A short ‘deriva­tion’ of Watan­abe’s Free En­ergy Formula

Wuschel SchulzJan 29, 2024, 11:41 PM
13 points
6 comments7 min readLW link

How im­por­tant is AI hack­ing as LLMs ad­vance?

Artyom KarpovJan 29, 2024, 6:41 PM
1 point
0 comments6 min readLW link

LLM Psy­cho­met­rics: A Spec­u­la­tive Ap­proach to AI Safety

psklJan 29, 2024, 6:38 PM
3 points
4 comments1 min readLW link
(pascal.cc)

[Question] How to write bet­ter?

TeaTieAndHatJan 29, 2024, 5:02 PM
8 points
24 comments1 min readLW link

Pro­ces­sor clock speeds are not how fast AIs think

Ege ErdilJan 29, 2024, 2:39 PM
135 points
55 comments2 min readLW link

Nat­u­ral se­lec­tion for ingame char­ac­ter build optimisation

Kongo LandwalkerJan 29, 2024, 11:34 AM
8 points
5 comments2 min readLW link

Anal­ogy Bank for AI Safety

utilistrutilJan 29, 2024, 2:35 AM
23 points
0 comments8 min readLW link

Min­neapo­lis-St Paul ACX Ar­ti­cle Club: Med­i­ta­tion and LSD

25HourJan 29, 2024, 1:24 AM
3 points
0 comments1 min readLW link

Sim­ple dis­tri­bu­tion ap­prox­i­ma­tion: When sam­pled 100 times, can lan­guage mod­els yield 80% A and 20% B?

Jan 29, 2024, 12:24 AM
39 points
5 comments4 min readLW link

Why I take short timelines seriously

NicholasKeesJan 28, 2024, 10:27 PM
122 points
29 comments4 min readLW link

Win Friends and In­fluence Peo­ple Ch. 2: The Bombshell

gullJan 28, 2024, 9:40 PM
37 points
13 comments17 min readLW link
(www.google.com)

Riga ACX Fe­bru­ary 2024 Meetup: 2023 in Review

AnastasiaJan 28, 2024, 9:36 PM
4 points
0 comments1 min readLW link

Things You’re Allowed to Do: At the Dentist

rbinnnJan 28, 2024, 6:39 PM
39 points
16 comments1 min readLW link
(metavee.github.io)

[Question] What ex­actly did that great AI fu­ture in­volve again?

lemonhopeJan 28, 2024, 10:10 AM
9 points
27 comments1 min readLW link

Pal­world de­vel­op­ment blog post

bhauthJan 28, 2024, 5:56 AM
82 points
12 comments1 min readLW link
(note.com)

Vir­tu­ally Ra­tional—VRChat Meetup

Jan 28, 2024, 5:52 AM
25 points
3 comments1 min readLW link

[Stan­ford Daily] Table Talk

sudoJan 28, 2024, 3:15 AM
6 points
1 comment9 min readLW link
(stanforddaily.com)

AI Law-a-Thon

IknownothingJan 28, 2024, 2:30 AM
5 points
3 comments1 min readLW link

Chap­ter 1 of How to Win Friends and In­fluence People

gullJan 28, 2024, 12:32 AM
51 points
5 comments17 min readLW link
(www.google.com)

Epistemic Hell

rogersbaconJan 27, 2024, 5:13 PM
71 points
20 comments14 min readLW link

David Burns Thinks Psy­chother­apy Is a Learn­able Skill. Git Gud.

MorpheusJan 27, 2024, 1:21 PM
28 points
20 comments11 min readLW link
(podcast.clearerthinking.org)

Aligned AI is dual use technology

lcJan 27, 2024, 6:50 AM
58 points
31 comments2 min readLW link

Ques­tions I’d Want to Ask an AGI+ to Test Its Un­der­stand­ing of Ethics

sweenesmJan 26, 2024, 11:40 PM
14 points
6 comments4 min readLW link

An In­vi­ta­tion to Refrain from Down­vot­ing Posts into Net-Nega­tive Karma

MikkWJan 26, 2024, 8:13 PM
2 points
12 comments1 min readLW link

The Good Balsamic Vinegar

jennJan 26, 2024, 7:30 PM
52 points
4 comments2 min readLW link
(jenn.site)

