Get your tick­ets to Man­i­fest 2024 by May 13th!

Saul MunnMay 3, 2024, 11:57 PM
18 points
0 commentsLW link

Embodiment

A*May 3, 2024, 8:06 PM
4 points
0 comments1 min readLW link

(Geo­met­ri­cally) Max­i­mal Lot­tery-Lot­ter­ies Exist

LorxusMay 3, 2024, 7:29 PM
13 points
11 comments26 min readLW link

[Question] Were there any an­cient ra­tio­nal­ists?

OliverHaymanMay 3, 2024, 6:26 PM
11 points
3 comments1 min readLW link

Key take­aways from our EA and al­ign­ment re­search sur­veys

May 3, 2024, 6:10 PM
112 points
10 comments21 min readLW link

“AI Safety for Fleshy Hu­mans” an AI Safety ex­plainer by Nicky Case

habrykaMay 3, 2024, 6:10 PM
90 points
11 comments4 min readLW link
(aisafety.dance)

AI Clar­ity: An Ini­tial Re­search Agenda

May 3, 2024, 1:54 PM
18 points
1 comment8 min readLW link

Ap­ply to ESPR & PAIR, Ra­tion­al­ity and AI Camps for Ages 16-21

Anna GajdovaMay 3, 2024, 12:36 PM
58 points
5 comments1 min readLW link

On pre­cise out-of-con­text steering

Olli JärviniemiMay 3, 2024, 9:41 AM
9 points
6 comments3 min readLW link

LLM+Plan­ners hy­bridi­s­a­tion for friendly AGI

installgentooMay 3, 2024, 8:40 AM
7 points
2 comments1 min readLW link

Mechanis­tic In­ter­pretabil­ity Work­shop Hap­pen­ing at ICML 2024!

May 3, 2024, 1:18 AM
48 points
6 comments1 min readLW link

Weekly newslet­ter for AI safety events and train­ing programs

Bryce RobertsonMay 3, 2024, 12:33 AM
29 points
0 comments1 min readLW link

CCS: Coun­ter­fac­tual Civ­i­liza­tion Simulation

MorphismMay 2, 2024, 10:54 PM
3 points
0 comments2 min readLW link

Let’s De­sign A School, Part 2.1 School as Ed­u­ca­tion—Structure

SableMay 2, 2024, 10:04 PM
26 points
2 comments10 min readLW link
(affablyevil.substack.com)

Why I’m not do­ing PauseAI

kwiat.devMay 2, 2024, 10:00 PM
−8 points
5 comments4 min readLW link

AI #61: Meta Trouble

ZviMay 2, 2024, 6:40 PM
29 points
0 comments52 min readLW link
(thezvi.wordpress.com)

Why is AGI/​ASI Inevitable?

DeathlessAmaranthMay 2, 2024, 6:27 PM
14 points
6 comments1 min readLW link

AISN #34: New Mili­tary AI Sys­tems Plus, AI Labs Fail to Uphold Vol­un­tary Com­mit­ments to UK AI Safety In­sti­tute, and New AI Policy Pro­pos­als in the US Senate

May 2, 2024, 4:12 PM
6 points
0 comments8 min readLW link
(newsletter.safe.ai)

Ai Salon: Trust­wor­thy AI Fu­tures #1

Ian EisenbergMay 2, 2024, 4:07 PM
1 point
0 comments1 min readLW link

How to write Pseu­docode and why you should

Johannes C. MayerMay 2, 2024, 3:53 PM
8 points
5 comments3 min readLW link

AI #62: Too Soon to Tell

ZviMay 2, 2024, 3:40 PM
30 points
8 comments31 min readLW link
(thezvi.wordpress.com)

White­board Pro­gram Tra­ce­ing: De­bug a Pro­gram Be­fore you have the Code

Johannes C. MayerMay 2, 2024, 3:30 PM
3 points
0 comments1 min readLW link

[Question] Which skin­care prod­ucts are ev­i­dence-based?

Vanessa KosoyMay 2, 2024, 3:22 PM
120 points
48 comments1 min readLW link

Q&A on Pro­posed SB 1047

ZviMay 2, 2024, 3:10 PM
74 points
8 comments44 min readLW link
(thezvi.wordpress.com)

[Question] What are the Ac­tivi­ties that make up your Re­search Pro­cess?

Johannes C. MayerMay 2, 2024, 3:01 PM
4 points
0 comments1 min readLW link

[Question] How do you Select the Right Re­search Ac­i­tivity in the Right Mo­ment?

