12 May 2024 21:58 UTC

22 points

0 comments4 min readLW link

(formalizingboundaries.substack.com)

Understanding rationality vs. ideology debates

Aryeh Englander12 May 2024 19:20 UTC

13 points

1 comment6 min readLW link

Partitioned Book Club

jenn12 May 2024 18:38 UTC

22 points

6 comments4 min readLW link

Inner Optimization Mechanisms in Neural Nets

ProgramCrafter12 May 2024 17:52 UTC

3 points

1 comment1 min readLW link

Building intuition with spaced repetition systems

Jacob G-W12 May 2024 15:49 UTC

55 points

8 comments4 min readLW link

(jacobgw.com)

Beware unfinished bridges

Adam Zerner12 May 2024 9:29 UTC

43 points

11 comments3 min readLW link

What comes after Roam’s renaissance?

Itay Dreyfus12 May 2024 8:51 UTC

15 points

23 comments11 min readLW link

(productidentity.co)

The Natural Selection of Bad Vibes (Part 1)

Kevin Dorst12 May 2024 8:28 UTC

13 points

3 comments7 min readLW link

(kevindorst.substack.com)

Geometric Utilitarianism (And Why It Matters)

StrivingForLegibility12 May 2024 3:41 UTC

34 points

2 comments11 min readLW link

If language is for communication, what does that imply about LLMs?

Bill Benzon12 May 2024 2:55 UTC

10 points

0 comments1 min readLW link

[Linkpost] Towards a Theoretical Understanding of the ‘Reversal Curse’ via Training Dynamics

Bogdan Ionut Cirstea11 May 2024 22:59 UTC

6 points

0 comments1 min readLW link

(arxiv.org)

How To Do Patching Fast

Joseph Miller11 May 2024 20:13 UTC

44 points

8 comments4 min readLW link

Can we build a better Public Doublecrux?

Raemon11 May 2024 19:21 UTC

53 points

6 comments4 min readLW link

[Question] How do I get better at D&D Sci?

FinalFormal211 May 2024 18:48 UTC

10 points

7 comments1 min readLW link

[Question] Resources for learning about poise / gracefulness?

David Gross11 May 2024 18:30 UTC

14 points

1 comment1 min readLW link

New intro textbook on AIXI

Alex_Altair11 May 2024 18:18 UTC

47 points

8 comments1 min readLW link

Questions are usually too cheap

Nathan Young11 May 2024 13:00 UTC

57 points

19 comments6 min readLW link

(nathanpmyoung.substack.com)

dead post 2

David Chapel11 May 2024 9:33 UTC

−6 points

4 comments1 min readLW link

[Question] Ethics and prospects of AI related jobs?

dr_s11 May 2024 9:31 UTC

10 points

8 comments1 min readLW link

Should I Finish My Bachelor’s Degree?

Zack_M_Davis11 May 2024 5:17 UTC

27 points

14 comments6 min readLW link

(zackmdavis.net)

Custom Audio Switch Box

jefftk11 May 2024 2:40 UTC

9 points

0 comments1 min readLW link

(www.jefftk.com)

MATS Winter 2023-24 Retrospective

utilistrutil, LauraVaughan, McKennaFitzgerald, Christian Smith, Juan Gil, Henry Sleight, Matthew Wearden and Ryan Kidd

11 May 2024 0:09 UTC

87 points

28 comments49 min readLW link

Applying refusal-vector ablation to a Llama 3 70B agent

Simon Lermen11 May 2024 0:08 UTC

51 points

14 comments7 min readLW link

Qualia

A*10 May 2024 19:11 UTC

3 points

0 comments1 min readLW link

The Alignment Problem No One Is Talking About

James Stephen Brown10 May 2024 18:34 UTC

10 points

10 comments2 min readLW link

(nonzerosum.games)

