[Question] When to men­tion ir­rele­vant ac­cu­sa­tions?

philhJan 14, 2023, 9:58 PM
20 points
50 comments1 min readLW link

World-Model In­ter­pretabil­ity Is All We Need

Thane RuthenisJan 14, 2023, 7:37 PM
36 points
22 comments21 min readLW link

Cur­rent AI Models Seem Suffi­cient for Low-Risk, Benefi­cial AI

harsimonyJan 14, 2023, 6:55 PM
17 points
1 comment2 min readLW link

[Question] Ba­sic Ques­tion about LLMs: how do they know what task to perform

GarakJan 14, 2023, 1:13 PM
1 point
3 comments1 min readLW link

Aligned with what?

Program DenJan 14, 2023, 10:28 AM
3 points
41 comments1 min readLW link

Wok­ism, re­think­ing pri­ori­ties and the Bostrom case

Arturo MaciasJan 14, 2023, 2:27 AM
−25 points
2 comments4 min readLW link

A gen­eral com­ment on dis­cus­sions of ge­netic group differences

anonymous8101Jan 14, 2023, 2:11 AM
71 points
46 comments3 min readLW link

Ab­strac­tions as mor­phisms be­tween (co)algebras

Erik JennerJan 14, 2023, 1:51 AM
17 points
1 comment8 min readLW link

Con­crete Rea­sons for Hope about AI

Zac Hatfield-DoddsJan 14, 2023, 1:22 AM
94 points
13 comments1 min readLW link

Nega­tive Ex­per­tise

Jonas KgomoJan 14, 2023, 12:51 AM
4 points
0 comments1 min readLW link
(twitter.com)

Mid-At­lantic AI Align­ment Alli­ance Unconference

QuinnJan 13, 2023, 8:33 PM
7 points
2 comments1 min readLW link

Smal­lpox vac­cines are widely available, for now

David HornbeinJan 13, 2023, 8:02 PM
26 points
5 comments1 min readLW link

How does GPT-3 spend its 175B pa­ram­e­ters?

Robert_AIZIJan 13, 2023, 7:21 PM
41 points
14 comments6 min readLW link
(aizi.substack.com)

[ASoT] Si­mu­la­tors show us be­havi­oural prop­er­ties by default

JozdienJan 13, 2023, 6:42 PM
36 points
3 comments3 min readLW link

Wheel of Con­sent The­ory for Ra­tion­al­ists and Effec­tive Altruists

adamwilderJan 13, 2023, 5:59 PM
1 point
0 comments2 min readLW link

Money is a way of thank­ing strangers

DirectedEvolutionJan 13, 2023, 5:06 PM
13 points
5 comments4 min readLW link

Tracr: Com­piled Trans­form­ers as a Lab­o­ra­tory for In­ter­pretabil­ity | Deep­Mind

DragonGodJan 13, 2023, 4:53 PM
62 points
12 comments1 min readLW link
(arxiv.org)

How we could stum­ble into AI catastrophe

HoldenKarnofskyJan 13, 2023, 4:20 PM
71 points
18 comments18 min readLW link
(www.cold-takes.com)

Ro­bust­ness & Evolu­tion [MLAISU W02]

Esben KranJan 13, 2023, 3:47 PM
10 points
0 comments3 min readLW link
(newsletter.apartresearch.com)

On Cook­ing With Gas

ZviJan 13, 2023, 2:20 PM
38 points
60 comments6 min readLW link
(thezvi.wordpress.com)

Be­ware safety-washing

LizkaJan 13, 2023, 1:59 PM
51 points
2 comments4 min readLW link

Some Ar­gu­ments Against Strong Scaling

Joar SkalseJan 13, 2023, 12:04 PM
25 points
21 comments16 min readLW link

[Question] Where do you find peo­ple who ac­tu­ally do things?

