Cap­i­tal and in­equal­ity

NathanBarnardAug 15, 2022, 5:23 PM
7 points
2 comments5 min readLW link

[Question] Are there prac­ti­cal ex­er­cises for de­vel­op­ing the Scout mind­set?

ChristianKlAug 15, 2022, 5:23 PM
15 points
2 comments1 min readLW link

[Question] How do you get a job as a soft­ware de­vel­oper?

lsusrAug 15, 2022, 2:45 PM
22 points
24 comments1 min readLW link

The Parable of the Boy Who Cried 5% Chance of Wolf

KatWoodsAug 15, 2022, 2:33 PM
140 points
24 comments2 min readLW link

And the Rev­enues Are So Small

ZviAug 15, 2022, 1:00 PM
19 points
5 comments11 min readLW link
(thezvi.wordpress.com)

Ex­treme Security

lcAug 15, 2022, 12:11 PM
38 points
6 comments5 min readLW link

No short­cuts to knowl­edge: Why AI needs to ease up on scal­ing and learn how to code

YldedlyAug 15, 2022, 8:42 AM
5 points
0 comments1 min readLW link
(deoxyribose.github.io)

Seek­ing In­terns/​RAs for Mechanis­tic In­ter­pretabil­ity Projects

Neel NandaAug 15, 2022, 7:11 AM
61 points
0 comments2 min readLW link

A Mechanis­tic In­ter­pretabil­ity Anal­y­sis of Grokking

Aug 15, 2022, 2:41 AM
373 points
48 comments36 min readLW link1 review
(colab.research.google.com)

[Question] If a nuke is com­ing to­wards SF Bay can peo­ple bunker in BART tun­nels?

Pee DoomAug 15, 2022, 1:56 AM
15 points
2 comments1 min readLW link

[Question] What is the prob­a­bil­ity that a su­per­in­tel­li­gent, sen­tient AGI is ac­tu­ally in­fea­si­ble?

Nathan1123Aug 14, 2022, 10:41 PM
−3 points
6 comments1 min readLW link

Deal­ing With Delusions

adrusiAug 14, 2022, 9:11 PM
9 points
2 comments1 min readLW link

All the posts I will never write

Alexander Gietelink OldenzielAug 14, 2022, 6:29 PM
54 points
8 comments8 min readLW link

Brain-like AGI pro­ject “ain­telope”

Gunnar_ZarnckeAug 14, 2022, 4:33 PM
54 points
2 comments1 min readLW link

AI Trans­parency: Why it’s crit­i­cal and how to ob­tain it.

Zohar JacksonAug 14, 2022, 10:31 AM
6 points
1 comment5 min readLW link

A brief note on Sim­plic­ity Bias

carboniferous_umbraculum Aug 14, 2022, 2:05 AM
20 points
0 comments4 min readLW link

Evolu­tion is a bad anal­ogy for AGI: in­ner alignment

Quintin PopeAug 13, 2022, 10:15 PM
81 points
15 comments8 min readLW link

An Un­canny Prison

Nathan1123Aug 13, 2022, 9:40 PM
3 points
3 comments2 min readLW link

Florida Elections

DoubleAug 13, 2022, 8:10 PM
−3 points
8 comments1 min readLW link

Cul­ti­vat­ing Valiance

Shoshannah TekofskyAug 13, 2022, 6:47 PM
35 points
4 comments4 min readLW link

An ex­tended rocket al­ign­ment analogy

rememberAug 13, 2022, 6:22 PM
28 points
3 comments4 min readLW link

[Question] The OpenAI play­ground for GPT-3 is a ter­rible in­ter­face. Is there any great lo­cal (or web) app for ex­plor­ing/​learn­ing with lan­guage mod­els?

avivAug 13, 2022, 4:34 PM
3 points
1 comment1 min readLW link

[Question] What is an agent in re­duc­tion­ist ma­te­ri­al­ism?

