Lorxus Fa­vors: An Ex­per­i­ment in Self-Backed Giftlike Macroe­co­nomics (+ Ex­tra Bits)

Lorxus12 Nov 2025 23:02 UTC
7 points
0 comments8 min readLW link
(tiled-with-pentagons.blogspot.com)

A Time­less Uni­verse Viewed From the Inside

0xA12 Nov 2025 22:32 UTC
1 point
0 comments3 min readLW link

Please, Don’t Roll Your Own Metaethics

Wei Dai12 Nov 2025 22:17 UTC
153 points
68 comments2 min readLW link

A bad re­view != a bad book

Algon12 Nov 2025 22:05 UTC
9 points
3 comments1 min readLW link

The Pope Offers Wisdom

Zvi12 Nov 2025 21:50 UTC
51 points
3 comments8 min readLW link
(thezvi.wordpress.com)

Why Truth First?

johnswentworth12 Nov 2025 21:45 UTC
51 points
6 comments6 min readLW link

So­cial drives 2: “Ap­proval Re­ward”, from norm-en­force­ment to sta­tus-seeking

Steven Byrnes12 Nov 2025 20:40 UTC
42 points
9 comments17 min readLW link

OpenAI Re­leases GPT 5.1

anaguma12 Nov 2025 20:33 UTC
13 points
1 comment1 min readLW link
(openai.com)

[Question] Is SGD ca­pa­bil­ities re­search pos­i­tive?

Brendan Long12 Nov 2025 20:32 UTC
7 points
1 comment1 min readLW link

Bit­coin Halv­ings and the Tri­so­laran Mis­take: When Ex­ter­nal Ac­tors Mas­quer­ade as Nat­u­ral Laws

Mi12 Nov 2025 20:30 UTC
12 points
0 comments1 min readLW link

Lighthaven-ish Ticket Strat­egy: Three Pillars of FOMO

JohnofCharleston12 Nov 2025 20:10 UTC
59 points
0 comments5 min readLW link

Per­sonal Ac­count: To the Muck and the Mire

soycarts12 Nov 2025 19:38 UTC
2 points
0 comments1 min readLW link

We live in the luck­iest timeline

beyarkay (Boyd Kane)12 Nov 2025 18:59 UTC
2 points
6 comments5 min readLW link
(boydkane.com)

AI for Safety & Science Nodes in Ber­lin & the Bay Area

Allison Duettmann12 Nov 2025 18:49 UTC
6 points
0 comments2 min readLW link

Reflec­tions on be­ing Sorted

Gordon Seidoh Worley12 Nov 2025 17:40 UTC
23 points
0 comments9 min readLW link
(www.uncertainupdates.com)

Lorxus Does Halfhaven: 11/​01~11/​07

Lorxus12 Nov 2025 16:43 UTC
9 points
0 comments2 min readLW link
(tiled-with-pentagons.blogspot.com)

Undis­solv­able Prob­lems: things that still con­fuse me

Yair Halberstadt12 Nov 2025 16:30 UTC
26 points
22 comments2 min readLW link

In­tro­duc­ing faruvc.org

jefftk12 Nov 2025 16:00 UTC
47 points
10 comments1 min readLW link
(www.jefftk.com)

Warn­ing Aliens About the Danger­ous AI We Might Create

12 Nov 2025 15:26 UTC
91 points
25 comments5 min readLW link

9+ weeks of men­tored AI safety re­search in Lon­don – Pivotal Re­search Fellowship

Tobias H12 Nov 2025 15:21 UTC
9 points
0 comments2 min readLW link

I Read Red Heart and I Heart It

Taylor G. Lunt12 Nov 2025 14:54 UTC
38 points
16 comments2 min readLW link

Mis­cel­la­neous ob­ser­va­tions about board games

Dentosal12 Nov 2025 12:49 UTC
4 points
0 comments2 min readLW link

Why to Com­mit to a Writ­ing and Pub­lish­ing Schedule

dreeves12 Nov 2025 7:35 UTC
10 points
0 comments2 min readLW link

5 Things I Learned After 10 Days of Inkhaven

Ben Pace12 Nov 2025 7:20 UTC
107 points
5 comments3 min readLW link

Do not hand off what you can­not pick up

habryka12 Nov 2025 6:32 UTC
144 points
24 comments4 min readLW link

Bet­ter than Baseline

Screwtape12 Nov 2025 6:30 UTC
24 points
1 comment4 min readLW link

How hu­man-like do safe AI mo­ti­va­tions need to be?

