Prov­ably Safe AI: Wor­ld­view and Projects

Aug 9, 2024, 11:21 PM
54 points
44 comments7 min readLW link

All The Lat­est Hu­man tFUS Studies

sarahconstantinAug 9, 2024, 10:20 PM
46 points
2 comments8 min readLW link
(sarahconstantin.substack.com)

But Where do the Vari­ables of my Causal Model come from?

DalcyAug 9, 2024, 10:07 PM
38 points
1 comment8 min readLW link

[LDSL#2] La­tent vari­able mod­els, net­work mod­els, and lin­ear diffu­sion of sparse lognormals

tailcalledAug 9, 2024, 7:57 PM
26 points
2 comments3 min readLW link

“Which Fu­ture Mind is Me?” Is a Ques­tion of Values

dadadarrenAug 9, 2024, 6:17 PM
17 points
12 comments3 min readLW link

Si­mu­la­tion-aware causal de­ci­sion the­ory: A case for one-box­ing in CDT

kongus_bongusAug 9, 2024, 6:09 PM
15 points
11 comments2 min readLW link

The gate­keep­ers of the AI al­gorithms will shape our society

ProfessorFalkenAug 9, 2024, 5:59 PM
−5 points
3 comments1 min readLW link

[Question] Prac­ti­cal ad­vice for se­cure vir­tual com­mu­ni­ca­tion post easy AI voice-clon­ing?

hmysAug 9, 2024, 5:32 PM
6 points
5 comments2 min readLW link

The Carnot Eng­ine of Economics

StrivingForLegibilityAug 9, 2024, 3:59 PM
5 points
0 comments5 min readLW link

Ou­trage Bonding

Jonathan MoregårdAug 9, 2024, 1:46 PM
63 points
12 comments2 min readLW link
(honestliving.substack.com)

Non-Trans­ac­tional Compliments

Jonathan MoregårdAug 9, 2024, 1:42 PM
16 points
0 comments1 min readLW link
(honestliving.substack.com)

Far­mKind’s Illu­sory Offer

jefftkAug 9, 2024, 11:30 AM
71 points
5 comments3 min readLW link
(www.jefftk.com)

Altru­ism and Selfishness

Zero ContradictionsAug 9, 2024, 6:15 AM
−3 points
0 comments1 min readLW link
(thewaywardaxolotl.blogspot.com)

Michael Stream­lines on Buddhism

Chris_LeongAug 9, 2024, 4:44 AM
8 points
0 comments1 min readLW link
(x.com)

Altru­ism and Vi­tal­ism Aren’t Fel­low Travelers

Arjun PanicksseryAug 9, 2024, 2:01 AM
24 points
2 comments3 min readLW link
(arjunpanickssery.substack.com)

Car­ing only about your child may in­crease hu­man suffering

CipollaAug 8, 2024, 11:47 PM
−15 points
2 comments8 min readLW link

The Hes­sian rank bounds the learn­ing coefficient

Lucius BushnaqAug 8, 2024, 8:55 PM
68 points
10 comments4 min readLW link

GPT-4o Sys­tem Card

Zach Stein-PerlmanAug 8, 2024, 8:30 PM
68 points
11 comments2 min readLW link
(openai.com)

Par­a­sites (not a metaphor)

lemonhopeAug 8, 2024, 8:07 PM
133 points
19 comments1 min readLW link

Some Unortho­dox Ways To Achieve High GDP Growth

Aug 8, 2024, 6:58 PM
57 points
6 comments6 min readLW link

You can re­move GPT2’s Lay­erNorm by fine-tun­ing for an hour

StefanHexAug 8, 2024, 6:33 PM
165 points
11 comments8 min readLW link

Leav­ing MIRI, Seek­ing Funding

abramdemskiAug 8, 2024, 6:32 PM
264 points
19 comments2 min readLW link

[Question] Does VETLM solve AI su­per­al­ign­ment?

Oleg TrottAug 8, 2024, 6:22 PM
−1 points
10 comments1 min readLW link

Toy Models of Su­per­po­si­tion: what about BitNets?

Alejandro TlaieAug 8, 2024, 4:29 PM
5 points
1 comment5 min readLW link

[LDSL#1] Perfor­mance op­ti­miza­tion as a metaphor for life

tailcalledAug 8, 2024, 4:16 PM
31 points
6 comments5 min readLW link

Four Ran­dom­ized Con­trol Tri­als In Economics

Maxwell TabarrokAug 8, 2024, 3:59 PM
20 points
1 comment4 min readLW link
(www.maximum-progress.com)

Cheap White­boards!

