefftk8 Dec 2020 20:20 UTC
4 points
0 comments2 min readLW link
(www.jefftk.com)

Con­ser­vatism in neo­cor­tex-like AGIs

Steven Byrnes8 Dec 2020 16:37 UTC
22 points
5 comments8 min readLW link

Sig­nal­ing importance

Mati_Roy8 Dec 2020 9:14 UTC
6 points
4 comments1 min readLW link

How long does it take to be­come Gaus­sian?

Maxwell Peterson8 Dec 2020 7:23 UTC
140 points
40 comments4 min readLW link

Why are deli­cious bis­cuits ob­scure?

KatjaGrace8 Dec 2020 6:10 UTC
17 points
18 comments2 min readLW link
(meteuphoric.com)

White Sphere Hypothesis

James S. Eriee8 Dec 2020 5:56 UTC
6 points
6 comments1 min readLW link

An el­e­gant proof of Laplace’s rule of succession

Eric Neyman7 Dec 2020 22:43 UTC
33 points
7 comments8 min readLW link
(ericneyman.wordpress.com)

Please Take the 2020 Effec­tive Altru­ism Survey

Peter Wildeford7 Dec 2020 22:18 UTC
20 points
0 comments1 min readLW link

Notes on Fairness

David Gross7 Dec 2020 18:52 UTC
20 points
4 comments8 min readLW link

An­nounc­ing the Tech­ni­cal AI Safety Podcast

Quinn7 Dec 2020 18:51 UTC
42 points
6 comments2 min readLW link
(technical-ai-safety.libsyn.com)

Travers­ing a Cog­ni­tion Space

Rafael Harth7 Dec 2020 18:32 UTC
17 points
5 comments12 min readLW link

[Question] Num­ber-guess­ing pro­to­col?

abramdemski7 Dec 2020 15:07 UTC
19 points
28 comments1 min readLW link

Launch­ing the Fore­cast­ing AI Progress Tournament

Tamay7 Dec 2020 14:08 UTC
20 points
0 comments1 min readLW link
(www.metaculus.com)

[Question] Recom­men­da­tion for a good in­ter­na­tional event bet­ting site like pre­dic­tit.org

df fd7 Dec 2020 9:09 UTC
6 points
2 comments1 min readLW link

Toward A Cul­ture of Persuasion

DirectedEvolution7 Dec 2020 2:42 UTC
17 points
14 comments6 min readLW link

The In­com­pre­hen­si­bil­ity Bluff

SocratesDissatisfied6 Dec 2020 18:26 UTC
44 points
22 comments6 min readLW link

[Question] Pre-Hind­sight Prompt: Why did 2021 NOT bring a re­turn to nor­malcy?

mike_hawke6 Dec 2020 17:35 UTC
22 points
13 comments1 min readLW link

Cul­tural accumulation

KatjaGrace6 Dec 2020 6:20 UTC
93 points
53 comments3 min readLW link
(meteuphoric.com)

Values Form a Shift­ing Land­scape (and why you might care)

VojtaKovarik5 Dec 2020 23:56 UTC
28 points
6 comments4 min readLW link

D&D.Sci

abstractapplic5 Dec 2020 23:26 UTC
81 points
50 comments1 min readLW link

AI Prob­lems Shared by Non-AI Systems

VojtaKovarik5 Dec 2020 22:15 UTC
7 points
2 comments4 min readLW link

Hu­man Ge­netic Eng­ineer­ing: In­creas­ing Intelligence

GeneSmith5 Dec 2020 22:06 UTC
36 points
5 comments10 min readLW link

[Question] Fi­nance—ac­cessibil­ity (ask­ing for text­book recom­men­da­tions)

max he5 Dec 2020 21:14 UTC
3 points
8 comments1 min readLW link

[Question] AI Win­ter Is Com­ing—How to profit from it?

maximkazhenkov5 Dec 2020 20:23 UTC
15 points
7 comments1 min readLW link

[Question] How can I re­store my pre­vi­ous ac­count?

Stirling_Westrup25 Dec 2020 19:31 UTC
1 point
2 comments1 min readLW link

Anti-EMH Ev­i­dence (and a plea for help)

Wei Dai5 Dec 2020 18:29 UTC
93 points
44 comments5 min readLW link

Su­per­vised learn­ing in the brain, part 4: com­pres­sion /​ filtering

Steven Byrnes5 Dec 2020 17:06 UTC
19 points
0 comments5 min readLW link

Notes on Care

David Gross5 Dec 2020 16:33 UTC
8 points
0 comments6 min readLW link

[RXN#7] Rus­sian x-risks newslet­ter fall 2020

avturchin5 Dec 2020 16:28 UTC
12 points
0 comments3 min readLW link

The AI Safety Game (UPDATED)

Daniel Kokotajlo5 Dec 2020 10:27 UTC
45 points
10 comments3 min readLW link

Map and Ter­ri­tory: Sum­mary and Thoughts

Adam Zerner5 Dec 2020 8:21 UTC
16 points
4 comments26 min readLW link

Luna Love­g­ood and the Cham­ber of Se­crets—Part 5

lsusr5 Dec 2020 1:23 UTC
109 points
8 comments3 min readLW link

Fore­cast­ing is a responsibility

DirectedEvolution5 Dec 2020 0:40 UTC
23 points
23 comments2 min readLW link

Beyond 175 billion pa­ram­e­ters: Can we an­ti­ci­pate fu­ture GPT-X Ca­pa­bil­ities?

bakztfuture4 Dec 2020 23:42 UTC
−1 points
1 comment2 min readLW link

On­line Meetup for the Meetup Or­ga­niz­ers (Sun, 20th De­cem­ber)

Ruby4 Dec 2020 23:30 UTC
21 points
2 comments1 min readLW link

Meetup Or­ga­niz­ers, Our Vir­tual Gar­den is at Your Disposal

Ruby4 Dec 2020 23:29 UTC
59 points
10 comments2 min readLW link

The Hard Prob­lem of Magic

enaumov4 Dec 2020 18:51 UTC
1 point
6 comments1 min readLW link

Com­mit­ment and cred­i­bil­ity in mul­ti­po­lar AI scenarios

anni_leskela4 Dec 2020 18:48 UTC
31 points
3 comments18 min readLW link