Johannes C. MayerMay 2, 2024, 2:45 PM
6 points
1 comment1 min readLW link

[Question] Can stealth air­craft be de­tected op­ti­cally?

Yair HalberstadtMay 2, 2024, 7:47 AM
20 points
27 comments1 min readLW link

An ex­pla­na­tion of evil in an or­ga­nized world

KatjaGraceMay 2, 2024, 5:20 AM
26 points
9 comments2 min readLW link
(worldspiritsockpuppet.com)

Why I stopped work­ing on AI safety

jbkjrMay 2, 2024, 5:08 AM
−5 points
0 comments4 min readLW link
(jbkjr.me)

[Linkpost] Silver Bul­letin: For most peo­ple, poli­tics is about fit­ting in

Gunnar_ZarnckeMay 1, 2024, 6:12 PM
18 points
4 comments1 min readLW link
(www.natesilver.net)

Launch­ing ap­pli­ca­tions for AI Safety Ca­reers Course In­dia 2024

Axiom_FuturesMay 1, 2024, 5:55 PM
4 points
1 comment1 min readLW link

[Question] Shane Legg’s nec­es­sary prop­er­ties for ev­ery AGI Safety plan

jacquesthibsMay 1, 2024, 5:15 PM
58 points
12 comments1 min readLW link

KAN: Kol­mogorov-Arnold Networks

Gunnar_ZarnckeMay 1, 2024, 4:50 PM
18 points
15 comments1 min readLW link
(arxiv.org)

Man­i­fund Q1 Retro: Learn­ings from im­pact certs

Austin ChenMay 1, 2024, 4:48 PM
40 points
1 commentLW link

ACX Covid Ori­gins Post con­vinced readers

ErnestScribblerMay 1, 2024, 1:06 PM
77 points
7 comments2 min readLW link

LessWrong Com­mu­nity Week­end 2024, open for applications

May 1, 2024, 10:18 AM
79 points
2 comments7 min readLW link

Take SCIFs, it’s dan­ger­ous to go alone

May 1, 2024, 8:02 AM
42 points
1 comment3 min readLW link

AXRP Epi­sode 30 - AI Se­cu­rity with Jeffrey Ladish

DanielFilanMay 1, 2024, 2:50 AM
25 points
0 comments79 min readLW link

Neuro/​BCI/​WBE for Safe AI Workshop

Allison DuettmannMay 1, 2024, 12:46 AM
3 points
0 comments1 min readLW link

AGI: Cryp­tog­ra­phy, Se­cu­rity & Mul­tipo­lar Sce­nar­ios Workshop

Allison DuettmannMay 1, 2024, 12:42 AM
8 points
1 comment1 min readLW link

The for­mal goal is a pointer

MorphismMay 1, 2024, 12:27 AM
20 points
10 comments1 min readLW link

Arch-an­ar­chy:The­ory and practice

Peter lawless Apr 30, 2024, 11:20 PM
−6 points
0 comments2 min readLW link

“Open Source AI” is a lie, but it doesn’t have to be

jacobhaimesApr 30, 2024, 11:10 PM
19 points
5 comments6 min readLW link
(jacob-haimes.github.io)

Ques­tions for labs

Zach Stein-PerlmanApr 30, 2024, 10:15 PM
77 points
11 comments8 min readLW link

Real­ity com­pre­hen­si­bil­ity: are there illog­i­cal things in re­al­ity?

DDthinkerApr 30, 2024, 9:30 PM
−3 points
0 comments10 min readLW link

Mechanis­ti­cally Elic­it­ing La­tent Be­hav­iors in Lan­guage Models

Apr 30, 2024, 6:51 PM
210 points
43 comments45 min readLW link

[Question] What is the eas­iest/​funnest way to build up a com­pre­hen­sive un­der­stand­ing of AI and AI Safety?

Jordan ArelApr 30, 2024, 6:41 PM
4 points
2 comments1 min readLW link

Transcoders en­able fine-grained in­ter­pretable cir­cuit anal­y­sis for lan­guage models

Apr 30, 2024, 5:58 PM
74 points
14 comments17 min readLW link

An­nounc­ing the 2024 Roots of Progress Blog-Build­ing Intensive

jasoncrawfordApr 30, 2024, 5:37 PM
14 points
0 comments2 min readLW link
(rootsofprogress.org)

The In­ten­tional Stance, LLMs Edition

Eleni AngelouApr 30, 2024, 5:12 PM
30 points
3 comments8 min readLW link