Pascal’s Mugging and the Order of Quantification

SorenJ10 May 2024 18:34 UTC

11 points

3 comments2 min readLW link

New to this community

kjsisco10 May 2024 18:34 UTC

1 point

1 comment1 min readLW link

dead post 1

David Chapel10 May 2024 18:34 UTC

−14 points

1 comment1 min readLW link

Podcast with Yoshua Bengio on Why AI Labs are “Playing Dice with Humanity’s Future”

garrison10 May 2024 17:23 UTC

41 points

0 comments2 min readLW link

(garrisonlovely.substack.com)

(Geometrically) Maximal Lottery-Lotteries Are Probably Not Unique

Lorxus10 May 2024 16:00 UTC

16 points

1 comment14 min readLW link

What do you value ?

Akram Choudhary10 May 2024 15:34 UTC

3 points

1 comment2 min readLW link

[Question] Do you know of lists of p(doom)s/AI forecasts/ AI quotes?

Nathan Young10 May 2024 11:47 UTC

8 points

2 comments1 min readLW link

[Question] Have any parties in the current European Parliamentary Election made public statements on AI?

MondSemmel10 May 2024 10:22 UTC

9 points

0 comments1 min readLW link

AI and Chemical, Biological, Radiological, & Nuclear Hazards: A Regulatory Review

Elliot Mckernon and Deric Cheng

10 May 2024 8:41 UTC

7 points

1 comment10 min readLW link

shortest goddamn bayes guide ever

lemonhope10 May 2024 7:06 UTC

54 points

8 comments1 min readLW link

Linear infra-Bayesian Bandits

Vanessa Kosoy10 May 2024 6:41 UTC

40 points

5 comments1 min readLW link

(arxiv.org)

Why Care About Natural Latents?

johnswentworth and David Lorell

9 May 2024 23:14 UTC

56 points

3 comments5 min readLW link

What I learned from doing Quiz Bowl

Jacob G-W9 May 2024 21:05 UTC

10 points

0 comments6 min readLW link

(jacobgw.com)

My thesis (Algorithmic Bayesian Epistemology) explained in more depth

Eric Neyman9 May 2024 19:43 UTC

82 points

4 comments27 min readLW link

(ericneyman.wordpress.com)

Dyslucksia

Shoshannah Tekofsky9 May 2024 19:21 UTC

156 points

45 comments6 min readLW link

Has Generative AI Already Peaked? - Computerphile

daviddelauba9 May 2024 18:27 UTC

7 points

2 comments1 min readLW link

(www.youtube.com)

[Question] Thoughts on the relative economic benefits of polyamorous relationships?

Oliver Kuperman9 May 2024 18:26 UTC

−1 points

4 comments1 min readLW link

AI Safety Strategies Landscape

Charbel-Raphaël9 May 2024 17:33 UTC

34 points

1 comment42 min readLW link

Knowledge Base 9: Increasing intelligence

iwis9 May 2024 15:46 UTC

−5 points

0 comments1 min readLW link

We might be missing some key feature of AI takeoff; it’ll probably seem like “we could’ve seen this coming”

Lukas_Gloor9 May 2024 15:43 UTC

100 points

36 comments5 min readLW link

Four Unrelated Is Over

jefftk9 May 2024 14:50 UTC

14 points

2 comments1 min readLW link

(www.jefftk.com)

AI #63: Introducing Alpha Fold 3

Zvi9 May 2024 14:20 UTC

33 points

2 comments28 min readLW link

(thezvi.wordpress.com)

I Got 95 Theses But a Glitch Ain’t One

Zvi9 May 2024 14:10 UTC

16 points

0 comments16 min readLW link

(thezvi.wordpress.com)

The Human’s Role in Mesa Optimization

silentbob9 May 2024 12:07 UTC

5 points

0 comments2 min readLW link

Visualizing neural network planning

Nevan Wichers, Victor Tao, Fazl and Riccardo Volpato

9 May 2024 6:40 UTC

4 points

0 comments5 min readLW link