Con­tra pa­pers claiming su­per­hu­man AI forecasting

12 Sep 2024 18:10 UTC
180 points
16 comments7 min readLW link

OpenAI o1

Zach Stein-Perlman12 Sep 2024 17:30 UTC
147 points
41 comments1 min readLW link

How to Give in to Threats (with­out in­cen­tiviz­ing them)

Mikhail Samin12 Sep 2024 15:55 UTC
51 points
26 comments5 min readLW link

Open Prob­lems in AIXI Agent Foundations

Cole Wyeth12 Sep 2024 15:38 UTC
35 points
2 comments10 min readLW link

On the de­struc­tion of Amer­ica’s best high school

Chris_Leong12 Sep 2024 15:30 UTC
−6 points
7 comments1 min readLW link
(scottaaronson.blog)

Op­ti­mis­ing un­der ar­bi­trar­ily many con­straint equations

dkl912 Sep 2024 14:59 UTC
6 points
0 comments3 min readLW link
(dkl9.net)

AI #81: Alpha Proteo

Zvi12 Sep 2024 13:00 UTC
59 points
3 comments35 min readLW link
(thezvi.wordpress.com)

[Question] When can I be nu­mer­ate?

FinalFormal212 Sep 2024 4:05 UTC
25 points
3 comments1 min readLW link

A Non­con­struc­tive Ex­is­tence Proof of Aligned Superintelligence

Roko12 Sep 2024 3:20 UTC
0 points
78 comments1 min readLW link
(transhumanaxiology.substack.com)

Col­laps­ing the Belief/​Knowl­edge Distinction

Jeremias11 Sep 2024 21:24 UTC
−7 points
8 comments1 min readLW link

[Paper] Pro­gram­ming Re­fusal with Con­di­tional Ac­ti­va­tion Steering

Bruce W. Lee11 Sep 2024 20:57 UTC
41 points
0 comments11 min readLW link
(arxiv.org)

Check­ing pub­lic figures on whether they “an­swered the ques­tion” quick anal­y­sis from Har­ris/​Trump de­bate, and a proposal

david reinstein11 Sep 2024 20:25 UTC
7 points
4 comments1 min readLW link
(open.substack.com)

AI Safety Newslet­ter #41: The Next Gen­er­a­tion of Com­pute Scale Plus, Rank­ing Models by Sus­cep­ti­bil­ity to Jailbreak­ing, and Ma­chine Ethics

11 Sep 2024 19:14 UTC
5 points
1 comment5 min readLW link
(newsletter.safe.ai)

Re­fac­tor­ing cry­on­ics as struc­tural brain preservation

Andy_McKenzie11 Sep 2024 18:36 UTC
102 points
14 comments3 min readLW link

[Question] Is this a Pivotal Weak Act? Creat­ing bac­te­ria that de­com­pose metal

doomyeser11 Sep 2024 18:07 UTC
9 points
9 comments3 min readLW link

How to dis­cover the na­ture of sen­tience, and ethics

Gustavo Ramires11 Sep 2024 17:22 UTC
−2 points
4 comments5 min readLW link

Seek­ing Mechanism De­signer for Re­search into In­ter­nal­iz­ing Catas­trophic Externalities

c.trout11 Sep 2024 15:09 UTC
24 points
2 comments3 min readLW link

Could Things Be Very Differ­ent?—How His­tor­i­cal In­er­tia Might Blind Us To Op­ti­mal Solutions

James Stephen Brown11 Sep 2024 9:53 UTC
5 points
0 comments8 min readLW link
(nonzerosum.games)

Re­for­ma­tive Hypocrisy, and Pay­ing Close Enough At­ten­tion to Selec­tively Re­ward It.

Andrew_Critch11 Sep 2024 4:41 UTC
53 points
11 comments3 min readLW link

A nec­es­sary Mem­brane for­mal­ism feature

ThomasCederborg10 Sep 2024 21:33 UTC
20 points
6 comments11 min readLW link

For­mal­iz­ing the In­for­mal (event in­vite)

abramdemski10 Sep 2024 19:22 UTC
42 points
0 comments1 min readLW link

AI #80: Never Have I Ever

Zvi10 Sep 2024 17:50 UTC
45 points
20 comments39 min readLW link
(thezvi.wordpress.com)

The Best Lay Ar­gu­ment is not a Sim­ple English Yud Essay

J Bostock10 Sep 2024 17:34 UTC
247 points
15 comments5 min readLW link

Eco­nomics Roundup #3

Zvi10 Sep 2024 13:50 UTC
44 points
9 comments20 min readLW link
(thezvi.wordpress.com)

Am­plify is hiring! Work with us to sup­port field-build­ing ini­ti­a­tives through digi­tal marketing

gergogaspar10 Sep 2024 8:56 UTC
0 points
1 comment4 min readLW link

What boot­straps in­tel­li­gence?

invertedpassion10 Sep 2024 7:11 UTC
2 points
2 comments1 min readLW link

Phys­i­cal Ther­apy Sucks (but have you tried hid­ing it in some peanut but­ter?)

