Galaxy Trucker Needs a New Se­cond Half

jefftk7 Sep 2022 20:10 UTC
13 points
7 comments1 min readLW link
(www.jefftk.com)

[Question] In a lack of data, how should you weigh cre­dences in the­o­ret­i­cal physics’s The­o­ries of Every­thing, or TOEs?

Noosphere897 Sep 2022 18:25 UTC
7 points
11 comments1 min readLW link

Gen­er­a­tors Of Disagree­ment With AI Alignment

George3d67 Sep 2022 18:15 UTC
27 points
9 comments9 min readLW link
(www.epistem.ink)

Shröd­inger’s lot­tery or: Why you are go­ing to live forever

Chase Dowdell7 Sep 2022 18:13 UTC
1 point
2 comments4 min readLW link

Is train­ing data go­ing to be diluted by AI-gen­er­ated con­tent?

Hannes Thurnherr7 Sep 2022 18:13 UTC
10 points
7 comments1 min readLW link

It’s (not) how you use it

Eleni Angelou7 Sep 2022 17:15 UTC
8 points
1 comment2 min readLW link

First we shape our so­cial graph; then it shapes us

Henrik Karlsson7 Sep 2022 15:50 UTC
52 points
6 comments8 min readLW link
(escapingflatland.substack.com)

AI-as­sisted list of ten con­crete al­ign­ment things to do right now

lukehmiles7 Sep 2022 8:38 UTC
8 points
5 comments4 min readLW link

Can “Re­ward Eco­nomics” solve AI Align­ment?

Q Home7 Sep 2022 7:58 UTC
3 points
15 comments18 min readLW link

Is there a list of pro­jects to get started with In­ter­pretabil­ity?

Franziska Fischer7 Sep 2022 4:27 UTC
8 points
2 comments1 min readLW link

Progress Re­port 7: mak­ing GPT go hur­rdurr in­stead of brrrrrrr

Nathan Helm-Burger7 Sep 2022 3:28 UTC
21 points
0 comments4 min readLW link

Fram­ing AI Childhoods

David Udell6 Sep 2022 23:40 UTC
37 points
8 comments4 min readLW link

Deleted com­ments archive

Said Achmiz6 Sep 2022 21:54 UTC
9 points
3 comments1 min readLW link

Guitar Pedals on Fiddle

jefftk6 Sep 2022 19:30 UTC
10 points
0 comments2 min readLW link
(www.jefftk.com)

Re­jected Early Drafts of New­comb’s Problem

zahmahkibo6 Sep 2022 19:04 UTC
112 points
5 comments3 min readLW link

[Question] How can we se­cure more re­search po­si­tions at our uni­ver­si­ties for x-risk re­searchers?

Neil Crawford6 Sep 2022 17:17 UTC
11 points
0 comments1 min readLW link

Com­mu­nity Build­ing for Grad­u­ate Stu­dents: A Tar­geted Approach

Neil Crawford6 Sep 2022 17:17 UTC
6 points
0 comments4 min readLW link

How Josiah be­came an AI safety researcher

Neil Crawford6 Sep 2022 17:17 UTC
4 points
0 comments1 min readLW link

No, hu­man brains are not (much) more effi­cient than computers

Jesse Hoogland6 Sep 2022 13:53 UTC
20 points
21 comments3 min readLW link
(www.jessehoogland.com)

On oxy­tocin-sen­si­tive neu­rons in au­di­tory cortex

Steven Byrnes6 Sep 2022 12:54 UTC
32 points
6 comments12 min readLW link

EA & LW Fo­rums Weekly Sum­mary (28 Aug − 3 Sep 22’)

Zoe Williams6 Sep 2022 11:06 UTC
51 points
2 comments14 min readLW link

Alex Lawsen On Fore­cast­ing AI Progress

Michaël Trazzi6 Sep 2022 9:32 UTC
18 points
0 comments2 min readLW link
(theinsideview.ai)

What are you for?

