All 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 20242025

AllJan

All 1 2 3 4 5 6 78

Stream Entry

lsusr7 Jan 2025 23:56 UTC

41 points

0 comments4 min readLW link

Don’t fall for ontology pyramid schemes

Lorec7 Jan 2025 23:29 UTC

12 points

3 comments2 min readLW link

Bridgewater x Metaculus Forecasting Contest Goes Global — Feb 3, $25k, Opportunities

ChristianWilliams7 Jan 2025 21:40 UTC

10 points

0 comments1 min readLW link

(www.metaculus.com)

A Principled Cartoon Guide to NVC

plex and Espedair Street

7 Jan 2025 21:01 UTC

25 points

5 comments5 min readLW link

Disagreement on AGI Suggests It’s Near

tangerine7 Jan 2025 20:42 UTC

24 points

5 comments1 min readLW link

Role embeddings: making authorship more salient to LLMs

Nina Panickssery and Christopher Ackerman

7 Jan 2025 20:13 UTC

38 points

0 comments8 min readLW link

Will bird flu be the next Covid? “Little chance” says my dashboard.

Nathan Young7 Jan 2025 20:10 UTC

19 points

0 comments1 min readLW link

[Fiction] [Comic] Effective Altruism and Rationality meet at a Secular Solstice afterparty

tandem7 Jan 2025 19:11 UTC

94 points

4 comments1 min readLW link

Predicting AI Releases Through Side Channels

Reworr R7 Jan 2025 19:06 UTC

11 points

0 comments1 min readLW link

Rebuttals for ~all criticisms of AIXI

Cole Wyeth7 Jan 2025 17:41 UTC

17 points

5 comments14 min readLW link

OpenAI #10: Reflections

Zvi7 Jan 2025 17:00 UTC

131 points

6 comments11 min readLW link

(thezvi.wordpress.com)

Other implications of radical empathy

MichaelStJules7 Jan 2025 16:10 UTC

3 points

0 comments1 min readLW link

Actualism, asymmetry and extinction

MichaelStJules7 Jan 2025 16:02 UTC

−1 points

0 comments1 min readLW link

Meditation insights as phase shifts in your self-model

Jonas Hallgren7 Jan 2025 10:09 UTC

7 points

1 comment3 min readLW link

Alleviating shrimp pain is immoral.

G Wood7 Jan 2025 7:28 UTC

−5 points

0 comments4 min readLW link

D&D.Sci Dungeonbuilding: the Dungeon Tournament Evaluation & Ruleset

aphyer7 Jan 2025 5:02 UTC

27 points

5 comments5 min readLW link

Incredibow

jefftk7 Jan 2025 3:30 UTC

17 points

3 comments1 min readLW link

(www.jefftk.com)

Building Big Science from the Bottom-Up: A Fractal Approach to AI Safety

Lauren Greenspan7 Jan 2025 3:08 UTC

37 points

2 comments12 min readLW link

My Experience With A Magnet Implant

Vale7 Jan 2025 3:01 UTC

5 points

2 comments1 min readLW link

(vale.rocks)

You should delay engineering-heavy research in light of R&D automation

Daniel Paleka7 Jan 2025 2:11 UTC

32 points

3 comments5 min readLW link

(newsletter.danielpaleka.com)

Testing for Scheming with Model Deletion

Guive7 Jan 2025 1:54 UTC

59 points

12 comments21 min readLW link

(guive.substack.com)

Guilt, Shame, and Depravity

Benquo7 Jan 2025 1:16 UTC

11 points

2 comments4 min readLW link

Turning up the Heat on Deceptively-Misaligned AI

J Bostock7 Jan 2025 0:13 UTC

19 points

15 comments4 min readLW link

(My) self-referential reason to believe in free will

jacek6 Jan 2025 23:35 UTC

16 points

5 comments1 min readLW link

[Question] Is my distinctiveness evidence for being in a simulation?

