[Question] What do we *re­ally* ex­pect from a well-al­igned AI?

jan betley4 Jan 2021 20:57 UTC
13 points
10 comments1 min readLW link

Utopianism

Mateusz Mazurkiewicz4 Jan 2021 18:40 UTC
1 point
1 comment2 min readLW link

Em­bar­rass­ment and Instinct

damiensnyder4 Jan 2021 18:16 UTC
6 points
1 comment3 min readLW link
(www.damiensnyder.com)

You are Dis­so­ci­at­ing (prob­a­bly)

Gordon Seidoh Worley4 Jan 2021 14:37 UTC
34 points
4 comments4 min readLW link

Open & Wel­come Thread—Jan­uary 2021

jsalvatier4 Jan 2021 7:39 UTC
21 points
45 comments1 min readLW link

Re­view: The Gio­conda Smile

KatjaGrace4 Jan 2021 7:00 UTC
8 points
3 comments4 min readLW link
(worldspiritsockpuppet.com)

The Sense-Mak­ing Web

Chris_Leong4 Jan 2021 6:17 UTC
41 points
21 comments6 min readLW link

[Question] What the ra­tio­nal de­ci­sion pro­cess for de­cid­ing for or against cry­on­ics when there’s a pos­si­bil­ity the fu­ture might be “bad”?

prolyx4 Jan 2021 5:08 UTC
1 point
1 comment2 min readLW link

Akra­sia is Hypocrisy.

Lev Protter4 Jan 2021 5:07 UTC
−10 points
2 comments1 min readLW link

Multi-di­men­sional re­wards for AGI in­ter­pretabil­ity and control

Steven Byrnes4 Jan 2021 3:08 UTC
19 points
8 comments10 min readLW link

The de­spair of nor­ma­tive re­al­ism bot

Joe Carlsmith3 Jan 2021 23:07 UTC
30 points
1 comment18 min readLW link

Notes on Attention

David Gross3 Jan 2021 21:52 UTC
32 points
2 comments17 min readLW link

Bets, Bonds, and Kindergarteners

jefftk3 Jan 2021 21:20 UTC
415 points
35 comments2 min readLW link1 review
(www.jefftk.com)

[Question] What tech­ni­cal-ish books do you recom­mend that are read­able on Kin­dle?

Rudi C3 Jan 2021 20:54 UTC
3 points
5 comments1 min readLW link

Ra­tional Ot­tawa Pre­dic­tions for 2021

eapache3 Jan 2021 20:53 UTC
7 points
0 comments1 min readLW link
(grandunifiedempty.com)

Men­tal sub­agent im­pli­ca­tions for AI Safety

moridinamael3 Jan 2021 18:59 UTC
11 points
0 comments3 min readLW link

Ret­ro­spec­tive on Teach­ing Ra­tion­al­ity Workshops

Neel Nanda3 Jan 2021 17:15 UTC
59 points
2 comments31 min readLW link

On writ­ing like a butterfly

KatjaGrace3 Jan 2021 7:30 UTC
24 points
0 comments3 min readLW link
(worldspiritsockpuppet.com)

Don’t Use Your Fa­vorite Weapon

Aaron Bergman3 Jan 2021 4:01 UTC
33 points
7 comments6 min readLW link
(aaronbergman.substack.com)

Bucket Bri­gade: Video

jefftk3 Jan 2021 2:50 UTC
10 points
8 comments1 min readLW link
(www.jefftk.com)

Are we all mis­al­igned?

Mateusz Mazurkiewicz3 Jan 2021 2:42 UTC
11 points
0 comments5 min readLW link

[Question] If the fun­da­men­tal prob­lem that eco­nomics ad­dresses is the scarcity of re­sources, then what are the ba­sic ques­tions other sub­jects at­tempt to solve?

