Philoso­phers wrestling with evil, as a so­cial me­dia feed

David GrossJun 3, 2024, 10:25 PM
51 points
2 comments16 min readLW link

ACI#8: Value as a Func­tion of Pos­si­ble Worlds

Akira PyinyaJun 3, 2024, 9:49 PM
6 points
2 comments7 min readLW link

in defense of Linus Pauling

bhauthJun 3, 2024, 9:27 PM
49 points
8 comments2 min readLW link
(www.bhauth.com)

Find­ing the es­ti­mate of the value of a state in RL agents

Jun 3, 2024, 8:26 PM
8 points
4 comments4 min readLW link

Search­ing Magic Cards

jefftkJun 3, 2024, 5:40 PM
9 points
2 comments1 min readLW link
(www.jefftk.com)

The Stan­dard Analogy

Zack_M_DavisJun 3, 2024, 5:15 PM
125 points
28 comments12 min readLW link

[Question] How was Less On­line for you?

Gordon Seidoh WorleyJun 3, 2024, 5:10 PM
22 points
4 comments1 min readLW link

AI catas­tro­phes and rogue deployments

BuckJun 3, 2024, 5:04 PM
120 points
16 comments8 min readLW link

Com­pa­nies’ safety plans ne­glect risks from schem­ing AI

Zach Stein-PerlmanJun 3, 2024, 3:00 PM
73 points
4 comments6 min readLW link

ACX Meetup

svfritzJun 3, 2024, 1:02 PM
1 point
0 comments1 min readLW link

Com­ments on An­thropic’s Scal­ing Monosemanticity

Robert_AIZIJun 3, 2024, 12:15 PM
98 points
8 comments7 min readLW link

Poli­tics is the mind-kil­ler, but maybe we should talk about it anyway

Chris_LeongJun 3, 2024, 6:37 AM
14 points
33 comments3 min readLW link

[Question] How do you shut down an es­caped model?

quetzal_rainbowJun 2, 2024, 7:51 PM
15 points
8 comments1 min readLW link

How to Bet­ter Re­port Sparse Au­toen­coder Performance

J BostockJun 2, 2024, 7:34 PM
20 points
4 comments3 min readLW link

[Question] List of ar­gu­ments for Bayesianism

Aryeh EnglanderJun 2, 2024, 7:06 PM
9 points
3 comments1 min readLW link

Ori­gins of the Lab Mouse

Niko_McCartyJun 2, 2024, 3:40 PM
16 points
0 comments20 min readLW link
(press.asimov.com)

Why write down the ba­sics of logic if they are so ev­i­dent?

Crazy philosopherJun 2, 2024, 12:02 PM
3 points
9 comments1 min readLW link

How it All Went Down: The Puz­zle Hunt that took us way, way Less Online

A*Jun 2, 2024, 8:01 AM
135 points
5 comments5 min readLW link

Si­mu­la­tions and Altruism

FateGrinderJun 2, 2024, 2:45 AM
−7 points
2 comments25 min readLW link

Scan­ning your Brain with 100,000,000,000 wires?

Johannes C. MayerJun 1, 2024, 6:37 PM
6 points
6 comments2 min readLW link

[Question] Turn­ing la­texed notes into blog posts

Terence CoelhoJun 1, 2024, 6:03 PM
5 points
2 comments1 min readLW link

How do you know you are right when de­bat­ing? Calcu­late your AmIRight score.

MrThinkJun 1, 2024, 3:55 PM
2 points
5 comments2 min readLW link

Links for May

Kaj_SotalaJun 1, 2024, 10:20 AM
20 points
16 comments18 min readLW link
(kajsotala.fi)

[Question] What do co­her­ence ar­gu­ments ac­tu­ally prove about agen­tic be­hav­ior?

sunwillriseJun 1, 2024, 9:37 AM
123 points
39 comments6 min readLW link

AI Safety: A Climb To Ar­maged­don?

kmenouJun 1, 2024, 6:02 AM
8 points
3 comments1 min readLW link
(arxiv.org)

When does ex­ter­nal be­havi­our im­ply in­teral struc­ture?

