Vi­sion Week­end US Edition

Allison DuettmannSep 20, 2023, 9:28 PM
4 points
0 comments1 min readLW link

Fore­sight Vi­sion Week­end Europe Edition

Allison DuettmannSep 20, 2023, 9:25 PM
3 points
0 comments1 min readLW link

Notes on ChatGPT’s “mem­ory” for strings and for events

Bill BenzonSep 20, 2023, 6:12 PM
3 points
0 comments10 min readLW link

Belief and the Truth

Sam I amSep 20, 2023, 5:38 PM
2 points
14 comments5 min readLW link
(open.substack.com)

Image Hi­jacks: Ad­ver­sar­ial Images can Con­trol Gen­er­a­tive Models at Runtime

Sep 20, 2023, 3:23 PM
58 points
9 comments1 min readLW link
(arxiv.org)

In­ter­pretabil­ity Ex­ter­nal­ities Case Study—Hun­gry Hun­gry Hippos

Magdalena WacheSep 20, 2023, 2:42 PM
64 points
22 comments2 min readLW link

An Ele­men­tary In­tro­duc­tion to In­fra-Bayesianism

CharlesRWSep 20, 2023, 2:29 PM
16 points
0 comments1 min readLW link

Weekly In­ci­dence In­clud­ing Delay

jefftkSep 20, 2023, 2:00 PM
11 points
0 comments2 min readLW link
(www.jefftk.com)

[Question] The stereo­type of male clas­si­cal mu­sic lovers be­ing gay

BB6Sep 20, 2023, 1:23 PM
11 points
6 comments1 min readLW link

Hous­ing Roundup #6

ZviSep 20, 2023, 1:10 PM
27 points
8 comments14 min readLW link
(thezvi.wordpress.com)

Care­less talk on US-China AI com­pe­ti­tion? (and crit­i­cism of CAIS cov­er­age)

Oliver SourbutSep 20, 2023, 12:46 PM
16 points
3 comments10 min readLW link3 reviews
(www.oliversourbut.net)

A New Bayesian De­ci­sion Theory

Pareto OptimalSep 20, 2023, 9:36 AM
−6 points
0 comments1 min readLW link
(paretooptimal.substack.com)

Protest against Meta’s ir­re­versible pro­lifer­a­tion (Sept 29, San Fran­cisco)

Holly_ElmoreSep 19, 2023, 11:40 PM
54 points
33 commentsLW link

The AI Ex­plo­sion Might Never Happen

snewmanSep 19, 2023, 11:20 PM
22 points
31 comments9 min readLW link

Science of Deep Learn­ing more tractably ad­dresses the Sharp Left Turn than Agent Foundations

NickGabsSep 19, 2023, 10:06 PM
20 points
2 comments6 min readLW link

For­mal­iz­ing «Boundaries» with Markov blankets

ChipmonkSep 19, 2023, 9:01 PM
21 points
20 comments3 min readLW link

Pre­ci­sion of Sets of Forecasts

niplavSep 19, 2023, 6:19 PM
20 points
5 comments10 min readLW link

The Proxy Poli­ti­cal Party

antidefaultSep 19, 2023, 5:47 PM
−3 points
4 comments1 min readLW link
(antidefault.net)

The Limits of the Ex­is­tence Proof Ar­gu­ment for Gen­eral Intelligence

Amadeus PagelSep 19, 2023, 5:45 PM
−21 points
3 comments1 min readLW link
(amadeuspagel.com)

[Question] Is there a pub­li­cly available list of ex­am­ples of fron­tier model ca­pa­bil­ities?

Max KearneySep 19, 2023, 5:45 PM
1 point
0 comments1 min readLW link

Tal­linn, Es­to­nia – ACX Mee­tups Every­where Au­tumn 2023

AndrewSep 19, 2023, 4:24 PM
1 point
0 comments1 min readLW link

An­thropic’s Re­spon­si­ble Scal­ing Policy & Long-Term Benefit Trust

Zac Hatfield-DoddsSep 19, 2023, 3:09 PM
85 points
26 comments3 min readLW link1 review
(www.anthropic.com)

AISN #22: The Land­scape of US AI Leg­is­la­tion - Hear­ings, Frame­works, Bills, and Laws

Dan HSep 19, 2023, 2:44 PM
20 points
0 comments5 min readLW link
(newsletter.safe.ai)

Com­pila­tion of Profit for Good Redteam­ing and Responses

Brad West Sep 19, 2023, 1:34 PM
1 point
0 comments9 min readLW link

[Link post] Michael Niel­sen’s “Notes on Ex­is­ten­tial Risk from Ar­tifi­cial Su­per­in­tel­li­gence”