Johannes C. MayerAug 8, 2024, 1:52 PM
27 points
2 comments1 min readLW link

AI #76: Six Shorts Sto­ries About OpenAI

ZviAug 8, 2024, 1:50 PM
53 points
10 comments48 min readLW link
(thezvi.wordpress.com)

[Question] What the cost differ­ence in pro­cess­ing in­put vs. out­put to­kens with LLMs?

kotrfaAug 8, 2024, 10:43 AM
3 points
10 comments1 min readLW link

Meno’s Paradox

HudjefaAug 8, 2024, 5:59 AM
0 points
10 comments1 min readLW link

Case Story: Lack of Con­sumer Pro­tec­tion Pro­ce­dures AI Ma­nipu­la­tion and the Threat of Fund Con­cen­tra­tion in Crypto Seek­ing As­sis­tance to Fund a Civil Case to Estab­lish Facts and Pro­tect Vuln­er­a­ble Con­sumers from Da­m­age Caused by Au­to­mated Sys­tems

Petr 'Margot' AndreevAug 8, 2024, 5:55 AM
−9 points
0 comments9 min readLW link

Mo­ti­va­tion Theory

Zero ContradictionsAug 8, 2024, 5:05 AM
3 points
0 comments1 min readLW link
(thewaywardaxolotl.blogspot.com)

It’s time for a self-re­pro­duc­ing machine

Carl FeynmanAug 7, 2024, 9:52 PM
96 points
69 comments9 min readLW link

[LDSL#0] Some episte­molog­i­cal conundrums

tailcalledAug 7, 2024, 7:52 PM
54 points
11 comments10 min readLW link

Help us seed AI Safety Brussels

Aug 7, 2024, 6:32 AM
3 points
2 comments3 min readLW link

Adap­tive Coherence

Zero ContradictionsAug 7, 2024, 6:17 AM
2 points
0 comments2 min readLW link
(thewaywardaxolotl.blogspot.com)

In­di­vi­d­ual Utilities Shift Con­tin­u­ously as Geo­met­ric Weights Shift

StrivingForLegibilityAug 7, 2024, 1:41 AM
2 points
0 comments17 min readLW link

Gra­di­ent As­cen­ders Reach the Harsanyi Hyperplane

StrivingForLegibilityAug 7, 2024, 1:40 AM
4 points
0 comments6 min readLW link

Deriv­ing the Geo­met­ric Utili­tar­ian Weights

StrivingForLegibilityAug 7, 2024, 1:39 AM
2 points
0 comments11 min readLW link

Prov­ing the Geo­met­ric Utili­tar­ian Theorem

StrivingForLegibilityAug 7, 2024, 1:39 AM
25 points
0 comments8 min readLW link

The Geo­met­ric Im­por­tance of Side Payments

StrivingForLegibilityAug 7, 2024, 1:38 AM
8 points
4 comments3 min readLW link

At­ten­tion-Fea­ture Tables in Gemma 2 Resi­d­ual Streams

J BostockAug 6, 2024, 10:56 PM
2 points
0 comments14 min readLW link

[Question] What are the strate­gic im­pli­ca­tions if aliens and Earth civ­i­liza­tions pro­duce similar util­ities?

Maxime RichéAug 6, 2024, 9:16 PM
4 points
1 comment1 min readLW link

WTH is Cere­brolysin, ac­tu­ally?

Aug 6, 2024, 8:40 PM
175 points
23 comments17 min readLW link

The Prag­matic Side of Cryp­to­graph­i­cally Box­ing AI

Bart JaworskiAug 6, 2024, 5:46 PM
6 points
0 comments9 min readLW link

In­fer­ence-Only De­bate Ex­per­i­ments Us­ing Math Problems

Aug 6, 2024, 5:44 PM
31 points
0 comments2 min readLW link

[Question] Is an AI re­li­gion jus­tified?

p4rziv4lAug 6, 2024, 3:42 PM
−35 points
11 comments1 min readLW link

Startup Roundup #2

ZviAug 6, 2024, 1:30 PM
45 points
0 comments32 min readLW link
(thezvi.wordpress.com)

Mechanis­tic Ano­maly De­tec­tion Re­search Update

Aug 6, 2024, 10:33 AM
11 points
0 comments1 min readLW link
(blog.eleuther.ai)

Rea­son­ing is not search—a chess example

p.b.Aug 6, 2024, 9:29 AM
4 points
3 comments2 min readLW link