Links and brief mus­ings for June

Kaj_SotalaJul 6, 2024, 10:10 AM
26 points
0 comments10 min readLW link
(kajsotala.fi)

In­de­ci­sion and in­ter­nal­ized au­thor­ity figures

Kaj_SotalaJul 6, 2024, 10:10 AM
69 points
1 comment2 min readLW link
(kajsotala.fi)

Free Will, Deter­minism, And Choice

Zero ContradictionsJul 6, 2024, 6:34 AM
7 points
3 comments1 min readLW link
(thewaywardaxolotl.blogspot.com)

Travel Buffer

jefftkJul 6, 2024, 2:20 AM
17 points
3 comments1 min readLW link
(www.jefftk.com)

[Question] What progress have we made on au­to­mated au­dit­ing?

LawrenceCJul 6, 2024, 1:49 AM
38 points
1 comment1 min readLW link

A “Bit­ter Les­son” Ap­proach to Align­ing AGI and ASI

RogerDearnaleyJul 6, 2024, 1:23 AM
64 points
41 comments24 min readLW link

D&D.Sci: Whom Shall You Call?

abstractapplicJul 5, 2024, 8:53 PM
40 points
6 comments2 min readLW link

[In­terim re­search re­port] Ac­ti­va­tion plateaus & sen­si­tive di­rec­tions in GPT2

Jul 5, 2024, 5:05 PM
65 points
2 comments5 min readLW link

Min­i­mal­ist And Max­i­mal­ist Type Systems

adamShimiJul 5, 2024, 4:25 PM
17 points
6 comments3 min readLW link
(epistemologicalfascinations.substack.com)

ML4Good Sum­mer Boot­camps—Ap­pli­ca­tions Open [dead­line ex­tended]

YMJul 5, 2024, 1:59 PM
12 points
0 comments1 min readLW link

[Question] Are there any plans to launch a pa­per­back ver­sion of “Ra­tion­al­ity: From AI to Zom­bies”?

m_arjJul 5, 2024, 11:14 AM
2 points
1 comment1 min readLW link

Dooms­day Ar­gu­ment and the False Dilemma of An­thropic Reasoning

Ape in the coatJul 5, 2024, 5:38 AM
48 points
61 comments7 min readLW link

Find­ing the Wis­dom to Build Safe AI

Gordon Seidoh WorleyJul 4, 2024, 7:04 PM
36 points
10 comments9 min readLW link

Libs vs Frame­works, Mid­dle-Level Reg­u­lar­i­ties vs Theories

adamShimiJul 4, 2024, 7:01 PM
23 points
0 comments2 min readLW link
(epistemologicalfascinations.substack.com)

The Po­ten­tial Im­pos­si­bil­ity of Sub­jec­tive Death

VictorLJZJul 4, 2024, 6:17 PM
3 points
35 comments1 min readLW link

Con­sider the hum­ble rock (or: why the dumb thing kills you)

pleiotrothJul 4, 2024, 1:54 PM
62 points
11 comments4 min readLW link

AI #71: Farewell to Chevron

ZviJul 4, 2024, 1:40 PM
53 points
9 comments36 min readLW link
(thezvi.wordpress.com)

The Dumb­ifi­ca­tion of our smart screens

Itay DreyfusJul 4, 2024, 6:32 AM
18 points
0 comments5 min readLW link
(productidentity.co)

In­tro­duc­tion to French AI Policy

Lucie PhilipponJul 4, 2024, 3:39 AM
111 points
12 comments6 min readLW link

How pre­dic­tive pro­cess­ing solved my wrist pain

max_shenJul 4, 2024, 1:56 AM
36 points
8 comments8 min readLW link

80,000 hours should re­move OpenAI from the Job Board (and similar EA orgs should do similarly)

RaemonJul 3, 2024, 8:34 PM
274 points
71 comments3 min readLW link

Notes on Tun­ing Metacognition

JoNeedsSleepJul 3, 2024, 7:54 PM
9 points
0 comments5 min readLW link

When Are Re­sults from Com­pu­ta­tional Com­plex­ity Not Too Coarse?

DalcyJul 3, 2024, 7:06 PM
41 points
8 comments3 min readLW link

Mus­ings on LLM Scale (Jul 2024)

Vladimir_NesovJul 3, 2024, 6:35 PM
34 points
0 comments3 min readLW link

Static Anal­y­sis As A Lifestyle

adamShimiJul 3, 2024, 6:29 PM
65 points
11 comments3 min readLW link
(epistemologicalfascinations.substack.com)

AI de­vel­op­ment is an act of so­cial revolution

artemiocobbJul 3, 2024, 6:00 PM
3 points
0 comments3 min readLW link

[Question] What per­cent of the sun would a Dyson Sphere cover?