Joel BeckerSep 19, 2023, 1:31 PM
67 points
12 commentsLW link
(michaelnotebook.com)

[Question] Do LLMs Im­ple­ment NLP Al­gorithms for Bet­ter Next To­ken Pre­dic­tions?

simeon_cSep 19, 2023, 12:28 PM
5 points
1 comment1 min readLW link

On martingales

Joey MarcellinoSep 19, 2023, 11:39 AM
8 points
4 comments4 min readLW link

Luck based medicine: an­gry el­dritch sugar gods edition

ElizabethSep 19, 2023, 4:40 AM
75 points
14 comments9 min readLW link
(acesounderglass.com)

Don’t Think About the Thing Be­hind the Cur­tain.

keltanSep 19, 2023, 2:07 AM
4 points
0 comments5 min readLW link

Panel with Is­raeli Prime Minister on ex­is­ten­tial risk from AI

Michaël TrazziSep 18, 2023, 11:16 PM
22 points
2 comments1 min readLW link
(x.com)

Some rea­sons why I fre­quently pre­fer com­mu­ni­cat­ing via text

Adam ZernerSep 18, 2023, 9:50 PM
53 points
18 comments2 min readLW link

Why I Don’t Believe The Law of the Ex­cluded Middle

Thoth HermesSep 18, 2023, 6:53 PM
−11 points
46 comments5 min readLW link
(thothhermes.substack.com)

Fore­cast­ing for Policy (FORPOL) - Main take­aways, prac­ti­cal learn­ings & report

janklenhaSep 18, 2023, 5:44 PM
2 points
0 comments4 min readLW link

The Talk: a brief ex­pla­na­tion of sex­ual dimorphism

MalmesburySep 18, 2023, 4:23 PM
527 points
77 comments16 min readLW link3 reviews

[Question] Where might I di­rect promis­ing-to-me re­searchers to ap­ply for al­ign­ment jobs/​grants?

abramdemskiSep 18, 2023, 4:20 PM
45 points
10 comments1 min readLW link

[Re­view] Move First, Think Later: Sense and Non­sense in Im­prov­ing Your Chess

Arjun PanicksserySep 18, 2023, 3:10 PM
33 points
2 comments6 min readLW link
(arjunpanickssery.substack.com)

Tech­ni­cal AI Safety Re­search Land­scape [Slides]

Magdalena WacheSep 18, 2023, 1:56 PM
42 points
0 comments4 min readLW link

The om­ni­zoid—Heighn FDT De­bate #5

HeighnSep 18, 2023, 11:54 AM
4 points
0 comments3 min readLW link

Ask for Feel­ings not Tunes

jefftkSep 18, 2023, 2:10 AM
11 points
0 comments1 min readLW link
(www.jefftk.com)

Three ways in­ter­pretabil­ity could be impactful

Arthur ConmySep 18, 2023, 1:02 AM
47 points
8 comments4 min readLW link

Show LW: Get a phone call if pre­dic­tion mar­kets pre­dict nu­clear war

LorenzoSep 17, 2023, 10:25 PM
35 points
8 comments1 min readLW link
(recursing.github.io)

Microdooms averted by work­ing on AI Safety

Nikola JurkovicSep 17, 2023, 9:46 PM
34 points
3 comments3 min readLW link
(forum.effectivealtruism.org)

Eu­gen­ics Performed By A Blind, Idiot God

Bentham's BulldogSep 17, 2023, 8:37 PM
63 points
11 comments2 min readLW link

Ac­tu­ally, “per­sonal at­tacks af­ter ob­ject-level ar­gu­ments” is a pretty good rule of epistemic conduct

Max HSep 17, 2023, 8:25 PM
37 points
15 comments7 min readLW link

Joseph Bloom on choos­ing AI Align­ment over bio, what many as­piring re­searchers get wrong, and more (in­ter­view)

Sep 17, 2023, 6:45 PM
27 points
2 comments8 min readLW link

Cat­a­lyst books

CatneeSep 17, 2023, 5:05 PM
7 points
2 comments1 min readLW link

Telopheme, telophore, and telotect

TsviBTSep 17, 2023, 4:24 PM
46 points
7 comments8 min readLW link

How to think about slow­ing AI

Zach Stein-PerlmanSep 17, 2023, 4:00 PM
14 points
2 comments3 min readLW link
(forum.effectivealtruism.org)

Book Re­view: Con­scious­ness Ex­plained (as the Great Cat­a­lyst)

Rafael HarthSep 17, 2023, 3:30 PM
23 points
14 comments22 min readLW link1 review

Reflex­ive de­ci­sion the­ory is an un­solved problem

Richard_KennawaySep 17, 2023, 2:15 PM
40 points
27 comments4 min readLW link