23 Jul 2024 20:15 UTC

27 points

4 comments18 min readLW link

(www.florencehinder.com)

How reasonable is taking extinction risk?

FVelde23 Jul 2024 18:05 UTC

2 points

4 comments4 min readLW link

Unlearning via RMU is mostly shallow

Andy Arditi and bilalchughtai

23 Jul 2024 16:07 UTC

50 points

3 comments6 min readLW link

Monthly Roundup #20: July 2024

Zvi23 Jul 2024 12:50 UTC

33 points

9 comments38 min readLW link

(thezvi.wordpress.com)

Confusing the metric for the meaning: Perhaps correlated attributes are “natural”

NickyP23 Jul 2024 12:43 UTC

33 points

3 comments4 min readLW link

My covid-related beliefs and questions

Severin T. Seehrich23 Jul 2024 3:27 UTC

8 points

0 comments1 min readLW link

[Question] Is there a Schelling point for group house room listings?

NoSignalNoNoise23 Jul 2024 3:03 UTC

4 points

0 comments1 min readLW link

Room Available in Boston Group House

NoSignalNoNoise23 Jul 2024 2:55 UTC

15 points

1 comment1 min readLW link

D&D.Sci Scenario Index

aphyer and abstractapplic

23 Jul 2024 2:00 UTC

73 points

0 comments2 min readLW link

How to avoid death by AI.

Krantz23 Jul 2024 1:59 UTC

−4 points

13 comments2 min readLW link

ML Safety Research Advice—GabeM

Gabe M23 Jul 2024 1:45 UTC

29 points

2 comments14 min readLW link

(open.substack.com)

Ransomware Payments Should Require a Sin Tax

Brian Bien22 Jul 2024 21:16 UTC

20 points

10 comments2 min readLW link

The Elusive Root Cause of Schizophrenia—Thesis Introduction Only

kareempforbes22 Jul 2024 20:24 UTC

−9 points

0 comments2 min readLW link

Is Chinese AGI a valid concern for the USA?

sammyboiz22 Jul 2024 20:21 UTC

0 points

2 comments9 min readLW link

Trying to understand Hanson’s Cultural Drift argument

Kemp22 Jul 2024 20:20 UTC

9 points

3 comments2 min readLW link

Efficient Dictionary Learning with Switch Sparse Autoencoders

Anish Mudide22 Jul 2024 18:45 UTC

118 points

19 comments12 min readLW link

Analyzing DeepMind’s Probabilistic Methods for Evaluating Agent Capabilities

Axel Højmark, Govind Pimpale, Arjun Panickssery, Marius Hobbhahn and Jérémy Scheurer

22 Jul 2024 16:17 UTC

69 points

0 comments16 min readLW link

The Garden of Eden

Alexander Turok22 Jul 2024 16:07 UTC

23 points

2 comments9 min readLW link

Caring about excellence

owencb22 Jul 2024 14:24 UTC

47 points

4 comments1 min readLW link

Tim Dillon’s fake business is the most influential video I have watched in the last 24 months

Stuart Johnson22 Jul 2024 12:54 UTC

−4 points

0 comments1 min readLW link

(youtu.be)

On the CrowdStrike Incident

Zvi22 Jul 2024 12:40 UTC

75 points

14 comments17 min readLW link

(thezvi.wordpress.com)

Auto-Enhance: Developing a meta-benchmark to measure LLM agents’ ability to improve other agents

Sam F. Brown, BasilLabib, Codruta (Coco) Lugoj and Sai Sasank Y

22 Jul 2024 12:33 UTC

20 points

0 comments14 min readLW link

What does “the universe is quantum” actually mean?

