All200520062007200820092010201120122013201420152016201720182019202020212022202320242025
AllJanFebMarAprMayJunJulAugSepOctNovDec
All12345678910111213141516171819202122232425262728293031

MATS AI Safety Strat­egy Cur­ricu­lum v2

DanielFilan and Ryan Kidd
Oct 7, 2024, 10:44 PM
43 points

17 votes

Overall karma indicates overall quality.

6 comments13 min readLW link

2025 Color Trends

sarahconstantinOct 7, 2024, 9:20 PM
40 points

18 votes

Overall karma indicates overall quality.

7 comments6 min readLW link
(sarahconstantin.substack.com)

Clar­ify­ing Align­ment Fun­da­men­tals Through the Lens of Ontology

Ben IhrigOct 7, 2024, 8:57 PM
12 points

6 votes

Overall karma indicates overall quality.

4 comments24 min readLW link

Ethics on Cos­mic Scale, Outer Space Treaty, Directed Pansper­mia, For­wards-Con­tam­i­na­tion, Tech­nol­ogy Assess­ment, Plane­tary Pro­tec­tion, and Fermi’s Paradox

MrFantasticOct 7, 2024, 8:56 PM
−12 points

8 votes

Overall karma indicates overall quality.

0 comments1 min readLW link

Do­main-spe­cific SAEs

jacob_droriOct 7, 2024, 8:15 PM
28 points

13 votes

Overall karma indicates overall quality.

2 comments5 min readLW link

Me­tac­u­lus Is Open Source

ChristianWilliamsOct 7, 2024, 7:55 PM
13 points

6 votes

Overall karma indicates overall quality.

0 comments1 min readLW link
(www.metaculus.com)

Re­search up­date: Towards a Law of Iter­ated Ex­pec­ta­tions for Heuris­tic Estimators

Eric NeymanOct 7, 2024, 7:29 PM
87 points

23 votes

Overall karma indicates overall quality.

2 comments22 min readLW link

AI Model Registries: A Foun­da­tional Tool for AI Governance

Elliot Mckernon, Deric Cheng and Gwyn Glasser
Oct 7, 2024, 7:27 PM
20 points

10 votes

Overall karma indicates overall quality.

1 comment4 min readLW link
(www.convergenceanalysis.org)

Eval­u­at­ing the truth of state­ments in a world of am­bigu­ous lan­guage.

HastingsOct 7, 2024, 6:08 PM
48 points

23 votes

Overall karma indicates overall quality.

19 comments2 min readLW link

Ad­vice for journalists

Nathan YoungOct 7, 2024, 4:46 PM
101 points

42 votes

Overall karma indicates overall quality.

53 comments9 min readLW link
(nathanpmyoung.substack.com)

Time Effi­cient Re­sis­tance Training

romeostevensitOct 7, 2024, 3:15 PM
42 points

20 votes

Overall karma indicates overall quality.

12 comments3 min readLW link

A Nar­row Path: a plan to deal with AI ex­tinc­tion risk

Andrea_Miotti, davekasten and Tolga
Oct 7, 2024, 1:02 PM
80 points

34 votes

Overall karma indicates overall quality.

12 comments2 min readLW link
(www.narrowpath.co)

Toy Models of Fea­ture Ab­sorp­tion in SAEs

chanind, hrdkbhatnagar, TomasD and Joseph Bloom
Oct 7, 2024, 9:56 AM
49 points

21 votes

Overall karma indicates overall quality.

8 comments10 min readLW link

An ar­gu­ment that con­se­quen­tial­ism is incomplete

cousin_itOct 7, 2024, 9:45 AM
35 points

17 votes

Overall karma indicates overall quality.

27 comments1 min readLW link

An X-Ray is Worth 15 Fea­tures: Sparse Au­toen­coders for In­ter­pretable Ra­diol­ogy Re­port Generation

hugofry, Ahmed Abdulaal, NMontanaBrown and a-ijishakin
Oct 7, 2024, 8:53 AM
40 points

21 votes

Overall karma indicates overall quality.

1 comment5 min readLW link
(arxiv.org)

Com­pel­ling Villains and Co­her­ent Values

Cole WyethOct 6, 2024, 7:53 PM
42 points

20 votes

Overall karma indicates overall quality.