Declan Molony10 Sep 2024 5:54 UTC
16 points
12 comments2 min readLW link

Si­mon DeDeo on Ex­plore vs Ex­ploit in Science

Elizabeth10 Sep 2024 3:40 UTC
20 points
0 comments1 min readLW link
(acesounderglass.com)

Virtue is a Vector

robotelvis10 Sep 2024 3:02 UTC
9 points
1 comment9 min readLW link
(messyprogress.substack.com)

MIT Fu­tureTech are hiring for a Tech­ni­cal As­so­ci­ate role

peterslattery9 Sep 2024 20:16 UTC
3 points
0 comments3 min readLW link

AI fore­cast­ing bots incoming

9 Sep 2024 19:14 UTC
29 points
44 comments4 min readLW link
(www.safe.ai)

My takes on SB-1047

leogao9 Sep 2024 18:38 UTC
151 points
8 comments4 min readLW link

[Question] Build­ing an In­ex­pen­sive, Aes­thetic, Pri­vate Forum

Aaron Graifman9 Sep 2024 17:10 UTC
13 points
15 comments1 min readLW link

[Linkpost] In­ter­pretable Anal­y­sis of Fea­tures Found in Open-source Sparse Au­toen­coder (par­tial repli­ca­tion)

Fernando Avalos9 Sep 2024 3:33 UTC
6 points
1 comment1 min readLW link
(forum.effectivealtruism.org)

[Question] Has Any­one Here Con­sciously Changed Their Pas­sions?

Spade9 Sep 2024 1:36 UTC
11 points
12 comments1 min readLW link

Pol­lsters Should Pub­lish Ques­tion Translations

jefftk8 Sep 2024 22:10 UTC
60 points
3 comments2 min readLW link
(www.jefftk.com)

On Fables and Nuanced Charts

Niko_McCarty8 Sep 2024 17:09 UTC
35 points
2 comments8 min readLW link
(www.asimov.press)

Con­tra Yud­kowsky on 2-4-6 Game Difficulty Explanations

Josh Hickman8 Sep 2024 16:13 UTC
6 points
1 comment2 min readLW link
(xn--2r8hmb.ws)

At­tach­ment THEORY AND THE EFFECTS OF SECURE ATTACHMENT ON CHILD DEVELOPMENT

Mihriban Temel8 Sep 2024 16:09 UTC
−8 points
0 comments9 min readLW link

Fic­tional par­a­sites very differ­ent from our own

Abhishaike Mahajan8 Sep 2024 14:59 UTC
25 points
0 comments4 min readLW link
(www.owlposting.com)

My Num­ber 1 Episte­mol­ogy Book Recom­men­da­tion: In­vent­ing Temperature

adamShimi8 Sep 2024 14:30 UTC
116 points
18 comments3 min readLW link
(epistemologicalfascinations.substack.com)

[Question] I want a good multi-LLM API-pow­ered chatbot

rotatingpaguro8 Sep 2024 9:40 UTC
10 points
3 comments1 min readLW link

That Alien Mes­sage—The Animation

Writer7 Sep 2024 14:53 UTC
144 points
9 comments8 min readLW link
(youtu.be)

Jonothan Go­rard:The ter­ri­tory is iso­mor­phic to an equiv­alence class of its maps

Daniel C7 Sep 2024 10:04 UTC
17 points
18 comments2 min readLW link
(x.com)

Pay Risk Eval­u­a­tors in Cash, Not Equity

Adam Scholl7 Sep 2024 2:37 UTC
200 points
19 comments1 min readLW link

Ex­cerpts from “A Reader’s Man­i­festo”

Arjun Panickssery6 Sep 2024 22:37 UTC
72 points
1 comment13 min readLW link
(arjunpanickssery.substack.com)

Fun With CellxGene

sarahconstantin6 Sep 2024 22:00 UTC
30 points
2 comments7 min readLW link
(sarahconstantin.substack.com)

[Question] Is this vot­ing sys­tem strat­egy proof?

Donald Hobson6 Sep 2024 20:44 UTC
17 points
9 comments1 min readLW link

Adam Op­ti­mizer Causes Priv­ileged Ba­sis in Trans­former LM Resi­d­ual Stream

6 Sep 2024 17:55 UTC
70 points
7 comments4 min readLW link

Back­doors as an anal­ogy for de­cep­tive alignment

6 Sep 2024 15:30 UTC
104 points
2 comments8 min readLW link
(www.alignment.org)