Gothen­burg LW /​ ACX meetup

Stefan8 Jan 2025 21:39 UTC
2 points
0 comments1 min readLW link

Aris­toc­racy and Hostage Capital

Arjun Panickssery8 Jan 2025 19:38 UTC
108 points
7 comments3 min readLW link
(arjunpanickssery.substack.com)

[Question] What is the most im­pres­sive game LLMs can play well?

Cole Wyeth8 Jan 2025 19:38 UTC
19 points
20 comments1 min readLW link

The Type of Writ­ing that Pushes Women Away

Dahlia8 Jan 2025 18:54 UTC
23 points
4 comments2 min readLW link

Ann Alt­man has filed a law­suit in US fed­eral court alleg­ing that she was sex­u­ally abused by Sam Altman

quanticle8 Jan 2025 14:59 UTC
7 points
3 comments1 min readLW link

AI Safety Outreach Sem­i­nar & So­cial (on­line)

Linda Linsefors8 Jan 2025 13:25 UTC
9 points
0 comments1 min readLW link

XX by Rian Hughes: Pre­ten­tious Bullshit

Yair Halberstadt8 Jan 2025 13:02 UTC
33 points
5 comments5 min readLW link

Ac­ti­va­tion space in­ter­pretabil­ity may be doomed

8 Jan 2025 12:49 UTC
152 points
34 comments8 min readLW link

AI Safety as a YC Startup

Lukas Petersson8 Jan 2025 10:46 UTC
58 points
9 comments5 min readLW link

The ab­solute ba­sics of rep­re­sen­ta­tion the­ory of finite groups

Dmitry Vaintrob8 Jan 2025 9:47 UTC
21 points
1 comment10 min readLW link

Im­pli­ca­tions of the AI Se­cu­rity Gap

Dan Braun8 Jan 2025 8:31 UTC
46 points
0 comments9 min readLW link

What are poly­se­man­tic neu­rons?

8 Jan 2025 7:35 UTC
9 points
0 comments4 min readLW link
(aisafety.info)

Tips On Em­piri­cal Re­search Slides

8 Jan 2025 5:06 UTC
97 points
4 comments6 min readLW link

On Eat­ing the Sun

jessicata8 Jan 2025 4:57 UTC
96 points
99 comments3 min readLW link
(unstablerontology.substack.com)

Book re­view: Range by David Epstein

PatrickDFarley8 Jan 2025 4:27 UTC
14 points
0 comments15 min readLW link

Can we have Epipha­nies and Eureka mo­ments more fre­quently?

CstineSublime8 Jan 2025 2:20 UTC
2 points
0 comments4 min readLW link

Job Open­ing: SWE to help im­prove grant-mak­ing software

Ethan Ashkie8 Jan 2025 0:54 UTC
22 points
1 comment2 min readLW link
(survivalandflourishing.com)

Markov’s Inequal­ity Explained

criticalpoints8 Jan 2025 0:31 UTC
13 points
2 comments3 min readLW link
(eregis.github.io)

Stream Entry

lsusr7 Jan 2025 23:56 UTC
78 points
12 comments4 min readLW link

Don’t fall for on­tol­ogy pyra­mid schemes

Lorec7 Jan 2025 23:29 UTC
16 points
8 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

7 Jan 2025 21:01 UTC
51 points
9 comments5 min readLW link

Disagree­ment on AGI Suggests It’s Near

tangerine7 Jan 2025 20:42 UTC
30 points
15 comments1 min readLW link

Role em­bed­dings: mak­ing au­thor­ship more salient to LLMs

7 Jan 2025 20:13 UTC
50 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
27 points
0 comments1 min readLW link

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

tandem7 Jan 2025 19:11 UTC
163 points
9 comments1 min readLW link

Pre­dict­ing AI Re­leases Through Side Channels

Reworr R7 Jan 2025 19:06 UTC
16 points
1 comment1 min readLW link

Re­but­tals for ~all crit­i­cisms of AIXI

Cole Wyeth7 Jan 2025 17:41 UTC
26 points
17 comments14 min readLW link

OpenAI #10: Reflections

Zvi7 Jan 2025 17:00 UTC
149 points
7 comments11 min readLW link
(thezvi.wordpress.com)

Some im­pli­ca­tions of rad­i­cal empathy

MichaelStJules7 Jan 2025 16:10 UTC
3 points
0 comments7 min readLW link

Ac­tu­al­ism, asym­me­try and extinction

MichaelStJules7 Jan 2025 16:02 UTC
1 point
4 comments9 min readLW link

Med­i­ta­tion in­sights as phase shifts in your self-model

Jonas Hallgren7 Jan 2025 10:09 UTC
15 points
3 comments3 min readLW link

Alle­vi­at­ing shrimp pain is im­moral.

G Wood7 Jan 2025 7:28 UTC
−7 points
6 comments4 min readLW link

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

aphyer7 Jan 2025 5:02 UTC
34 points
8 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
9 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
44 points
3 comments5 min readLW link
(newsletter.danielpaleka.com)

Test­ing for Schem­ing with Model Deletion

Guive7 Jan 2025 1:54 UTC
59 points
21 comments21 min readLW link
(guive.substack.com)

Guilt, Shame, and Depravity

Benquo7 Jan 2025 1:16 UTC
15 points
12 comments4 min readLW link

Turn­ing up the Heat on De­cep­tively-Misal­igned AI

J Bostock7 Jan 2025 0:13 UTC
19 points
16 comments4 min readLW link

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

jacek6 Jan 2025 23:35 UTC
12 points
6 comments1 min readLW link

Defi­ni­tion of al­ign­ment sci­ence I like

quetzal_rainbow6 Jan 2025 20:40 UTC
21 points
0 comments3 min readLW link

How will we up­date about schem­ing?

ryan_greenblatt6 Jan 2025 20:21 UTC
176 points
21 comments37 min readLW link

What Indi­ca­tors Should We Watch to Disam­biguate AGI Timelines?

snewman6 Jan 2025 19:57 UTC
142 points
57 comments13 min readLW link

Gen­er­at­ing Cog­nate­ful Sen­tences with Large Lan­guage Models

vkethana6 Jan 2025 18:40 UTC
11 points
1 comment10 min readLW link

Really rad­i­cal empathy

MichaelStJules6 Jan 2025 17:46 UTC
19 points
0 comments10 min readLW link

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

rife6 Jan 2025 17:34 UTC
4 points
20 comments1 min readLW link
(awakenmoon.ai)

[Question] Meal Re­place­ments in 2025?

alkjash6 Jan 2025 15:37 UTC
30 points
11 comments1 min readLW link

AI safety con­tent you could create

Adam Jones6 Jan 2025 15:35 UTC
19 points
0 comments5 min readLW link
(adamjones.me)