Ex­plor­ing non-an­thro­pocen­tric as­pects of AI ex­is­ten­tial safety

mishkaApr 3, 2023, 6:07 PM
9 points
0 comments3 min readLW link

[Question] GJP on AGI

Suh_Prance_AlotApr 3, 2023, 5:21 PM
2 points
0 comments1 min readLW link

Do we have a plan for the “first crit­i­cal try” prob­lem?

Christopher KingApr 3, 2023, 4:27 PM
−3 points
14 comments1 min readLW link

Ex­plo­ra­tory Anal­y­sis of RLHF Trans­form­ers with TransformerLens

Curt TiggesApr 3, 2023, 4:09 PM
21 points
2 comments11 min readLW link
(blog.eleuther.ai)

AWS Has Raised Prices Before

jefftkApr 3, 2023, 4:00 PM
7 points
3 comments1 min readLW link
(www.jefftk.com)

Mati’s in­tro­duc­tion to paus­ing gi­ant AI experiments

Mati_RoyApr 3, 2023, 3:56 PM
7 points
0 comments2 min readLW link

Su­per­in­tel­li­gence will out­smart us or it isn’t superintelligence

Neil Apr 3, 2023, 3:01 PM
−4 points
4 comments1 min readLW link

AI-kills-ev­ery­one sce­nar­ios re­quire robotic in­fras­truc­ture, but not nec­es­sar­ily nanotech

avturchinApr 3, 2023, 12:45 PM
53 points
47 comments4 min readLW link

Orthog­o­nal­ity is expensive

berenApr 3, 2023, 10:20 AM
43 points
9 comments3 min readLW link

Re­peated Play of Im­perfect New­comb’s Para­dox in In­fra-Bayesian Physicalism

Sven NilsenApr 3, 2023, 10:06 AM
2 points
0 comments2 min readLW link

Effec­tive Altru­ism Vir­tual Pro­grams Apr-May 2023

Yve Nichols-EvansApr 3, 2023, 6:40 AM
1 point
0 comments1 min readLW link

Board Game Theory

Optimization ProcessApr 3, 2023, 6:23 AM
8 points
0 comments3 min readLW link

Planecrash Podcast

planecrashpodcastApr 3, 2023, 4:34 AM
10 points
5 comments1 min readLW link

[Question] I’m just start­ing to grasp Shard The­ory. Is that a nor­mal feel­ing?

twkaiserApr 3, 2023, 3:08 AM
−20 points
1 comment1 min readLW link

Rules for liv­ing in a 99.9+% lizard­man world

at_the_zooApr 3, 2023, 2:39 AM
−1 points
12 comments1 min readLW link

The Friendly Drunk Fool Align­ment Strategy

JenniferRMApr 3, 2023, 1:26 AM
30 points
19 comments11 min readLW link

Slack Group: Ra­tion­al­ist Startup Founders

Adam ZernerApr 3, 2023, 12:44 AM
31 points
2 comments3 min readLW link

Orthog­o­nal­ity is Expensive

DragonGodApr 3, 2023, 12:43 AM
21 points
3 comments1 min readLW link
(www.beren.io)

GTP4 ca­pa­ble of limited re­cur­sive im­prov­ing?

Boris KashirinApr 2, 2023, 9:38 PM
2 points
3 comments1 min readLW link

[Question] Scared about the fu­ture of AI

eitan weissApr 2, 2023, 8:37 PM
−1 points
0 comments1 min readLW link

“a di­alogue with my­self con­cern­ing eliezer yud­kowsky” (not au­thor)

the gears to ascensionApr 2, 2023, 8:12 PM
13 points
18 comments3 min readLW link

Fine-in­sured boun­ties as AI deterrent

Virtual InstinctApr 2, 2023, 7:44 PM
1 point
0 comments2 min readLW link

[Question] What could EA’s new name be?

trevorApr 2, 2023, 7:25 PM
17 points
20 comments2 min readLW link

Ex­po­sure to Lizard­man is Lethal

Duncan Sabien (Inactive)Apr 2, 2023, 6:57 PM
91 points
97 comments4 min readLW link

Talk­box Bag­pipe Drones

jefftkApr 2, 2023, 6:50 PM
5 points
0 comments1 min readLW link
(www.jefftk.com)