4 comments4 min readLW link

To Be Born in a Bag

Niko_McCartyOct 6, 2024, 5:21 PM
19 points

12 votes

Overall karma indicates overall quality.

1 comment16 min readLW link
(www.asimov.press)

Whim­si­cal Thoughts on an AI Notepad: Ex­plor­ing Non-In­va­sive Neu­ral In­te­gra­tion via Viral and Stem Cell Pathways

Pug stankyOct 6, 2024, 4:37 PM
1 point

2 votes

Overall karma indicates overall quality.

2 comments4 min readLW link

Why I’m not a Bayesian

Richard_NgoOct 6, 2024, 3:22 PM
221 points

149 votes

Overall karma indicates overall quality.

104 comments10 min readLW link
(www.mindthefuture.info)

Euro­pean Progress Conference

Martin SustrikOct 6, 2024, 11:10 AM
27 points

17 votes

Overall karma indicates overall quality.

11 comments3 min readLW link
(250bpm.substack.com)

Open Thread Fall 2024

habrykaOct 5, 2024, 10:28 PM
44 points

24 votes

Overall karma indicates overall quality.

194 comments1 min readLW link

[Question] Seek­ing AI Align­ment Tu­tor/​Ad­vi­sor: $100–150/​hr

MrThinkOct 5, 2024, 9:28 PM
28 points

17 votes

Overall karma indicates overall quality.

3 comments2 min readLW link

In­ter­pretabil­ity of SAE Fea­tures Rep­re­sent­ing Check in ChessGPT

Jonathan KutasovOct 5, 2024, 8:43 PM
27 points

9 votes

Overall karma indicates overall quality.

2 comments8 min readLW link

2024 Elec­tion Fore­cast­ing Contest

mike20731Oct 5, 2024, 8:43 PM
4 points

3 votes

Overall karma indicates overall quality.

0 comments1 min readLW link
(www.mikesblog.net)

5 ways to im­prove CoT faithfulness

Caleb BiddulphOct 5, 2024, 8:17 PM
46 points

19 votes

Overall karma indicates overall quality.

40 comments6 min readLW link

Con­scious­ness As Re­cur­sive Reflections

Gunnar_ZarnckeOct 5, 2024, 8:00 PM
7 points

7 votes

Overall karma indicates overall quality.

2 comments1 min readLW link
(www.astralcodexten.com)

Mus­ings on Text Data Wall (Oct 2024)

Vladimir_NesovOct 5, 2024, 7:00 PM
41 points

13 votes

Overall karma indicates overall quality.

2 comments5 min readLW link

Ap­ply to the Co­op­er­a­tive AI PhD Fel­low­ship by Oc­to­ber 14th!

Lewis HammondOct 5, 2024, 12:41 PM
23 points

12 votes

Overall karma indicates overall quality.

0 comments1 min readLW link

AISafety.info: What is the “nat­u­ral ab­strac­tions hy­poth­e­sis”?

AlgonOct 5, 2024, 12:31 PM
38 points

14 votes

Overall karma indicates overall quality.

2 comments3 min readLW link
(aisafety.info)

ARENA4.0 Cap­stone: Hyper­pa­ram­e­ter tun­ing for MELBO + repli­ca­tion on Llama-3.2-1b-Instruct

25Hour and submarat
Oct 5, 2024, 11:30 AM
34 points

10 votes

Overall karma indicates overall quality.

2 comments8 min readLW link

Ex­plor­ing SAE fea­tures in LLMs with defi­ni­tion trees and to­ken lists

mwatkinsOct 4, 2024, 10:15 PM
46 points

12 votes

Overall karma indicates overall quality.

5 comments6 min readLW link

AXRP Epi­sode 37 - Jaime Sevilla on Fore­cast­ing AI

DanielFilanOct 4, 2024, 9:00 PM
21 points

6 votes

Overall karma indicates overall quality.

3 comments56 min readLW link

[Question] Seek­ing Solu­tions for Ag­gre­gat­ing Clas­sifier Outputs

Saeid GhafouriOct 4, 2024, 5:39 PM
−1 points

4 votes

Overall karma indicates overall quality.