Tahp22 Jul 2024 11:52 UTC

2 points

0 comments14 min readLW link

Initial Experiments Using SAEs to Help Detect AI Generated Text

Aaron_Scher22 Jul 2024 5:16 UTC

17 points

0 comments14 min readLW link

Categories of leadership on technical teams

benkuhn22 Jul 2024 4:50 UTC

35 points

0 comments8 min readLW link

(www.benkuhn.net)

An experiment on hidden cognition

Olli Järviniemi22 Jul 2024 3:26 UTC

25 points

2 comments7 min readLW link

OpenAI Boycott Revisit

Jake Dennie22 Jul 2024 1:44 UTC

17 points

2 comments2 min readLW link

Coalitional agency

Richard_Ngo22 Jul 2024 0:09 UTC

56 points

6 comments6 min readLW link

The AI Driver’s Licence—A Policy Proposal

Joshua W and Tessa Malan

21 Jul 2024 20:38 UTC

0 points

1 comment19 min readLW link

Demography and Destiny

Zero Contradictions21 Jul 2024 20:34 UTC

6 points

11 comments1 min readLW link

(thewaywardaxolotl.blogspot.com)

The $100B plan with “70% risk of killing us all” w Stephen Fry [video]

Oleg Trott21 Jul 2024 20:06 UTC

36 points

8 comments1 min readLW link

(www.youtube.com)

Raising Welfare for Lab Rodents

xanderbalwit21 Jul 2024 19:18 UTC

1 point

0 comments1 min readLW link

(press.asimov.com)

A simple model of math skill

Alex_Altair21 Jul 2024 18:57 UTC

101 points

16 comments8 min readLW link

Using an LLM perplexity filter to detect weight exfiltration

Adam Karvonen21 Jul 2024 18:18 UTC

25 points

11 comments2 min readLW link

[Question] Would a scope-insensitive AGI be less likely to incapacitate humanity?

Jim Buhler21 Jul 2024 14:15 UTC

2 points

3 comments1 min readLW link

Holomorphic surjection theorem (Picard’s little theorem)

dkl921 Jul 2024 13:24 UTC

15 points

0 comments2 min readLW link

(dkl9.net)

aimless ace analyzes active amateur: a micro-aaaaalignment proposal

lemonhope21 Jul 2024 12:37 UTC

12 points

0 comments1 min readLW link

Pivotal Acts are easier than Alignment?

Michael Soareverix21 Jul 2024 12:15 UTC

1 point

4 comments1 min readLW link

Ball Sq Pathways

jefftk21 Jul 2024 2:20 UTC

13 points

1 comment1 min readLW link

(www.jefftk.com)

Freedom and Privacy of Thought Architectures

SebastianG 20 Jul 2024 21:43 UTC

5 points

2 comments1 min readLW link

Introduction to Modern Dating: Strategic Dating Advice for beginners

Jesper Lindholm20 Jul 2024 15:45 UTC

5 points

6 comments13 min readLW link

Why Georgism Lost Its Popularity

Zero Contradictions20 Jul 2024 15:08 UTC

45 points

53 comments1 min readLW link

(zerocontradictions.net)

Only Fools Avoid Hindsight Bias

Kevin Dorst20 Jul 2024 13:42 UTC

−11 points

5 comments6 min readLW link

(kevindorst.substack.com)

A more systematic case for inner misalignment

Richard_Ngo20 Jul 2024 5:03 UTC

31 points

4 comments5 min readLW link

BatchTopK: A Simple Improvement for TopK-SAEs

Bart Bussmann, Patrick Leask and Neel Nanda

20 Jul 2024 2:20 UTC

53 points

0 comments4 min readLW link

Krona Compare

jefftk20 Jul 2024 1:10 UTC

10 points

0 comments2 min readLW link

(www.jefftk.com)

(Approximately) Deterministic Natural Latents

johnswentworth and David Lorell

19 Jul 2024 23:02 UTC

41 points

0 comments4 min readLW link

Feature Targeted LLC Estimation Distinguishes SAE Features from Random Directions

Lidor Banuel Dabbah and Aviel Boag

19 Jul 2024 20:32 UTC

59 points

6 comments16 min readLW link

JumpReLU SAEs + Early Access to Gemma 2 SAEs

Senthooran Rajamanoharan, Tom Lieberum, nps29, Arthur Conmy, Vikrant Varma, János Kramár and Neel Nanda

19 Jul 2024 16:10 UTC

48 points

10 comments1 min readLW link

(storage.googleapis.com)

Truth is Universal: Robust Detection of Lies in LLMs

Lennart Buerger19 Jul 2024 14:07 UTC

24 points

3 comments2 min readLW link

(arxiv.org)