Out of the Box

jesseduffieldNov 13, 2023, 11:43 PM
5 points
1 comment7 min readLW link

Loudly Give Up, Don’t Quietly Fade

ScrewtapeNov 13, 2023, 11:30 PM
165 points
12 comments6 min readLW link1 review

Great Em­pa­thy and Great Re­sponse Ability

positivesumNov 13, 2023, 11:04 PM
16 points
0 comments3 min readLW link
(tryingtruly.substack.com)

The­o­ries of Change for AI Auditing

Nov 13, 2023, 7:33 PM
54 points
0 comments18 min readLW link
(www.apolloresearch.ai)

They are made of re­peat­ing patterns

quetzal_rainbowNov 13, 2023, 6:17 PM
53 points
4 comments2 min readLW link

How to Upload a Mind (In Three Not-So-Easy Steps)

Nov 13, 2023, 6:13 PM
26 points
0 comments7 min readLW link
(youtu.be)

Non-my­opia stories

lberglundNov 13, 2023, 5:52 PM
29 points
10 comments7 min readLW link

It’s OK to eat shrimp: EAs Make In­valid In­fer­ences About Fish Qualia and Mo­ral Patienthood

Mikhail SaminNov 13, 2023, 4:51 PM
0 points
17 commentsLW link

Sugges­tions for chess puzzles

ZaneNov 13, 2023, 3:39 PM
13 points
1 comment1 min readLW link

Why small phe­nomenons are rele­vant to moral­ity ​

Ryo Nov 13, 2023, 3:25 PM
1 point
0 comments3 min readLW link

Op­tion­al­ity ap­proach to ethics

Ryo Nov 13, 2023, 3:23 PM
7 points
2 comments3 min readLW link

Redi­rect­ing one’s own taxes as an effec­tive al­tru­ism method

David GrossNov 13, 2023, 3:17 PM
−5 points
34 comments16 min readLW link

AISC Pro­ject: Bench­marks for Stable Reflectivity

jacquesthibsNov 13, 2023, 2:51 PM
17 points
0 comments8 min readLW link

Re­search Adenda: Model­ling Tra­jec­to­ries of Lan­guage Models

NickyPNov 13, 2023, 2:33 PM
28 points
0 comments12 min readLW link

Bostrom Goes Unheard

ZviNov 13, 2023, 2:11 PM
81 points
9 comments18 min readLW link

Novem­ber hang­out in Warsaw

ntoxegNov 13, 2023, 1:20 PM
1 point
1 comment1 min readLW link

The Science Al­gorithm AISC Project

Johannes C. MayerNov 13, 2023, 12:52 PM
12 points
0 comments1 min readLW link
(docs.google.com)

You can just spon­ta­neously call peo­ple you haven’t met in years

lcNov 13, 2023, 5:21 AM
167 points
21 comments1 min readLW link

Zvi’s Man­i­fold Mar­kets House Rules

ZviNov 13, 2023, 12:28 AM
53 points
6 comments3 min readLW link

[Question] What’s your best util­i­tar­ian model for risk­ing your best kid­neys?

IlioNov 12, 2023, 11:01 PM
−3 points
4 comments1 min readLW link

Helpful ex­am­ples to get a sense of mod­ern au­to­mated manipulation

trevorNov 12, 2023, 8:49 PM
33 points
4 comments9 min readLW link

The Snug­gle/​Date/​Slap Protocol

MadHatterNov 12, 2023, 8:44 PM
−21 points
4 comments2 min readLW link

Two chil­dren’s stories

Optimization ProcessNov 12, 2023, 8:29 PM
10 points
1 comment7 min readLW link

The Fun­da­men­tal The­o­rem for mea­surable fac­tor spaces

Matthias G. MayerNov 12, 2023, 7:25 PM
38 points
2 comments2 min readLW link

How ac­cu­rate are stan­dard Dark Triad per­son­al­ity scales?

jamesbillNov 12, 2023, 8:21 AM
0 points
2 comments2 min readLW link

[Question] What ML gears do you like?

