When does ex­ter­nal be­havi­our im­ply in­teral struc­ture?

Tyler Tracy31 May 2024 16:41 UTC
6 points
5 comments7 min readLW link

[Question] We might be drop­ping the ball on Au­tonomous Repli­ca­tion and Adap­ta­tion.

31 May 2024 13:49 UTC
61 points
30 comments4 min readLW link

Tax Cuts and Innovation

Maxwell Tabarrok31 May 2024 12:58 UTC
3 points
0 comments6 min readLW link
(www.maximum-progress.com)

The Gem­ini 1.5 Report

Zvi31 May 2024 12:20 UTC
18 points
0 comments17 min readLW link
(thezvi.wordpress.com)

Less Anti-Dakka

Mateusz Bagiński31 May 2024 9:07 UTC
23 points
5 comments3 min readLW link

Web-sur­fing tips for strange times

eukaryote31 May 2024 7:10 UTC
48 points
19 comments9 min readLW link
(eukaryotewritesblog.substack.com)

There Should Be More Align­ment-Driven Startups

31 May 2024 2:05 UTC
60 points
14 comments11 min readLW link

[Question] How likely is it that AI will tor­ture us un­til the end of time?

Damilo31 May 2024 1:26 UTC
4 points
24 comments2 min readLW link

Twin Peaks: un­der the air

KatjaGrace31 May 2024 1:20 UTC
25 points
2 comments2 min readLW link
(worldspiritsockpuppet.com)

Is suffer­ing like shit?

KatjaGrace31 May 2024 1:20 UTC
32 points
5 comments1 min readLW link
(worldspiritsockpuppet.com)

Fore­sight Vi­sion Week­end Europe 2024

Allison Duettmann31 May 2024 0:07 UTC
3 points
0 comments1 min readLW link

[Question] How have analo­gous In­dus­tries solved In­ter­ested > Trained > Em­ployed bot­tle­necks?

yanni kyriacos30 May 2024 23:59 UTC
4 points
1 comment1 min readLW link

Duck­bill Masks Bet­ter?

jefftk30 May 2024 23:40 UTC
20 points
3 comments1 min readLW link
(www.jefftk.com)

OpenAI: He­len Toner Speaks

Zvi30 May 2024 21:10 UTC
86 points
8 comments13 min readLW link
(thezvi.wordpress.com)

Non-Dis­par­age­ment Ca­naries for OpenAI

30 May 2024 19:20 UTC
287 points
51 comments2 min readLW link

Clar­ify­ing METR’s Au­dit­ing Role

Beth Barnes30 May 2024 18:41 UTC
108 points
1 comment2 min readLW link

A civ­i­liza­tion ran by amateurs

Olli Järviniemi30 May 2024 17:57 UTC
61 points
7 comments6 min readLW link

One week left to ap­ply for the Roots of Progress Blog-Build­ing Intensive

jasoncrawford30 May 2024 16:55 UTC
8 points
0 comments3 min readLW link
(rootsofprogress.org)

Get­ting started with AI Align­ment re­search: how to re­pro­duce an ex­per­i­ment from re­search paper

Alexander23030 May 2024 14:51 UTC
3 points
0 comments3 min readLW link

AI #66: Oh to Be Less Online

Zvi30 May 2024 14:20 UTC
37 points
6 comments56 min readLW link
(thezvi.wordpress.com)

The 27 papers

WitheringWeights30 May 2024 8:46 UTC
18 points
2 comments1 min readLW link

Help me to be­come “less wrong”

milanrosko30 May 2024 8:29 UTC
10 points
7 comments2 min readLW link

The Mar­ket Sin­gu­lar­ity: A New Perspective

azsantosk30 May 2024 7:05 UTC
1 point
0 comments15 min readLW link

Awakening

lsusr30 May 2024 7:03 UTC
118 points
79 comments9 min readLW link

Value Claims (In Par­tic­u­lar) Are Usu­ally Bullshit

johnswentworth30 May 2024 6:26 UTC
143 points
18 comments2 min readLW link

The Pearly Gates

lsusr30 May 2024 4:01 UTC
111 points
6 comments3 min readLW link

AXRP Epi­sode 32 - Un­der­stand­ing Agency with Jan Kulveit

DanielFilan30 May 2024 3:50 UTC
20 points
0 comments53 min readLW link

US Pres­i­den­tial Elec­tion: Tractabil­ity, Im­por­tance, and Ur­gency

kuhanj29 May 2024 23:52 UTC
42 points
2 comments3 min readLW link

San Fran­cisco ACX Meetup “First Satur­day”

