Mo­ti­va­tion gaps: Why so much EA crit­i­cism is hos­tile and lazy

titotalApr 22, 2024, 11:49 AM
70 points
5 commentsLW link
(titotal.substack.com)

The In­ner Ring by C. S. Lewis

Saul MunnApr 24, 2024, 10:48 PM
69 points
6 comments13 min readLW link
(www.lewissociety.org)

Duct Tape security

Isaac KingApr 26, 2024, 6:57 PM
69 points
11 comments5 min readLW link

AXRP Epi­sode 27 - AI Con­trol with Buck Sh­legeris and Ryan Greenblatt

DanielFilanApr 11, 2024, 9:30 PM
69 points
10 comments107 min readLW link

Text Posts from the Kids Group: 2020

jefftkApr 13, 2024, 10:30 PM
69 points
3 comments19 min readLW link
(www.jefftk.com)

The 2nd De­mo­graphic Transition

Maxwell TabarrokApr 6, 2024, 2:10 PM
68 points
17 comments4 min readLW link
(www.maximum-progress.com)

“Frac­tal Strat­egy” work­shop report

RaemonApr 6, 2024, 9:26 PM
68 points
23 comments10 min readLW link

Ophiol­ogy (or, how the Mamba ar­chi­tec­ture works)

Apr 9, 2024, 7:31 PM
67 points
8 comments10 min readLW link

Su­per­po­si­tion is not “just” neu­ron polysemanticity

LawrenceCApr 26, 2024, 11:22 PM
66 points
4 comments13 min readLW link

Im­prov­ing Dic­tionary Learn­ing with Gated Sparse Autoencoders

Apr 25, 2024, 6:43 PM
63 points
38 comments1 min readLW link
(arxiv.org)

On Llama-3 and Dwarkesh Pa­tel’s Pod­cast with Zuckerberg

ZviApr 22, 2024, 1:10 PM
63 points
4 comments47 min readLW link
(thezvi.wordpress.com)

Mov­ing on from com­mu­nity living

VikaApr 17, 2024, 5:02 PM
63 points
7 comments3 min readLW link
(vkrakovna.wordpress.com)

[Question] What’s with all the bans re­cently?

Gerald MonroeApr 4, 2024, 6:16 AM
62 points
83 comments4 min readLW link

Trans­fer Learn­ing in Humans

niplavApr 21, 2024, 8:49 PM
61 points
1 comment13 min readLW link

This is Water by David Foster Wallace

Nathan YoungApr 24, 2024, 9:21 PM
60 points
16 comments13 min readLW link
(fs.blog)

LessOn­line Fes­ti­val Up­dates Thread

Ben PaceApr 18, 2024, 9:55 PM
59 points
26 comments1 min readLW link

“Why I Write” by Ge­orge Or­well (1946)

Arjun PanicksseryApr 25, 2024, 4:02 PM
59 points
2 comments9 min readLW link
(www.orwellfoundation.com)

Gra­di­ent Des­cent on the Hu­man Brain

Apr 1, 2024, 10:39 PM
59 points
5 comments2 min readLW link

So What’s Up With PUFAs Chem­i­cally?

J BostockApr 27, 2024, 1:32 PM
57 points
23 comments6 min readLW link

Let’s De­sign A School, Part 1

SableApr 23, 2024, 9:50 PM
56 points
5 comments11 min readLW link
(affablyevil.substack.com)

Ex­per­i­ment on re­peat­ing choices

KatjaGraceApr 19, 2024, 4:20 AM
56 points
1 comment3 min readLW link
(worldspiritsockpuppet.com)

A D&D.Sci Dodecalogue

abstractapplicApr 12, 2024, 1:10 AM
56 points
0 comments3 min readLW link

Towards a for­mal­iza­tion of the agent struc­ture problem

Alex_AltairApr 29, 2024, 8:28 PM
55 points
6 comments14 min readLW link

Spa­tial at­ten­tion as a “tell” for em­pa­thetic simu­la­tion?