Ulisse MiniNov 11, 2023, 7:10 PM
25 points
4 comments1 min readLW link

Smart Ses­sions—Fi­nally a (kinda) win­dow-cen­tric ses­sion manager

Eli TyreNov 11, 2023, 6:54 PM
14 points
3 comments5 min readLW link

AISC pro­ject: Satis­fIA – AI that satis­fies with­out over­do­ing it

Jobst HeitzigNov 11, 2023, 6:22 PM
12 points
0 comments1 min readLW link
(docs.google.com)

Con­trol Sym­me­try: why we might want to start in­ves­ti­gat­ing asym­met­ric al­ign­ment interventions

domenicrosatiNov 11, 2023, 5:27 PM
25 points
1 comment2 min readLW link

Game The­ory with­out Argmax [Part 2]

Cleo NardoNov 11, 2023, 4:02 PM
31 points
14 comments13 min readLW link

Game The­ory with­out Argmax [Part 1]

Cleo NardoNov 11, 2023, 3:59 PM
70 points
18 comments19 min readLW link

It’s OK to be bi­ased to­wards humans

dr_sNov 11, 2023, 11:59 AM
54 points
69 comments6 min readLW link

The Top AI Safety Bets for 2023: GiveWiki’s Lat­est Recommendations

Dawn DrescherNov 11, 2023, 9:04 AM
3 points
2 commentsLW link

Ar­tifi­cial Gen­eral Horsiness

robotelvisNov 11, 2023, 5:15 AM
4 points
0 comments5 min readLW link
(messyprogress.substack.com)

Pal­isade is hiring Re­search Engineers

Nov 11, 2023, 3:09 AM
23 points
0 comments3 min readLW link

Open Phil re­leases RFPs on LLM Bench­marks and Forecasting

LawrenceCNov 11, 2023, 3:01 AM
53 points
0 comments2 min readLW link
(www.openphilanthropy.org)

Memo on some ne­glected topics

Lukas FinnvedenNov 11, 2023, 2:01 AM
28 points
2 commentsLW link
(open.substack.com)

Who is Sam Bankman-Fried (SBF) re­ally, and how could he have done what he did? - three the­o­ries and a lot of evidence

spencergNov 11, 2023, 1:04 AM
36 points
28 commentsLW link
(www.spencergreenberg.com)

Sur­vey on the ac­cel­er­a­tion risks of our new RFPs to study LLM capabilities

Ajeya CotraNov 10, 2023, 11:59 PM
27 points
1 commentLW link

Rat Fest 2024

LoganChipkinNov 10, 2023, 11:25 PM
7 points
6 comments1 min readLW link

How I Think, Part Three: Weigh­ing Cryonics

Richard HenageNov 10, 2023, 10:21 PM
4 points
1 comment2 min readLW link

Lin­ear en­cod­ing of char­ac­ter-level in­for­ma­tion in GPT-J to­ken embeddings

Nov 10, 2023, 10:19 PM
34 points
4 comments28 min readLW link

Fol­low-up sur­vey: inositol

ElizabethNov 10, 2023, 7:30 PM
13 points
1 comment1 min readLW link
(acesounderglass.com)

We have promis­ing al­ign­ment plans with low taxes

Seth HerdNov 10, 2023, 6:51 PM
44 points
9 comments5 min readLW link

[Question] Vec­tor search on a large dataset?

camsdixonNov 10, 2023, 6:43 PM
−1 points
2 comments1 min readLW link

About Me

Abe DillonNov 10, 2023, 6:32 PM
3 points
0 comments1 min readLW link

Me­tac­u­lus In­tro­duces AI-Pow­ered Com­mu­nity In­sights to Re­veal Fac­tors Driv­ing User Forecasts

ChristianWilliamsNov 10, 2023, 5:57 PM
6 points
0 commentsLW link
(www.metaculus.com)

Joy in the Here and Real

ScrewtapeNov 10, 2023, 5:22 PM
18 points
0 comments2 min readLW link

Arte­facts gen­er­ated by mode col­lapse in GPT-4 Turbo serve as ad­ver­sar­ial at­tacks.

Sohaib ImranNov 10, 2023, 3:23 PM
11 points
0 comments2 min readLW link

Wastew­a­ter RNA Read Lengths

jefftkNov 10, 2023, 3:20 PM
13 points
0 comments4 min readLW link
(www.jefftk.com)