Kaveh-Sedghi3 Jan 2021 2:36 UTC
1 point
0 comments1 min readLW link

More predictions

Tim Liptrot2 Jan 2021 15:53 UTC
8 points
0 comments1 min readLW link

Fea­ture re­quest: per­sonal notes about other users

CheerfulWarrior2 Jan 2021 14:54 UTC
23 points
14 comments1 min readLW link

Data about the new coro­n­avirus var­i­ant (B.1.1.7) from Denmark

Oskar Mathiasen2 Jan 2021 11:38 UTC
26 points
3 comments1 min readLW link

Re­view: The Div­ing Bell and the Butterfly

KatjaGrace2 Jan 2021 1:30 UTC
32 points
1 comment2 min readLW link
(worldspiritsockpuppet.com)

Over­all num­bers won’t show the English strain coming

Eric Neyman1 Jan 2021 23:00 UTC
60 points
12 comments2 min readLW link

Reflec­tions on Larks’ 2020 AI al­ign­ment liter­a­ture review

Alex Flint1 Jan 2021 22:53 UTC
79 points
7 comments6 min readLW link

Is Free Will A Myth?

Precious Oluwatobi Emmanuel1 Jan 2021 20:56 UTC
0 points
4 comments3 min readLW link

Thoughts on be­ing mortal

Joe Carlsmith1 Jan 2021 19:17 UTC
78 points
5 comments6 min readLW link

List of things I think are worth read­ing (last up­dated 3/​1/​2021)

just_browsing1 Jan 2021 17:05 UTC
3 points
2 comments4 min readLW link

Em­piri­cism in NLP : Test Oper­ate Text Exit (TOTE)

ChristianKl1 Jan 2021 16:09 UTC
11 points
10 comments3 min readLW link

Fore­cast­ing Newslet­ter: De­cem­ber 2020

NunoSempere1 Jan 2021 16:07 UTC
13 points
0 comments10 min readLW link

Luna Love­g­ood and the Cham­ber of Se­crets—Part 13

lsusr1 Jan 2021 8:01 UTC
75 points
22 comments2 min readLW link

Mis­takes to want

KatjaGrace1 Jan 2021 4:10 UTC
10 points
1 comment2 min readLW link
(worldspiritsockpuppet.com)

AI Align­ment, Philo­soph­i­cal Plu­ral­ism, and the Rele­vance of Non-Western Philosophy

xuan1 Jan 2021 0:08 UTC
30 points
21 comments20 min readLW link

A Healthy News Diet

mpr31 Dec 2020 22:19 UTC
8 points
5 comments5 min readLW link
(matthewroll.com)

Pre­dic­tions for 2021

Eric Neyman31 Dec 2020 21:12 UTC
8 points
2 comments6 min readLW link
(ericneyman.wordpress.com)

Some end-of-year me­dia recommendations

mingyuan31 Dec 2020 20:10 UTC
77 points
3 comments9 min readLW link

Luna Love­g­ood and the Cham­ber of Se­crets—Part 12

lsusr31 Dec 2020 20:02 UTC
68 points
21 comments2 min readLW link

Crowd-Fore­cast­ing Covid-19

nikos31 Dec 2020 19:30 UTC
17 points
0 comments5 min readLW link

Anti-Aging: State of the Art

JackH31 Dec 2020 19:07 UTC
371 points
176 comments11 min readLW link1 review

A Sim­plified Ver­sion of Per­spec­tive Solu­tion to the Sleep­ing Beauty Problem

dadadarren31 Dec 2020 18:27 UTC
9 points
39 comments5 min readLW link
(www.sleepingbeautyproblem.com)

[AN #131]: For­mal­iz­ing the ar­gu­ment of ig­nored at­tributes in a util­ity function

Rohin Shah31 Dec 2020 18:20 UTC
13 points
4 comments9 min readLW link
(mailchi.mp)

Covid 12/​31: Meet the New Year

Zvi31 Dec 2020 17:20 UTC
112 points
32 comments29 min readLW link
(thezvi.wordpress.com)

Do You Want the Com­plex­ity in the Tools or in Their Usage?

mxshn31 Dec 2020 10:58 UTC
7 points
5 comments2 min readLW link

2021 New Year Op­ti­miza­tion Puzzles

Scott Garrabrant31 Dec 2020 8:22 UTC
19 points
33 comments2 min readLW link

And You Take Me the Way I Am

Zack_M_Davis31 Dec 2020 5:45 UTC
13 points
5 comments1 min readLW link
(zackmdavis.net)

One Year of Pomodoros

Alex_Altair31 Dec 2020 4:42 UTC
56 points
7 comments9 min readLW link

See­ing the edge of the world

KatjaGrace31 Dec 2020 3:40 UTC
8 points
0 comments1 min readLW link
(worldspiritsockpuppet.com)