Tyler TracyMay 31, 2024, 4:41 PM
6 points
5 comments7 min readLW link

[Question] We might be drop­ping the ball on Au­tonomous Repli­ca­tion and Adap­ta­tion.

May 31, 2024, 1:49 PM
63 points
30 comments4 min readLW link

Tax Cuts and Innovation

Maxwell TabarrokMay 31, 2024, 12:58 PM
3 points
0 comments6 min readLW link
(www.maximum-progress.com)

The Gem­ini 1.5 Report

ZviMay 31, 2024, 12:20 PM
18 points
0 comments17 min readLW link
(thezvi.wordpress.com)

Less Anti-Dakka

Mateusz BagińskiMay 31, 2024, 9:07 AM
24 points
5 comments3 min readLW link

Web-sur­fing tips for strange times

eukaryoteMay 31, 2024, 7:10 AM
48 points
19 comments9 min readLW link
(eukaryotewritesblog.substack.com)

There Should Be More Align­ment-Driven Startups

May 31, 2024, 2:05 AM
62 points
14 comments11 min readLW link

[Question] How likely is it that AI will tor­ture us un­til the end of time?

DamiloMay 31, 2024, 1:26 AM
4 points
24 comments2 min readLW link

Twin Peaks: un­der the air

KatjaGraceMay 31, 2024, 1:20 AM
25 points
2 comments2 min readLW link
(worldspiritsockpuppet.com)

Is suffer­ing like shit?

KatjaGraceMay 31, 2024, 1:20 AM
32 points
5 comments1 min readLW link
(worldspiritsockpuppet.com)

Fore­sight Vi­sion Week­end Europe 2024

Allison DuettmannMay 31, 2024, 12:07 AM
3 points
0 comments1 min readLW link

[Question] How have analo­gous In­dus­tries solved In­ter­ested > Trained > Em­ployed bot­tle­necks?

yanni kyriacosMay 30, 2024, 11:59 PM
4 points
1 comment1 min readLW link

Duck­bill Masks Bet­ter?

jefftkMay 30, 2024, 11:40 PM
20 points
3 comments1 min readLW link
(www.jefftk.com)

OpenAI: He­len Toner Speaks

ZviMay 30, 2024, 9:10 PM
86 points
8 comments13 min readLW link
(thezvi.wordpress.com)

Non-Dis­par­age­ment Ca­naries for OpenAI

May 30, 2024, 7:20 PM
288 points
51 comments2 min readLW link

Clar­ify­ing METR’s Au­dit­ing Role

Beth BarnesMay 30, 2024, 6:41 PM
108 points
1 comment2 min readLW link

A civ­i­liza­tion ran by amateurs

Olli JärviniemiMay 30, 2024, 5:57 PM
61 points
8 comments6 min readLW link

One week left to ap­ply for the Roots of Progress Blog-Build­ing Intensive

jasoncrawfordMay 30, 2024, 4:55 PM
8 points
0 comments3 min readLW link
(rootsofprogress.org)

Get­ting started with AI Align­ment re­search: how to re­pro­duce an ex­per­i­ment from re­search paper

Alexander230May 30, 2024, 2:51 PM
3 points
0 comments3 min readLW link

AI #66: Oh to Be Less Online

ZviMay 30, 2024, 2:20 PM
37 points
6 comments56 min readLW link
(thezvi.wordpress.com)

The 27 papers

WitheringWeightsMay 30, 2024, 8:46 AM
18 points
2 comments1 min readLW link

The Mar­ket Sin­gu­lar­ity: A New Perspective

azsantoskMay 30, 2024, 7:05 AM
1 point
0 comments15 min readLW link

Awakening

lsusrMay 30, 2024, 7:03 AM
124 points
79 comments9 min readLW link

Value Claims (In Par­tic­u­lar) Are Usu­ally Bullshit

johnswentworthMay 30, 2024, 6:26 AM
144 points
18 comments2 min readLW link

The Pearly Gates

lsusrMay 30, 2024, 4:01 AM
127 points
6 comments3 min readLW link