lsusr6 Sep 2022 3:32 UTC
42 points
5 comments1 min readLW link

The Power (and limits?) of Chunking

NicholasKross6 Sep 2022 2:26 UTC
8 points
2 comments1 min readLW link

Another Un­phrased B-part

jefftk6 Sep 2022 1:30 UTC
10 points
0 comments2 min readLW link
(www.jefftk.com)

[Ex­plo­ra­tory] Be­com­ing more Agentic

Johannes C. Mayer6 Sep 2022 0:45 UTC
6 points
1 comment1 min readLW link

AI Gover­nance Needs Tech­ni­cal Work

Mau5 Sep 2022 22:28 UTC
41 points
1 comment8 min readLW link

pro­gram searches

Tamsin Leake5 Sep 2022 20:04 UTC
21 points
2 comments2 min readLW link
(carado.moe)

Over­ton Gym­nas­tics: An Ex­er­cise in Discomfort

5 Sep 2022 19:20 UTC
40 points
15 comments4 min readLW link

The Good King

GregorDeVillain5 Sep 2022 19:17 UTC
−6 points
0 comments13 min readLW link

Beta Read­ers are Great

HoldenKarnofsky5 Sep 2022 19:10 UTC
28 points
0 comments1 min readLW link
(www.cold-takes.com)

Im­pact Shares For Spec­u­la­tive Projects

Elizabeth5 Sep 2022 18:00 UTC
30 points
8 comments7 min readLW link
(acesounderglass.com)

An un­offi­cial “High­lights from the Se­quences” tier list

Akash5 Sep 2022 14:07 UTC
29 points
1 comment5 min readLW link

A Game About AI Align­ment (& Meta-Ethics): What Are the Must Haves?

JonathanErhardt5 Sep 2022 7:55 UTC
18 points
15 comments2 min readLW link

[Ex­plo­ra­tory] What does it mean that an ex­per­i­ment is high bit?

Johannes C. Mayer5 Sep 2022 3:13 UTC
5 points
0 comments2 min readLW link

(Link) I’m Miss­ing a Chunk of My Brain

mukashi5 Sep 2022 2:10 UTC
13 points
2 comments1 min readLW link
(www.nytimes.com)

THE 3 WILLPOWER KEYS

GregorDeVillain4 Sep 2022 22:57 UTC
−11 points
0 comments4 min readLW link

What’s your Mis­sion?

GregorDeVillain4 Sep 2022 18:52 UTC
−4 points
1 comment6 min readLW link

EA, Ve­ganism and Nega­tive An­i­mal Utilitarianism

Yair Halberstadt4 Sep 2022 18:30 UTC
9 points
12 comments1 min readLW link

The ethics of re­clin­ing air­plane seats

braces4 Sep 2022 17:59 UTC
92 points
70 comments1 min readLW link

Rus­sian Food for Petrov Day

weft4 Sep 2022 17:57 UTC
17 points
5 comments1 min readLW link

Pro­to­typ­ing in C

jefftk4 Sep 2022 17:50 UTC
19 points
11 comments2 min readLW link
(www.jefftk.com)

Turn your flash­cards into Art

Heye Groß4 Sep 2022 17:31 UTC
16 points
2 comments1 min readLW link

Let’s Ter­raform West Texas

blackstampede4 Sep 2022 16:24 UTC
87 points
33 comments5 min readLW link

[Question] Help me find a good Hackathon sub­ject

Charbel-Raphaël4 Sep 2022 8:40 UTC
6 points
18 comments1 min readLW link

Bay Sols­tice 2022 Call For Volunteers

Scott Alexander4 Sep 2022 6:44 UTC
43 points
2 comments1 min readLW link

The shard the­ory of hu­man values

4 Sep 2022 4:28 UTC
235 points
66 comments24 min readLW link2 reviews

Break­ing New­comb’s Prob­lem with Non-Halt­ing states

Slimepriestess4 Sep 2022 4:01 UTC
18 points
9 comments5 min readLW link

Monthly Shorts 8/​22

Celer4 Sep 2022 2:30 UTC
3 points
0 comments7 min readLW link
(keller.substack.com)

Fully Live Elec­tronic Contra

jefftk4 Sep 2022 1:30 UTC
9 points
0 comments1 min readLW link
(www.jefftk.com)