All200520062007200820092010201120122013201420152016201720182019202020212022202320242025
AllJanFebMarAprMayJunJulAugSepOctNovDec
All12345678910111213141516171819202122232425262728293031

Ti­maeus is hiring!

Jesse Hoogland, Stan van Wingerden, Alexander Gietelink Oldenziel and Daniel Murfet
Jul 12, 2024, 11:42 PM
67 points

28 votes

Overall karma indicates overall quality.

6 comments2 min readLW link

Con­sider at­tend­ing the AI Se­cu­rity Fo­rum ’24, a 1-day pre-DEFCON event

Charlie Rogers-SmithJul 12, 2024, 11:01 PM
21 points

4 votes

Overall karma indicates overall quality.

0 comments1 min readLW link

Me­moris­ing molec­u­lar structures

dkl9Jul 12, 2024, 10:40 PM
6 points

4 votes

Overall karma indicates overall quality.

0 comments2 min readLW link
(dkl9.net)

Robin Han­son AI X-Risk De­bate — High­lights and Analysis

LironJul 12, 2024, 9:31 PM
46 points

18 votes

Overall karma indicates overall quality.

7 comments45 min readLW link
(www.youtube.com)

De­sign­ing Ar­tifi­cial Wis­dom: The Wise Work­flow Re­search Organization

Jordan ArelJul 12, 2024, 7:18 PM
2 points

1 vote

Overall karma indicates overall quality.

0 comments8 min readLW link

White­board Pen Magaz­ines are Useful

Johannes C. MayerJul 12, 2024, 5:15 PM
41 points

22 votes

Overall karma indicates overall quality.

8 comments1 min readLW link

Align­ment: “Do what I would have wanted you to do”

Oleg TrottJul 12, 2024, 4:47 PM
11 points

6 votes

Overall karma indicates overall quality.

48 comments1 min readLW link

Virtue taxation

DentosalJul 12, 2024, 2:56 PM
9 points

7 votes

Overall karma indicates overall quality.

1 comment2 min readLW link

Most smart and skil­led peo­ple are out­side of the EA/​ra­tio­nal­ist com­mu­nity: an analysis

titotalJul 12, 2024, 12:13 PM
109 points

58 votes

Overall karma indicates overall quality.

39 comments14 min readLW link
(open.substack.com)

2024 Free­dom Com­mu­ni­ties Events

Tudor IliescuJul 12, 2024, 8:04 AM
−6 points

4 votes

Overall karma indicates overall quality.

1 comment1 min readLW link

Faith­ful vs In­ter­pretable Sparse Au­toen­coder Evals

Louka Ewington-PitsosJul 12, 2024, 5:37 AM
2 points

2 votes

Overall karma indicates overall quality.

0 comments12 min readLW link

Mov­ing away from phys­i­cal continuity

ProgramCrafterJul 12, 2024, 5:05 AM
2 points

2 votes

Overall karma indicates overall quality.

1 comment1 min readLW link

Trans­former Cir­cuit Faith­ful­ness Met­rics Are Not Robust

Joseph Miller, bilalchughtai and William_S
Jul 12, 2024, 3:47 AM
104 points

34 votes

Overall karma indicates overall quality.

5 comments7 min readLW link
(arxiv.org)

On Ar­tifi­cial Wisdom

Jordan ArelJul 12, 2024, 12:20 AM
3 points

2 votes

Overall karma indicates overall quality.

0 comments14 min readLW link

Yoshua Ben­gio: Rea­son­ing through ar­gu­ments against tak­ing AI safety seriously

Judd RosenblattJul 11, 2024, 11:53 PM
70 points

20 votes

Overall karma indicates overall quality.

3 comments1 min readLW link
(yoshuabengio.org)

Pod­cast: “How the Smart Money teaches trad­ing with Ricki He­ick­len” (Pa­trick McKen­zie in­ter­view­ing)

rossryJul 11, 2024, 10:49 PM
20 points

5 votes

Overall karma indicates overall quality.