RaemonJul 3, 2024, 5:27 PM
24 points
26 comments1 min readLW link

[Question] Iso­mor­phisms don’t pre­serve sub­jec­tive ex­pe­rience… right?

Terence CoelhoJul 3, 2024, 2:22 PM
5 points
26 comments1 min readLW link

3C’s: A Recipe For Mathing Concepts

Jul 3, 2024, 1:06 AM
81 points
5 comments7 min readLW link

An­nounc­ing the AI Fore­cast­ing Bench­mark Series | July 8, $120k in Prizes

ChristianWilliamsJul 2, 2024, 10:33 PM
15 points
0 comments5 min readLW link
(www.metaculus.com)

Open Sourc­ing Metaculus

ChristianWilliamsJul 2, 2024, 10:30 PM
44 points
0 comments2 min readLW link
(www.metaculus.com)

[Question] Why Can’t Sub-AGI Solve AI Align­ment? Or: Why Would Sub-AGI AI Not be Aligned?

MrThinkJul 2, 2024, 8:13 PM
4 points
23 comments1 min readLW link

[Question] Why haven’t there been as­sas­si­na­tion at­tempts against high pro­file AI ac­cel­er­a­tionists like sam alt­man yet?

louisTremJul 2, 2024, 6:16 PM
−13 points
4 comments2 min readLW link

How ARENA course ma­te­rial gets made

CallumMcDougallJul 2, 2024, 6:04 PM
41 points
2 comments7 min readLW link

An AI Race With China Can Be Bet­ter Than Not Racing

niplavJul 2, 2024, 5:57 PM
69 points
36 comments11 min readLW link

List of Col­lec­tive In­tel­li­gence Projects

Chris LakinJul 2, 2024, 2:10 PM
42 points
9 comments2 min readLW link
(chrislakin.blog)

De­com­pos­ing the QK cir­cuit with Bilin­ear Sparse Dic­tionary Learning

Jul 2, 2024, 1:17 PM
86 points
7 comments12 min readLW link

Eco­nomics Roundup #2

ZviJul 2, 2024, 12:40 PM
35 points
5 comments23 min readLW link
(thezvi.wordpress.com)

How Con­gres­sional Offices Pro­cess Con­stituent Communication

Tristan WilliamsJul 2, 2024, 12:38 PM
24 points
0 comments6 min readLW link

Othel­loGPT learned a bag of heuristics

Jul 2, 2024, 9:12 AM
111 points
10 comments9 min readLW link

Blueprint for a Brighter Fu­ture

Alex BeymanJul 2, 2024, 6:15 AM
−1 points
0 comments5 min readLW link

Covert Mal­i­cious Finetuning

Jul 2, 2024, 2:41 AM
90 points
4 comments3 min readLW link

In­ter­pret­ing Prefer­ence Models w/​ Sparse Autoencoders

Jul 1, 2024, 9:35 PM
75 points
12 comments9 min readLW link

Hon­est sci­ence is spirituality

pchvykovJul 1, 2024, 8:33 PM
−1 points
10 comments4 min readLW link

New Ex­ec­u­tive Team & Board — PIBBSS

Nora_AmmannJul 1, 2024, 7:30 PM
43 points
1 comment1 min readLW link

Un­curs­ing Civilization

LorecJul 1, 2024, 6:44 PM
−5 points
2 comments5 min readLW link

[Question] Self-cen­sor­ing on AI x-risk dis­cus­sions?

DecaeneusJul 1, 2024, 6:24 PM
17 points
2 comments1 min readLW link

Ra­tion­al­ists As Peo­ple Who Build Piles Of Rocks

SableJul 1, 2024, 10:32 AM
9 points
0 comments5 min readLW link
(affablyevil.substack.com)

How good are LLMs at do­ing ML on an un­known dataset?

Håvard Tveit IhleJul 1, 2024, 9:04 AM
33 points
4 comments13 min readLW link

Whirlwind Tour of Chain of Thought Liter­a­ture Rele­vant to Au­tomat­ing Align­ment Re­search.

sevdeawesomeJul 1, 2024, 5:50 AM
25 points
0 comments17 min readLW link