AynonymousPrsn1236 Jan 2025 21:27 UTC

8 points

42 comments2 min readLW link

Definition of alignment science I like

quetzal_rainbow6 Jan 2025 20:40 UTC

19 points

0 comments3 min readLW link

How will we update about scheming?

ryan_greenblatt6 Jan 2025 20:21 UTC

128 points

4 comments36 min readLW link

What Indicators Should We Watch to Disambiguate AGI Timelines?

snewman6 Jan 2025 19:57 UTC

115 points

32 comments13 min readLW link

Generating Cognateful Sentences with Large Language Models

vkethana6 Jan 2025 18:40 UTC

6 points

0 comments10 min readLW link

Really radical empathy

MichaelStJules6 Jan 2025 17:46 UTC

19 points

0 comments1 min readLW link

Independent research article analyzing consistent self-reports of experience in ChatGPT and Claude

rife6 Jan 2025 17:34 UTC

3 points

8 comments1 min readLW link

(awakenmoon.ai)

[Question] Meal Replacements in 2025?

alkjash6 Jan 2025 15:37 UTC

19 points

9 comments1 min readLW link

AI safety content you could create

Adam Jones6 Jan 2025 15:35 UTC

18 points

0 comments5 min readLW link

(adamjones.me)

Childhood and Education #8: Dealing with the Internet

Zvi6 Jan 2025 14:00 UTC

32 points

6 comments13 min readLW link

(thezvi.wordpress.com)

Latent Adversarial Training (LAT) Improves the Representation of Refusal

alexandraabbas, nlpet and hal2k

6 Jan 2025 10:24 UTC

17 points

5 comments10 min readLW link

Alternative Cancer Care As Biohacking & Book Review: Surviving “Terminal” Cancer

DenizT6 Jan 2025 7:43 UTC

31 points

4 comments15 min readLW link

Estimating the benefits of a new flu drug (BXM)

DirectedEvolution6 Jan 2025 4:31 UTC

34 points

2 comments3 min readLW link

Measuring Nonlinear Feature Interactions in Sparse Crosscoders [Project Proposal]

Jason Gross and rajashree

6 Jan 2025 4:22 UTC

19 points

0 comments12 min readLW link

Speedrunning Rationality: Day II

aproteinengine6 Jan 2025 3:59 UTC

6 points

3 comments2 min readLW link

“We know how to build AGI”—Sam Altman

Nikola Jurkovic6 Jan 2025 2:05 UTC

62 points

5 comments1 min readLW link

(blog.samaltman.com)

[Question] Is “hidden complexity of wishes problem” solved?

Roman Malov5 Jan 2025 22:59 UTC

10 points

4 comments1 min readLW link

A Ground-Level Perspective on Capacity Building in International Development

Sean Aubin5 Jan 2025 20:36 UTC

10 points

1 comment8 min readLW link

Why Linear AI Safety Hits a Wall and How Fractal Intelligence Unlocks Non-Linear Solutions

Andy E Williams5 Jan 2025 17:08 UTC

−3 points

6 comments5 min readLW link

How to Do a PhD (in AI Safety)

Lewis Hammond5 Jan 2025 16:57 UTC

6 points

0 comments1 min readLW link

(lewishammond.com)

Reasons for and against working on technical AI safety at a frontier AI lab

bilalchughtai5 Jan 2025 14:49 UTC

89 points

12 comments12 min readLW link

Oppression and production are competing explanations for wealth inequality.

Benquo5 Jan 2025 14:13 UTC

32 points

15 comments8 min readLW link

(benjaminrosshoffman.com)

Maximizing Communication, not Traffic

jefftk5 Jan 2025 13:00 UTC

133 points

7 comments1 min readLW link

(www.jefftk.com)

Policymakers don’t have access to paywalled articles

Adam Jones5 Jan 2025 10:56 UTC

17 points

4 comments2 min readLW link

(adamjones.me)

Capital Ownership Will Not Prevent Human Disempowerment

beren5 Jan 2025 6:00 UTC

112 points

9 comments14 min readLW link

Chinese Researchers Crack ChatGPT: Replicating OpenAI’s Advanced AI Model

Evan_Gaensbauer5 Jan 2025 3:50 UTC

−8 points

1 comment1 min readLW link

(www.geeky-gadgets.com)