Steven ByrnesApr 26, 2024, 3:10 PM
55 points
12 comments8 min readLW link

Math-to-English Cheat Sheet

nahojApr 8, 2024, 9:19 AM
54 points
5 comments6 min readLW link

[Closed] PIBBSS is hiring in a va­ri­ety of roles (al­ign­ment re­search and in­cu­ba­tion pro­gram)

Apr 9, 2024, 8:12 AM
54 points
0 comments3 min readLW link

We are headed into an ex­treme com­pute overhang

devrandomApr 26, 2024, 9:38 PM
54 points
34 comments2 min readLW link

Monthly Roundup #17: April 2024

ZviApr 15, 2024, 12:10 PM
54 points
4 comments76 min readLW link
(thezvi.wordpress.com)

LLMs seem (rel­a­tively) safe

JustisMillsApr 25, 2024, 10:13 PM
53 points
24 comments7 min readLW link
(justismills.substack.com)

So You Created a So­ciopath—New Book An­nounce­ment!

Garrett BakerApr 1, 2024, 6:02 PM
52 points
3 comments1 min readLW link

On Com­plex­ity Science

Garrett BakerApr 5, 2024, 2:24 AM
51 points
19 comments4 min readLW link

on the dol­lar-yen ex­change rate

bhauthApr 7, 2024, 4:49 AM
50 points
21 comments10 min readLW link
(www.bhauth.com)

Changes in Col­lege Admissions

ZviApr 24, 2024, 1:50 PM
50 points
11 comments39 min readLW link
(thezvi.wordpress.com)

Koan: di­v­in­ing alien datas­truc­tures from RAM activations

TsviBTApr 5, 2024, 6:04 PM
49 points
10 comments21 min readLW link

My in­tel­lec­tual jour­ney to (dis)solve the hard prob­lem of consciousness

Charbel-RaphaëlApr 6, 2024, 9:32 AM
49 points
44 comments30 min readLW link

AI #58: Star­gate AGI

ZviApr 4, 2024, 1:10 PM
49 points
9 comments60 min readLW link
(thezvi.wordpress.com)

Run evals on base mod­els too!

orthonormalApr 4, 2024, 6:43 PM
49 points
6 comments1 min readLW link

D&D.Sci: The Mad Tyrant’s Pet Tur­tles [Eval­u­a­tion and Rule­set]

abstractapplicApr 9, 2024, 2:01 PM
48 points
6 comments3 min readLW link

The Mom Test: Sum­mary and Thoughts

Adam ZernerApr 18, 2024, 3:34 AM
48 points
3 comments10 min readLW link

An In­tro­duc­tion to AI Sandbagging

Apr 26, 2024, 1:40 PM
47 points
13 comments8 min readLW link

I’m open for pro­jects (sort of)

cousin_itApr 18, 2024, 6:05 PM
46 points
13 comments1 min readLW link

LLM Eval­u­a­tors Rec­og­nize and Fa­vor Their Own Generations

Apr 17, 2024, 9:09 PM
46 points
1 comment3 min readLW link
(tiny.cc)

Ap­ply to LASR Labs: a Lon­don-based tech­ni­cal AI safety re­search programme

Apr 9, 2024, 5:34 PM
45 points
1 comment3 min readLW link

An­nounc­ing At­las Computing

miyazonoApr 11, 2024, 3:56 PM
45 points
4 comments4 min readLW link

Book re­view: Deep Utopia

PeterMcCluskeyApr 23, 2024, 7:55 PM
45 points
14 comments4 min readLW link
(bayesianinvestor.com)

Things Solenoid Narrates

Solenoid_EntityApr 12, 2024, 11:57 PM
45 points
2 comments2 min readLW link

D&D.Sci Long War: Defen­der of Data-mocracy

aphyerApr 26, 2024, 10:30 PM
44 points
20 comments4 min readLW link

ProLU: A Non­lin­ear­ity for Sparse Autoencoders

Glen TaggartApr 23, 2024, 2:09 PM
44 points
4 comments9 min readLW link

AI #60: Oh the Humanity

ZviApr 18, 2024, 2:10 PM
44 points
7 comments62 min readLW link
(thezvi.wordpress.com)

[Aspira­tion-based de­signs] 1. In­for­mal in­tro­duc­tion

28 Apr 2024 13:00 UTC
44 points
4 comments8 min readLW link