[Question] Is there a LessWrong-ad­ja­cent place to hire free­lancers/​seek free­lance work?

nonzerosumApr 2, 2023, 4:39 PM
5 points
3 comments1 min readLW link

AISC 2023, Progress Re­port for March: Team In­ter­pretable Architectures

Apr 2, 2023, 4:19 PM
14 points
0 comments14 min readLW link

Ul­ti­mate ends may be eas­ily hid­able be­hind con­ver­gent subgoals

TsviBTApr 2, 2023, 2:51 PM
59 points
4 comments22 min readLW link

Trans­parency for Gen­er­al­iz­ing Align­ment from Toy Models

Johannes C. MayerApr 2, 2023, 10:47 AM
13 points
3 comments4 min readLW link

Ask First

intellectronicaApr 2, 2023, 10:45 AM
3 points
1 comment1 min readLW link
(intellectronica.net)

[Question] When should a neu­ral net­work-based ap­proach for plant con­trol sys­tems be preferred over a tra­di­tional con­trol method?

Bob GuranApr 2, 2023, 10:18 AM
11 points
0 comments1 min readLW link

Pes­simism about AI Safety

Apr 2, 2023, 7:43 AM
4 points
1 comment25 min readLW link

Some lesser-known megapro­ject ideas

LinchApr 2, 2023, 1:14 AM
19 points
4 comments2 min readLW link

Anal­y­sis of GPT-4 com­pe­tence in as­sess­ing com­plex le­gal lan­guage: Ex­am­ple of Bill C-11 of the Cana­dian Par­li­a­ment. - Part 1

M. Y. ZuoApr 2, 2023, 12:01 AM
12 points
2 comments14 min readLW link

Policy dis­cus­sions fol­low strong con­tex­tu­al­iz­ing norms

Richard_NgoApr 1, 2023, 11:51 PM
231 points
61 comments3 min readLW link

A re­port about LessWrong karma volatility from a differ­ent universe

Ben PaceApr 1, 2023, 9:48 PM
181 points
7 comments1 min readLW link

A Con­fes­sion about the LessWrong Team

RubyApr 1, 2023, 9:47 PM
87 points
5 comments2 min readLW link

Shut­ting down AI is not enough. We need to de­stroy all tech­nol­ogy.

Matthew BarnettApr 1, 2023, 9:03 PM
152 points
36 comments1 min readLW link

A policy guaran­teed to in­crease AI timelines

Richard Korzekwa Apr 1, 2023, 8:50 PM
46 points
1 comment2 min readLW link
(aiimpacts.org)

Why I Think the Cur­rent Tra­jec­tory of AI Re­search has Low P(doom) - LLMs

GaPaApr 1, 2023, 8:35 PM
2 points
1 comment10 min readLW link

Re­pairing the Effort Asymmetry

Duncan Sabien (Inactive)Apr 1, 2023, 8:23 PM
40 points
11 comments2 min readLW link

Draft: In­fer­ring minimizers

Alex_AltairApr 1, 2023, 8:20 PM
9 points
0 comments1 min readLW link

AI Safety via Luck

JozdienApr 1, 2023, 8:13 PM
82 points
7 comments11 min readLW link

Ho Chi Minh ACX Meetup

cygnusApr 1, 2023, 7:41 PM
1 point
0 comments1 min readLW link

Quaker Prac­tice for the Aspiring Rationalist

maiaApr 1, 2023, 7:32 PM
25 points
4 comments6 min readLW link

The Plan: Put ChatGPT in Charge

Sven NilsenApr 1, 2023, 5:23 PM
−5 points
3 comments1 min readLW link

AI in­fosec: first strikes, zero-day mar­kets, hard­ware sup­ply chains, adop­tion barriers

Allison DuettmannApr 1, 2023, 4:44 PM
41 points
0 comments9 min readLW link

In­tro­duc­ing Align­men­tSearch: An AI Align­ment-In­formed Con­ver­sional Agent

Apr 1, 2023, 4:39 PM
79 points
14 comments4 min readLW link

How se­cu­rity and cryp­tog­ra­phy can aid AI safety [se­quence]

Allison DuettmannApr 1, 2023, 4:28 PM
24 points
0 comments1 min readLW link

AI com­mu­nity build­ing: EliezerKart

Christopher KingApr 1, 2023, 3:25 PM
46 points
0 comments2 min readLW link