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

Su­perba­bies: Put­ting The Pie­ces Together

sarahconstantinJul 11, 2024, 8:40 PM
216 points

102 votes

Overall karma indicates overall quality.

37 comments10 min readLW link
(sarahconstantin.substack.com)

Sher­lock­ian Ab­duc­tion Master List

Cole WyethJul 11, 2024, 8:27 PM
52 points

29 votes

Overall karma indicates overall quality.

66 comments36 min readLW link

Thoughts to ni­plav on lie-de­tec­tion, truth­fwl mechanisms, and wealth-inequality

Emrik and niplav
Jul 11, 2024, 6:55 PM
7 points

2 votes

Overall karma indicates overall quality.

8 comments11 min readLW link

Games for AI Control

charlie_griffin and Buck
Jul 11, 2024, 6:40 PM
45 points

21 votes

Overall karma indicates overall quality.

0 comments5 min readLW link

Video In­tro to Guaran­teed Safe AI

Mike Vaiana, Diogo de Lucena and Trent Hodgeson
Jul 11, 2024, 5:53 PM
27 points

13 votes

Overall karma indicates overall quality.

0 comments1 min readLW link
(youtu.be)

Effec­tive Empathy

Thac0Jul 11, 2024, 3:14 PM
4 points

2 votes

Overall karma indicates overall quality.

1 comment1 min readLW link

AI #72: Deny­ing the Future

ZviJul 11, 2024, 3:00 PM
45 points

26 votes

Overall karma indicates overall quality.

8 comments41 min readLW link
(thezvi.wordpress.com)

The Best Bits From Build, Baby, Build

Maxwell TabarrokJul 11, 2024, 2:09 PM
23 points

7 votes

Overall karma indicates overall quality.

0 comments4 min readLW link
(www.maximum-progress.com)

[Question] What Other Lines of Work are Safe from AI Au­toma­tion?

RogerDearnaleyJul 11, 2024, 10:01 AM
35 points

22 votes

Overall karma indicates overall quality.

35 comments5 min readLW link

De­com­pos­ing Agency — ca­pa­bil­ities with­out desires

owencb and Raymond Douglas
Jul 11, 2024, 9:38 AM
155 points

57 votes

Overall karma indicates overall quality.

32 comments12 min readLW link
(strangecities.substack.com)

Reli­able Sources: The Story of David Gerard

TracingWoodgrainsJul 10, 2024, 7:50 PM
391 points

146 votes

Overall karma indicates overall quality.

54 comments43 min readLW link

Manag­ing Emo­tional Po­ten­tial Energy

adamShimiJul 10, 2024, 6:20 PM
24 points

11 votes

Overall karma indicates overall quality.

4 comments4 min readLW link
(epistemologicalfascinations.substack.com)

[EAFo­rum xpost] A break­down of OpenAI’s revenue

dschwarz and Lawrence Phillips
Jul 10, 2024, 6:09 PM
57 points

25 votes

Overall karma indicates overall quality.

5 comments1 min readLW link
(forum.effectivealtruism.org)

Solv­ing Pas­cal’s Wager us­ing dy­namic programming

Paul WilczewskiJul 10, 2024, 6:09 PM
1 point

7 votes

Overall karma indicates overall quality.

0 comments5 min readLW link

Fluent, Cruxy Predictions

RaemonJul 10, 2024, 6:00 PM
86 points

34 votes

Overall karma indicates overall quality.

14 comments14 min readLW link

An­titrust as Con­trol­led Creative Destruction

Martin SustrikJul 10, 2024, 4:40 PM
14 points

5 votes

Overall karma indicates overall quality.

2 comments2 min readLW link
(250bpm.substack.com)

New page: Integrity

Zach Stein-PerlmanJul 10, 2024, 3:00 PM
91 points

29 votes

Overall karma indicates overall quality.

3 comments1 min readLW link

AirBnB Baking

jefftkJul 10, 2024, 12:50 PM
7 points

3 votes

Overall karma indicates overall quality.

