1 Sep 2022 5:06 UTC

62 points

10 comments1 min readLW link

Strategy For Conditioning Generative Models

james.lucassen and evhub

1 Sep 2022 4:34 UTC

31 points

4 comments18 min readLW link

Safety Committee Resources

jefftk1 Sep 2022 2:30 UTC

22 points

2 comments1 min readLW link

(www.jefftk.com)

Progress links and tweets, 2022-08-31

jasoncrawford31 Aug 2022 21:54 UTC

13 points

4 comments1 min readLW link

(rootsofprogress.org)

Enantiodromia

ChristianKl31 Aug 2022 21:13 UTC

38 points

7 comments3 min readLW link

[Question] Supposing Europe is headed for a serious energy crisis this winter, what can/should one do as an individual to prepare?

Erich_Grunewald31 Aug 2022 19:28 UTC

18 points

13 comments1 min readLW link

New 80,000 Hours problem profile on existential risks from AI

Benjamin Hilton31 Aug 2022 17:36 UTC

28 points

6 comments7 min readLW link

(80000hours.org)

Grand Theft Education

Zvi31 Aug 2022 11:50 UTC

66 points

18 comments20 min readLW link

(thezvi.wordpress.com)

How much impact can any one man have?

GregorDeVillain31 Aug 2022 10:26 UTC

9 points

3 comments4 min readLW link

[Question] How might we make better use of AI capabilities research for alignment purposes?

Jemal Young31 Aug 2022 4:19 UTC

11 points

4 comments1 min readLW link

[Question] AI Box Experiment: Are people still interested?

Double31 Aug 2022 3:04 UTC

30 points

13 comments1 min readLW link

OC ACX/LW in Newport Beach

Michael Michalchik31 Aug 2022 2:56 UTC

1 point

1 comment1 min readLW link

Survey of NLP Researchers: NLP is contributing to AGI progress; major catastrophe plausible

Sam Bowman31 Aug 2022 1:39 UTC

91 points

6 comments2 min readLW link

And the word was “God”

pchvykov30 Aug 2022 21:13 UTC

−22 points

4 comments3 min readLW link

Worlds Where Iterative Design Fails

johnswentworth30 Aug 2022 20:48 UTC

209 points

30 comments10 min readLW link 1 review

Inner Alignment via Superpowers

JamesH, Thomas Larsen and Jeremy Gillen

30 Aug 2022 20:01 UTC

37 points

13 comments4 min readLW link

ML Model Attribution Challenge [Linkpost]

aog30 Aug 2022 19:34 UTC

11 points

0 comments1 min readLW link

(mlmac.io)

How likely is deceptive alignment?

evhub30 Aug 2022 19:34 UTC

105 points

28 comments60 min readLW link

Built-In Bundling For Faster Loading

jefftk30 Aug 2022 19:20 UTC

15 points

0 comments2 min readLW link

(www.jefftk.com)

[Question] A bayesian updating on expert opinions

amarai30 Aug 2022 11:56 UTC

1 point

1 comment1 min readLW link

Any Utilitarianism Makes Sense As Policy

George3d630 Aug 2022 9:55 UTC

6 points

6 comments7 min readLW link

(www.epistem.ink)

A gentle primer on caring, including in strange senses, with applications

Kaarel30 Aug 2022 8:05 UTC

10 points

4 comments18 min readLW link

Modified Guess Culture

konstell30 Aug 2022 2:30 UTC

5 points

5 comments1 min readLW link

(konstell.com)

[Question] What is the best critique of AI existential risk arguments?

joshc30 Aug 2022 2:18 UTC

6 points

11 comments1 min readLW link

How to plan for a radically uncertain future?

Kerry30 Aug 2022 2:14 UTC

57 points

35 comments1 min readLW link

EA & LW Forums Weekly Summary (21 Aug − 27 Aug 22′)

Zoe Williams30 Aug 2022 1:42 UTC

57 points

4 comments12 min readLW link

Can We Align a Self-Improving AGI?

Peter S. Park30 Aug 2022 0:14 UTC

8 points

5 comments11 min readLW link

On the nature of help—a framework for helping

Faustify29 Aug 2022 20:42 UTC

3 points

2 comments13 min readLW link

Fundamental Uncertainty: Chapter 4 - Why don’t we do what we think we should?

Gordon Seidoh Worley29 Aug 2022 19:25 UTC

15 points

6 comments13 min readLW link

[Question] How can I reconcile the two most likely requirements for humanities near-term survival.

Erlja Jkdf.29 Aug 2022 18:46 UTC

1 point

6 comments1 min readLW link

New Canada AI Safety & Governance community

Wyatt Tessari L'Allié29 Aug 2022 18:45 UTC

21 points

0 comments1 min readLW link

Are Generative World Models a Mesa-Optimization Risk?

Thane Ruthenis29 Aug 2022 18:37 UTC

14 points

2 comments3 min readLW link

Sequencing Intro

jefftk29 Aug 2022 17:50 UTC

39 points

3 comments5 min readLW link

(www.jefftk.com)

How Do AI Timelines Affect Existential Risk?

Stephen McAleese29 Aug 2022 16:57 UTC

7 points

9 comments23 min readLW link

How might we align transformative AI if it’s developed very soon?

HoldenKarnofsky29 Aug 2022 15:42 UTC

140 points

55 comments45 min readLW link 1 review

An Audio Introduction to Nick Bostrom

PeterH29 Aug 2022 8:50 UTC

12 points

0 comments1 min readLW link

(forum.effectivealtruism.org)

Please Do Fight the Hypothetical

Lone Pine29 Aug 2022 8:35 UTC

18 points

6 comments3 min readLW link

Have you considered getting rid of death?

Willa29 Aug 2022 1:31 UTC

20 points

19 comments1 min readLW link

(immortalityisgreat.substack.com)

(My understanding of) What Everyone in Technical Alignment is Doing and Why

Thomas Larsen and elifland

29 Aug 2022 1:23 UTC

413 points

90 comments37 min readLW link 1 review

Breaking down the training/deployment dichotomy

Erik Jenner28 Aug 2022 21:45 UTC

30 points

3 comments3 min readLW link

More Clothes Over Time?

jefftk28 Aug 2022 20:30 UTC

30 points

1 comment1 min readLW link

(www.jefftk.com)

The Expanding Moral Cinematic Universe

Raemon28 Aug 2022 18:42 UTC

67 points

9 comments14 min readLW link

An Introduction to Current Theories of Consciousness

hohenheim28 Aug 2022 17:55 UTC

60 points

43 comments49 min readLW link

[Linkpost] Can lab-grown brains become conscious?

Jack R28 Aug 2022 17:45 UTC

14 points

3 comments1 min readLW link

Robert Long On Why Artificial Sentience Might Matter

Michaël Trazzi28 Aug 2022 17:30 UTC

29 points

5 comments5 min readLW link

(theinsideview.ai)

Artificial Moral Advisors: A New Perspective from Moral Psychology

David Gross28 Aug 2022 16:37 UTC

25 points

1 comment1 min readLW link

(dl.acm.org)

Pronunciations

Solenoid_Entity28 Aug 2022 11:43 UTC

15 points

7 comments2 min readLW link

First thing AI will do when it takes over is get fission going

visiax28 Aug 2022 5:56 UTC

−2 points

0 comments1 min readLW link

Who ordered alignment’s apple?

Eleni Angelou28 Aug 2022 4:05 UTC

6 points

3 comments3 min readLW link

Sufficiently many Godzillas as an alignment strategy

14285728 Aug 2022 0:08 UTC

8 points

3 comments1 min readLW link