Ulisse MiniJan 13, 2023, 6:57 AM
7 points
12 comments1 min readLW link

[Question] Could Si­mu­lat­ing an AGI Tak­ing Over the World Ac­tu­ally Lead to a LLM Tak­ing Over the World?

simeon_cJan 13, 2023, 6:33 AM
15 points
1 comment1 min readLW link

Burn­ing Up­time: When your Sand­box of Em­pa­thy is Leaky and also an Hourglass

CedarJan 13, 2023, 5:18 AM
13 points
2 comments3 min readLW link

Disen­tan­gling Shard The­ory into Atomic Claims

Leon LangJan 13, 2023, 4:23 AM
86 points
6 comments18 min readLW link

AGISF adap­ta­tion for in-per­son groups

Jan 13, 2023, 3:24 AM
44 points
2 comments3 min readLW link

Ac­tions and Flows

Alok SinghJan 13, 2023, 3:20 AM
5 points
0 comments1 min readLW link
(alok.github.io)

A Thor­ough In­tro­duc­tion to Abstraction

RohanSJan 13, 2023, 12:30 AM
9 points
1 comment18 min readLW link

The AI Con­trol Prob­lem in a wider in­tel­lec­tual context

philosophybearJan 13, 2023, 12:28 AM
11 points
3 comments12 min readLW link

The Align­ment Problems

Martín SotoJan 12, 2023, 10:29 PM
20 points
0 comments4 min readLW link

Pro­posal for In­duc­ing Steganog­ra­phy in LMs

Logan RiggsJan 12, 2023, 10:15 PM
22 points
3 comments2 min readLW link

An­nounc­ing the 2023 PIBBSS Sum­mer Re­search Fellowship

Jan 12, 2023, 9:31 PM
32 points
0 comments1 min readLW link

Vic­to­ria Krakovna on AGI Ruin, The Sharp Left Turn and Paradigms of AI Alignment

Michaël TrazziJan 12, 2023, 5:09 PM
40 points
3 comments4 min readLW link
(www.theinsideview.ai)

[Question] What is a dis­agree­ment you have around AI safety?

tailcalledJan 12, 2023, 4:58 PM
16 points
7 comments1 min readLW link

Re­ward is not Ne­c­es­sary: How to Create a Com­po­si­tional Self-Pre­serv­ing Agent for Life-Long Learning

Roman LeventovJan 12, 2023, 4:43 PM
17 points
2 comments2 min readLW link
(arxiv.org)

ChatGPT strug­gles to re­spond to the real world

Alex FlintJan 12, 2023, 4:02 PM
31 points
9 comments24 min readLW link

Covid 1/​12/​23: Un­ex­pected Spike in Deaths

ZviJan 12, 2023, 2:30 PM
31 points
2 comments8 min readLW link
(thezvi.wordpress.com)

[Linkpost] Scal­ing Laws for Gen­er­a­tive Mixed-Mo­dal Lan­guage Models

Amal Jan 12, 2023, 2:24 PM
15 points
2 comments1 min readLW link
(arxiv.org)

ea.do­mains—Do­mains Free to a Good Home

plexJan 12, 2023, 1:32 PM
24 points
0 commentsLW link

VIRTUA: a novel about AI alignment

Karl von WendtJan 12, 2023, 9:37 AM
46 points
12 comments1 min readLW link

Iron defi­cien­cies are very bad and you should treat them

ElizabethJan 12, 2023, 9:10 AM
108 points
34 comments11 min readLW link1 review
(acesounderglass.com)

Non­stan­dard anal­y­sis in ethics

Alok SinghJan 12, 2023, 5:58 AM
−1 points
0 comments78 min readLW link
(nickbostrom.com)

Ex­am­ple of the name­less ra­tio­nal­ist virtue

Alok SinghJan 12, 2023, 5:45 AM
−9 points
2 comments1 min readLW link

FFMI Gains: A List of Vitalities

porbyJan 12, 2023, 4:48 AM
26 points
3 comments7 min readLW link

[Linkpost] Dream­erV3: A Gen­eral RL Architecture

simeon_cJan 12, 2023, 3:55 AM
23 points
3 comments1 min readLW link
(arxiv.org)

Microsoft Plans to In­vest $10B in OpenAI; $3B In­vested to Date | For­tune

DragonGodJan 12, 2023, 3:55 AM
23 points
10 comments2 min readLW link
(fortune.com)

Progress and re­search dis­rup­tive­ness

Eleni AngelouJan 12, 2023, 3:51 AM
3 points
2 comments1 min readLW link
(www.nature.com)

The Fable of the AI Coomer: Why the So­cial Prowess of Machines is AI’s Most Prox­i­mal Threat

Ace DelgadoJan 12, 2023, 1:15 AM
−10 points
4 comments4 min readLW link

Write to Think

Michael SamoilovJan 12, 2023, 12:33 AM
10 points
2 comments2 min readLW link