1 comment1 min readLW link
(www.jefftk.com)

DIY RLHF: A sim­ple im­ple­men­ta­tion for hands on experience

Mike Vaiana and Trent Hodgeson
Jul 10, 2024, 12:07 PM
29 points

21 votes

Overall karma indicates overall quality.

0 comments6 min readLW link

Use­ful­ness grounds truth

invertedpassionJul 10, 2024, 7:58 AM
0 points

6 votes

Overall karma indicates overall quality.

0 comments4 min readLW link

On pass­ing Com­plete and Hon­est Ide­olog­i­cal Tur­ing Tests (CHITTs)

Aryeh EnglanderJul 10, 2024, 4:01 AM
11 points

4 votes

Overall karma indicates overall quality.

2 comments1 min readLW link

[Question] Pon­der­ing how good or bad things will be in the AGI future

SherrinfordJul 9, 2024, 10:46 PM
11 points

3 votes

Overall karma indicates overall quality.

9 comments2 min readLW link

Causal Graphs of GPT-2-Small’s Resi­d­ual Stream

David UdellJul 9, 2024, 10:06 PM
53 points

18 votes

Overall karma indicates overall quality.

7 comments7 min readLW link

[Question] If AI starts to end the world, is suicide a good idea?

IlluminateRealityJul 9, 2024, 9:53 PM
0 points

8 votes

Overall karma indicates overall quality.

8 comments1 min readLW link

Ra­tion­al­ist Pu­rity Test

Gunnar_ZarnckeJul 9, 2024, 8:30 PM
−9 points

19 votes

Overall karma indicates overall quality.

5 comments1 min readLW link
(ratpuritytest.com)

That which can be de­stroyed by the truth, should be as­sumed to should be de­stroyed by it

Thac0Jul 9, 2024, 7:39 PM
6 points

4 votes

Overall karma indicates overall quality.

0 comments3 min readLW link

AISN #38: Supreme Court De­ci­sion Could Limit Fed­eral Abil­ity to Reg­u­late AI Plus, “Cir­cuit Break­ers” for AI sys­tems, and up­dates on China’s AI industry

Corin Katzke, Alexa Pan, Julius and Dan H
Jul 9, 2024, 7:28 PM
5 points

2 votes

Overall karma indicates overall quality.

0 comments5 min readLW link
(newsletter.safe.ai)

Sum­mer Tour Stops

jefftkJul 9, 2024, 7:10 PM
10 points

2 votes

Overall karma indicates overall quality.

0 comments3 min readLW link
(www.jefftk.com)

Fix sim­ple mis­takes in ARC-AGI, etc.

Oleg TrottJul 9, 2024, 5:46 PM
9 points

7 votes

Overall karma indicates overall quality.

9 comments1 min readLW link

Paper Sum­mary: The Effects of Com­mu­ni­cat­ing Uncer­tainty on Public Trust in Facts and Numbers

Jeffrey HeningerJul 9, 2024, 4:50 PM
42 points

15 votes

Overall karma indicates overall quality.

2 comments2 min readLW link
(blog.aiimpacts.org)

UC Berkeley course on LLMs and ML Safety

Dan HJul 9, 2024, 3:40 PM
36 points

21 votes

Overall karma indicates overall quality.

1 comment1 min readLW link
(rdi.berkeley.edu)

What and Why: Devel­op­men­tal In­ter­pretabil­ity of Re­in­force­ment Learning

Garrett BakerJul 9, 2024, 2:09 PM
67 points

27 votes

Overall karma indicates overall quality.

4 comments6 min readLW link

Med­i­cal Roundup #3

ZviJul 9, 2024, 1:10 PM
39 points

12 votes

Overall karma indicates overall quality.

4 comments19 min readLW link
(thezvi.wordpress.com)

Con­sent across power differentials

Ramana KumarJul 9, 2024, 11:42 AM
52 points

17 votes

Overall karma indicates overall quality.

12 comments3 min readLW link