0 comments1 min readLW link

Amoeba roles in tech

Sindhu ShivaprasadOct 4, 2024, 5:25 PM
12 points

6 votes

Overall karma indicates overall quality.

0 comments4 min readLW link

LASR Labs Spring 2025 ap­pli­ca­tions are open!

Erin Robertson, charlie_griffin, joehardie and Justin Olive
Oct 4, 2024, 1:44 PM
38 points

24 votes

Overall karma indicates overall quality.

0 comments4 min readLW link

(Maybe) A Bag of Heuris­tics is All There Is & A Bag of Heuris­tics is All You Need

SodiumOct 3, 2024, 7:11 PM
35 points

13 votes

Overall karma indicates overall quality.

17 comments17 min readLW link

Does nat­u­ral se­lec­tion fa­vor AIs over hu­mans?

cdkgOct 3, 2024, 6:47 PM
20 points

9 votes

Overall karma indicates overall quality.

1 comment1 min readLW link
(link.springer.com)

What Hayek Taught Us About Nature

Ground Truth DataOct 3, 2024, 6:20 PM
−1 points

2 votes

Overall karma indicates overall quality.

6 comments2 min readLW link

Bi­as­ing VLM Re­sponse with Vi­sual Stimuli

Jaehyuk LimOct 3, 2024, 6:04 PM
5 points

2 votes

Overall karma indicates overall quality.

0 comments8 min readLW link

AI #84: Bet­ter Than a Podcast

ZviOct 3, 2024, 3:00 PM
56 points

18 votes

Overall karma indicates overall quality.

7 comments52 min readLW link
(thezvi.wordpress.com)

[Question] If I have some money, whom should I donate it to in or­der to re­duce ex­pected P(doom) the most?

KvmanThinkingOct 3, 2024, 11:31 AM
35 points

18 votes

Overall karma indicates overall quality.

37 comments1 min readLW link

Shut­ting down all com­pet­ing AI pro­jects might not buy a lot of time due to In­ter­nal Time Pressure

ThomasCederborgOct 3, 2024, 12:01 AM
12 points

7 votes

Overall karma indicates overall quality.

7 comments12 min readLW link

“25 Les­sons from 25 Years of Mar­riage” by hon­orary ra­tio­nal­ist Fer­rett Stein­metz

CronoDASOct 2, 2024, 10:42 PM
24 points

12 votes

Overall karma indicates overall quality.

2 comments1 min readLW link
(theferrett.substack.com)

MIT Fu­tureTech are hiring for a Head of Oper­a­tions role

peterslatteryOct 2, 2024, 5:11 PM
8 points

3 votes

Overall karma indicates overall quality.

0 comments4 min readLW link

Can AI Quan­tity beat AI Qual­ity?

Gianluca CalcagniOct 2, 2024, 3:21 PM
2 points

1 vote

Overall karma indicates overall quality.

0 comments5 min readLW link

[In­tu­itive self-mod­els] 3. The Homunculus

Steven ByrnesOct 2, 2024, 3:20 PM
78 points

23 votes

Overall karma indicates overall quality.

39 comments25 min readLW link

AI Safety Univer­sity Or­ga­niz­ing: Early Take­aways from Thir­teen Groups

agucovaOct 2, 2024, 3:14 PM
26 points

13 votes

Overall karma indicates overall quality.

0 comments9 min readLW link

Three main ar­gu­ments that AI will save hu­mans and one meta-argument

avturchinOct 2, 2024, 11:39 AM
9 points

12 votes

Overall karma indicates overall quality.

8 comments2 min readLW link

Should we ab­stain from vot­ing? (In non­de­ter­minis­tic elec­tions)

B JacobsOct 2, 2024, 10:07 AM
5 points

10 votes

Overall karma indicates overall quality.

8 comments4 min readLW link
(bobjacobs.substack.com)

AI Safety at the Fron­tier: Paper High­lights, Septem­ber ’24

gasteigerjoOct 2, 2024, 9:49 AM
13 points

5 votes

Overall karma indicates overall quality.

0 comments7 min readLW link
(aisafetyfrontier.substack.com)