The Per­spec­tive-based Ex­pla­na­tion to the Reflec­tive In­con­sis­tency Paradox

dadadarrenJan 26, 2024, 7:00 PM
10 points
16 comments8 min readLW link

To Boldly Code

StrivingForLegibilityJan 26, 2024, 6:25 PM
25 points
4 comments3 min readLW link

In­cor­po­rat­ing Mechanism De­sign Into De­ci­sion Theory

StrivingForLegibilityJan 26, 2024, 6:25 PM
17 points
4 comments4 min readLW link

Mak­ing ev­ery re­searcher seek grants is a bro­ken model

jasoncrawfordJan 26, 2024, 4:06 PM
159 points
41 comments4 min readLW link
(rootsofprogress.org)

Notes on Innocence

David GrossJan 26, 2024, 2:45 PM
13 points
21 comments18 min readLW link

Stacked Lap­top Monitor

jefftkJan 26, 2024, 2:10 PM
22 points
5 comments1 min readLW link
(www.jefftk.com)

Surgery Works Well Without The FDA

Maxwell TabarrokJan 26, 2024, 1:31 PM
43 points
28 comments4 min readLW link
(maximumprogress.substack.com)

[Question] Work­shop (hackathon, res­i­dence pro­gram, etc.) about for-profit AI Safety pro­jects?

Roman LeventovJan 26, 2024, 9:49 AM
21 points
5 comments1 min readLW link

Without fun­da­men­tal ad­vances, mis­al­ign­ment and catas­tro­phe are the de­fault out­comes of train­ing pow­er­ful AI

Jan 26, 2024, 7:22 AM
161 points
60 comments57 min readLW link

Ap­prox­i­mately Bayesian Rea­son­ing: Knigh­tian Uncer­tainty, Good­hart, and the Look-Else­where Effect

RogerDearnaleyJan 26, 2024, 3:58 AM
16 points
2 comments11 min readLW link

Mus­ings on Cargo Cult Consciousness

Gareth DavidsonJan 25, 2024, 11:00 PM
−13 points
11 comments17 min readLW link

RAND re­port finds no effect of cur­rent LLMs on vi­a­bil­ity of bioter­ror­ism attacks

StellaAthenaJan 25, 2024, 7:17 PM
94 points
14 comments1 min readLW link
(www.rand.org)

[Question] Bayesian Reflec­tion Prin­ci­ples and Ig­no­rance of the Future

cricketsJan 25, 2024, 7:00 PM
5 points
3 comments1 min readLW link

“Does your paradigm beget new, good, paradigms?”

RaemonJan 25, 2024, 6:23 PM
40 points
6 comments2 min readLW link

AI #48: The Talk of Davos

ZviJan 25, 2024, 4:20 PM
38 points
9 comments36 min readLW link
(thezvi.wordpress.com)

Im­port­ing a Python File by Name

jefftkJan 25, 2024, 4:00 PM
12 points
7 comments1 min readLW link
(www.jefftk.com)

[Re­post] The Copen­hagen In­ter­pre­ta­tion of Ethics

mesaoptimizerJan 25, 2024, 3:20 PM
77 points
4 comments5 min readLW link
(web.archive.org)

Nash Bar­gain­ing be­tween Subagents doesn’t solve the Shut­down Problem

A.H.Jan 25, 2024, 10:47 AM
22 points
1 comment9 min readLW link

Sta­tus-ori­ented spending

Adam ZernerJan 25, 2024, 6:46 AM
14 points
19 comments4 min readLW link

Pro­tect­ing agent boundaries

ChipmonkJan 25, 2024, 4:13 AM
11 points
6 comments2 min readLW link

[Question] Is a ran­dom box of gas pre­dictable af­ter 20 sec­onds?

Jan 24, 2024, 11:00 PM
37 points
35 comments1 min readLW link

[Question] Will quan­tum ran­dom­ness af­fect the 2028 elec­tion?

Jan 24, 2024, 10:54 PM
66 points
52 comments1 min readLW link

AISN #30: In­vest­ments in Com­pute and Mili­tary AI Plus, Ja­pan and Sin­ga­pore’s Na­tional AI Safety Institutes

Jan 24, 2024, 7:38 PM
27 points
1 comment6 min readLW link
(newsletter.safe.ai)

Krueger Lab AI Safety In­tern­ship 2024

Joey BreamJan 24, 2024, 7:17 PM
3 points
0 comments1 min readLW link

Agents that act for rea­sons: a thought experiment

Michele CampoloJan 24, 2024, 4:47 PM
3 points
0 comments3 min readLW link