ValentineAug 13, 2022, 3:39 PM
7 points
17 comments1 min readLW link

Refine’s First Blog Post Day

adamShimiAug 13, 2022, 10:23 AM
55 points
3 comments1 min readLW link

The Dumbest Pos­si­ble Gets There First

ArtaxerxesAug 13, 2022, 10:20 AM
44 points
7 comments2 min readLW link

I missed the crux of the al­ign­ment prob­lem the whole time

zeshenAug 13, 2022, 10:11 AM
53 points
7 comments3 min readLW link

Shapes of Mind and Plu­ral­ism in Alignment

adamShimiAug 13, 2022, 10:01 AM
33 points
2 comments2 min readLW link

How I think about alignment

Linda LinseforsAug 13, 2022, 10:01 AM
31 points
11 comments5 min readLW link

Steelmin­ing via Analogy

Paul BricmanAug 13, 2022, 9:59 AM
24 points
0 comments2 min readLW link
(paulbricman.com)

Ap­pendix: Jar­gon Dictionary

CFAR!DuncanAug 13, 2022, 8:09 AM
34 points
5 comments21 min readLW link

Ap­pendix: Ham­ming Questions

CFAR!DuncanAug 13, 2022, 8:07 AM
41 points
0 comments2 min readLW link

Build­ing a Bugs List prompts

CFAR!DuncanAug 13, 2022, 8:00 AM
69 points
9 comments2 min readLW link

Cam­bridge LW Meetup: Con­struc­tive Complaining

Tony WangAug 13, 2022, 4:52 AM
2 points
0 comments1 min readLW link

Gra­di­ent de­scent doesn’t se­lect for in­ner search

Ivan VendrovAug 13, 2022, 4:15 AM
47 points
23 comments4 min readLW link

[Question] How to bet against civ­i­liza­tional ad­e­quacy?

Wei DaiAug 12, 2022, 11:33 PM
54 points
20 comments1 min readLW link

In­fant AI Scenario

Nathan1123Aug 12, 2022, 9:20 PM
1 point
0 comments3 min readLW link

Deep­Mind al­ign­ment team opinions on AGI ruin arguments

VikaAug 12, 2022, 9:06 PM
395 points
37 comments14 min readLW link1 review

Dis­solve: The Petty Crimes of Blaise Pascal

SebastianG Aug 12, 2022, 8:04 PM
17 points
4 comments6 min readLW link

The Host Minds of HBO’s West­world.

NerretAug 12, 2022, 6:53 PM
1 point
0 comments3 min readLW link

What is es­ti­ma­tional pro­gram­ming? Squig­gle in context

QuinnAug 12, 2022, 6:39 PM
14 points
7 comments7 min readLW link

Over­sight Misses 100% of Thoughts The AI Does Not Think

johnswentworthAug 12, 2022, 4:30 PM
111 points
49 comments1 min readLW link

Timelines ex­pla­na­tion post part 1 of ?

Nathan Helm-BurgerAug 12, 2022, 4:13 PM
10 points
1 comment2 min readLW link

A lit­tle play­ing around with Blen­der­bot3

Nathan Helm-BurgerAug 12, 2022, 4:06 PM
9 points
0 comments1 min readLW link

Refin­ing the Sharp Left Turn threat model, part 1: claims and mechanisms

Aug 12, 2022, 3:17 PM
86 points
4 comments3 min readLW link1 review
(vkrakovna.wordpress.com)

Ar­gu­ment by In­tel­lec­tual Ordeal

lcAug 12, 2022, 1:03 PM
26 points
5 comments5 min readLW link

Anti-squat­ted AI x-risk do­mains index

plexAug 12, 2022, 12:01 PM
59 points
6 comments1 min readLW link

[Question] Perfect Predictors

aditya malikAug 12, 2022, 11:51 AM
2 points
5 comments1 min readLW link

[Question] What are some good ar­gu­ments against build­ing new nu­clear power plants?

RomanSAug 12, 2022, 7:32 AM
16 points
15 comments2 min readLW link

Seek­ing PCK (Ped­a­gog­i­cal Con­tent Knowl­edge)

CFAR!DuncanAug 12, 2022, 4:15 AM
62 points
11 comments5 min readLW link

Ar­tifi­cial in­tel­li­gence wireheading

Big TonyAug 12, 2022, 3:06 AM
5 points
2 comments1 min readLW link