Joe Carlsmith12 Nov 2025 5:32 UTC
27 points
9 comments52 min readLW link

Teleose­man­tics & Swampman

abramdemski12 Nov 2025 5:27 UTC
26 points
6 comments5 min readLW link

Re­sponse to “Tak­ing AI Welfare Se­ri­ously”: The Indi­rect Ap­proach to Mo­ral Patienthood

Juan Cadile12 Nov 2025 4:43 UTC
12 points
0 comments2 min readLW link

How I Learned That I Don’t Feel Com­pan­ionate Love

johnswentworth12 Nov 2025 4:18 UTC
115 points
32 comments4 min readLW link

Con­cep­tual rea­son­ing dataset v0.1 available (AI for AI safety/​AI for philos­o­phy)

12 Nov 2025 1:12 UTC
19 points
0 comments3 min readLW link

Fairly Break­ing Ties Without Fair Coins

Brendan Long11 Nov 2025 21:48 UTC
11 points
10 comments4 min readLW link
(www.brendanlong.com)

Kimi K2 Thinking

Zvi11 Nov 2025 21:10 UTC
47 points
0 comments5 min readLW link
(thezvi.wordpress.com)

Not-A-Book Re­view: The At­trac­tive Man (Dat­ing Coach Ser­vice)

25Hour11 Nov 2025 20:03 UTC
15 points
0 comments1 min readLW link
(lifeimprovementschemes.substack.com)

Don’t Get One-Shotted

Jordan Rubin11 Nov 2025 17:07 UTC
2 points
2 comments6 min readLW link
(jordanmrubin.substack.com)

Learn­ings from the Zurich AI Safety Day

11 Nov 2025 17:00 UTC
13 points
0 comments6 min readLW link

Steer­ing Lan­guage Models with Weight Arithmetic

11 Nov 2025 16:30 UTC
88 points
6 comments5 min readLW link

An­nounc­ing the So­ciety of Teen Scientists

rogersbacon11 Nov 2025 16:08 UTC
8 points
0 comments1 min readLW link

What is Hap­pen­ing in AI Gover­nance?

11 Nov 2025 15:59 UTC
6 points
0 comments5 min readLW link

Hu­man Agency at Stake

11 Nov 2025 15:57 UTC
8 points
0 comments6 min readLW link

Om­ni­science one bit at a time: Chap­ter 3

Dentosal11 Nov 2025 13:34 UTC
2 points
0 comments2 min readLW link

Evolu­tion’s Align­ment Solu­tion: Why Burnout Prevents Monsters

Elias_Kunnas11 Nov 2025 13:32 UTC
9 points
0 comments6 min readLW link

Thick prac­tices for AI tools

Alexandre Variengien11 Nov 2025 13:13 UTC
19 points
2 comments20 min readLW link
(alexandrevariengien.com)

The prob­lem of grace­ful deference

TsviBT11 Nov 2025 8:17 UTC
108 points
41 comments4 min readLW link

See Your Word Count While You Write

dreeves11 Nov 2025 8:02 UTC
7 points
3 comments2 min readLW link

On Stance

Screwtape11 Nov 2025 7:50 UTC
24 points
5 comments6 min readLW link

Break­ing the He­donic Rub­ber Band

Ben Pace11 Nov 2025 7:00 UTC
20 points
4 comments4 min readLW link

Re­ject­ing “Good­ness” Does Not Mean Ham­mer­ing The Defect Button

johnswentworth11 Nov 2025 6:50 UTC
25 points
6 comments2 min readLW link

Strength­en­ing Red Teams: A Mo­du­lar Scaf­fold for Con­trol Evaluations

Chloe Loughridge11 Nov 2025 6:20 UTC
7 points
0 comments1 min readLW link
(alignment.anthropic.com)

On the Nor­ma­tivity of De­bate: A Dis­cus­sion With Said Achmiz

Zack_M_Davis11 Nov 2025 5:49 UTC
21 points
1 comment22 min readLW link