Nate Sternberg29 May 2024 23:42 UTC
2 points
1 comment1 min readLW link

Thoughts on SB-1047

ryan_greenblatt29 May 2024 23:26 UTC
59 points
1 comment11 min readLW link

How I de­signed my own writ­ing sys­tem, VJScript

vkethana29 May 2024 23:18 UTC
2 points
1 comment1 min readLW link
(www.vkethana.com)

AI and integrity

Nathan Young29 May 2024 20:45 UTC
10 points
0 comments2 min readLW link
(nathanpmyoung.substack.com)

MIRI 2024 Com­mu­ni­ca­tions Strategy

Gretta Duleba29 May 2024 19:33 UTC
319 points
202 comments7 min readLW link

2024 Sum­mer AI Safety In­tro Fel­low­ship and So­cials in Boston

KevinWei29 May 2024 18:27 UTC
8 points
0 comments1 min readLW link

Apollo Re­search 1-year update

29 May 2024 17:44 UTC
93 points
0 comments7 min readLW link

Re­sponse to nos­talge­braist: proudly wav­ing my moral-an­tire­al­ist bat­tle flag

Steven Byrnes29 May 2024 16:48 UTC
102 points
29 comments11 min readLW link

Look­ing be­yond Everett in mul­ti­ver­sal views of LLMs

kromem29 May 2024 12:35 UTC
10 points
0 comments8 min readLW link

[Question] Invit­ing dis­cus­sion of “Beat AI: A con­test us­ing philo­soph­i­cal con­cepts”

David James29 May 2024 11:55 UTC
2 points
1 comment1 min readLW link

AI com­pa­nies’ commitments

Zach Stein-Perlman29 May 2024 11:00 UTC
36 points
0 comments1 min readLW link

One way vi­o­linists fail

Solenoid_Entity29 May 2024 4:08 UTC
33 points
5 comments3 min readLW link

Hardshipification

Jonathan Moregård28 May 2024 20:02 UTC
84 points
17 comments2 min readLW link
(honestliving.substack.com)

When Are Cir­cu­lar Defi­ni­tions A Prob­lem?

johnswentworth28 May 2024 20:00 UTC
68 points
15 comments3 min readLW link

Notes on Gracefulness

David Gross28 May 2024 18:40 UTC
19 points
2 comments25 min readLW link

[Question] What’s a bet­ter term now that “AGI” is too vague?

Seth Herd28 May 2024 18:02 UTC
15 points
9 comments2 min readLW link

Re­ward hack­ing be­hav­ior can gen­er­al­ize across tasks

28 May 2024 16:33 UTC
78 points
5 comments21 min readLW link

Quick Ad­vice on Writ­ing Essays

Niko_McCarty28 May 2024 15:02 UTC
10 points
0 comments3 min readLW link
(www.nikomccarty.com)

[Linkpost] The Ex­pres­sive Ca­pac­ity of State Space Models: A For­mal Lan­guage Perspective

Bogdan Ionut Cirstea28 May 2024 13:49 UTC
4 points
3 comments1 min readLW link
(arxiv.org)

OpenAI: Fallout

Zvi28 May 2024 13:20 UTC
204 points
25 comments36 min readLW link
(thezvi.wordpress.com)

2024 State of the AI Reg­u­la­tory Land­scape

28 May 2024 11:59 UTC
30 points
0 comments2 min readLW link
(www.convergenceanalysis.org)

Find­ing Back­ward Chain­ing Cir­cuits in Trans­form­ers Trained on Tree Search

28 May 2024 5:29 UTC
50 points
1 comment9 min readLW link
(arxiv.org)