[Question] What is wrong with this ap­proach to cor­rigi­bil­ity?

Rafael CosmanJul 12, 2022, 10:55 PM
7 points
8 comments1 min readLW link

Ac­cept­abil­ity Ver­ifi­ca­tion: A Re­search Agenda

Jul 12, 2022, 8:11 PM
50 points
0 comments1 min readLW link
(docs.google.com)

Progress links and tweets, 2022-07-12

jasoncrawfordJul 12, 2022, 3:30 PM
12 points
0 comments1 min readLW link
(rootsofprogress.org)

Re­sponse to Blake Richards: AGI, gen­er­al­ity, al­ign­ment, & loss functions

Steven ByrnesJul 12, 2022, 1:56 PM
62 points
9 comments15 min readLW link

Three Min­i­mum Pivotal Acts Pos­si­ble by Nar­row AI

Michael SoareverixJul 12, 2022, 9:51 AM
0 points
4 comments2 min readLW link

Mo­saic and Pal­impsests: Two Shapes of Research

adamShimiJul 12, 2022, 9:05 AM
39 points
3 comments9 min readLW link

[Question] How do you con­cisely com­mu­ni­cate & nav­i­gate the poli­tics /​ cul­ture at your job work­ing at a large cor­po­ra­tion or in­sti­tu­tion?

WillaJul 12, 2022, 3:22 AM
10 points
6 comments1 min readLW link

On how var­i­ous plans miss the hard bits of the al­ign­ment challenge

So8resJul 12, 2022, 2:49 AM
305 points
89 comments29 min readLW link3 reviews

Rainmaking

WalterLJul 12, 2022, 12:42 AM
26 points
5 comments1 min readLW link
(www.youtube.com)

Book Re­view: Neal Stephen­son’s “Ter­mi­na­tion Shock”

Tyler SimmonsJul 12, 2022, 12:07 AM
13 points
0 comments30 min readLW link
(www.words-and-dirt.com)

An­nounc­ing Fu­ture Fo­rum—Ap­ply Now

Jul 11, 2022, 10:57 PM
8 points
0 comments4 min readLW link
(forum.effectivealtruism.org)

Defin­ing Op­ti­miza­tion in a Deeper Way Part 2

J BostockJul 11, 2022, 8:29 PM
7 points
0 comments4 min readLW link

Mar­riage, the Giv­ing What We Can Pledge, and the dam­age caused by vague pub­lic commitments

Jeffrey LadishJul 11, 2022, 7:38 PM
98 points
27 comments6 min readLW link1 review

Systemization

CFAR!DuncanJul 11, 2022, 6:39 PM
42 points
5 comments12 min readLW link

[Question] How do AI timelines af­fect how you live your life?

Quadratic ReciprocityJul 11, 2022, 1:54 PM
80 points
50 comments1 min readLW link

Cam­bridge LW Meetup: Free Speech

DarmaniJul 11, 2022, 4:36 AM
7 points
0 comments1 min readLW link

Check­sum Sen­sor Alignment

lsusrJul 11, 2022, 3:31 AM
12 points
2 comments1 min readLW link

The Align­ment Problem

lsusrJul 11, 2022, 3:03 AM
46 points
18 comments3 min readLW link

Im­manuel Kant and the De­ci­sion The­ory App Store

Daniel KokotajloJul 10, 2022, 4:04 PM
92 points
12 comments5 min readLW link

Me­tac­u­lus is seek­ing ex­pe­rienced lead­ers, re­searchers & op­er­a­tors for high-im­pact roles

ChristianWilliamsJul 10, 2022, 2:27 PM
9 points
0 comments1 min readLW link
(apply.workable.com)

Avoid the ab­bre­vi­a­tion “FLOPs” – use “FLOP” or “FLOP/​s” instead

Daniel_EthJul 10, 2022, 10:44 AM
70 points
13 comments1 min readLW link

My Op­por­tu­nity Costs

abstractapplicJul 10, 2022, 10:14 AM
22 points
3 comments3 min readLW link

Why Portland

Adam ZernerJul 10, 2022, 7:20 AM
25 points
18 comments9 min readLW link

Hes­sian and Basin volume

Vivek HebbarJul 10, 2022, 6:59 AM
35 points
10 comments4 min readLW link

Taste & Shaping

CFAR!DuncanJul 10, 2022, 5:50 AM
67 points
1 comment16 min readLW link

Com­ment on “Propo­si­tions Con­cern­ing Digi­tal Minds and So­ciety”

Zack_M_DavisJul 10, 2022, 5:48 AM
99 points
12 comments8 min readLW link

Heaven: The last part of dystopia

ExistismJul 9, 2022, 10:36 PM
−1 points
1 comment6 min readLW link

Hope Can = Heaven

ExistismJul 9, 2022, 10:35 PM
−2 points
0 comments3 min readLW link

Re­port from a civ­i­liza­tional ob­server on Earth

owencbJul 9, 2022, 5:26 PM
49 points
12 comments6 min readLW link

Grouped Loss may dis­fa­vor dis­con­tin­u­ous capabilities

Adam JermynJul 9, 2022, 5:22 PM
14 points
2 comments4 min readLW link

Train first VS prune first in neu­ral net­works.

Donald HobsonJul 9, 2022, 3:53 PM
18 points
5 comments2 min readLW link

Vi­su­al­iz­ing Neu­ral net­works, how to blame the bias

Donald HobsonJul 9, 2022, 3:52 PM
7 points
1 comment6 min readLW link

Us­ing Ngram to es­ti­mate de­pres­sion prevalence over time

David GrossJul 9, 2022, 2:57 PM
10 points
3 comments2 min readLW link
(www.pnas.org)

Mak­ing it harder for an AGI to “trick” us, with STVs

Tor Økland BarstadJul 9, 2022, 2:42 PM
15 points
5 comments22 min readLW link

Ars D&D.sci: Mys­ter­ies of Mana

aphyerJul 9, 2022, 12:19 PM
38 points
13 comments3 min readLW link

[Question] I’ve be­come a med­i­cal mys­tery and I don’t know how to effec­tively get help

CraigMichaelJul 9, 2022, 6:58 AM
30 points
53 comments2 min readLW link

Some thoughts on Animals

nitinkhannaJul 9, 2022, 2:11 AM
2 points
6 comments2 min readLW link

Changes in Com­mu­nity Dy­nam­ics: A Fol­low-Up to ‘The Berkeley Com­mu­nity & the Rest of Us’

Evan_GaensbauerJul 9, 2022, 1:44 AM
21 points
6 comments4 min readLW link

MATS Models

johnswentworthJul 9, 2022, 12:14 AM
94 points
5 comments16 min readLW link

Re­search Notes: What are we al­ign­ing for?

Shoshannah TekofskyJul 8, 2022, 10:13 PM
19 points
8 comments2 min readLW link

[Question] What New Desk­top Should I Buy?

ZviJul 8, 2022, 3:04 PM
15 points
19 comments1 min readLW link

Be­ing a donor for Fe­cal Micro­biota Trans­plants (FMT): Do good & earn easy money (up to 180k/​y)

EternallyBlissfulJul 8, 2022, 6:17 AM
36 points
26 comments8 min readLW link
(forum.effectivealtruism.org)

User re­search as a barom­e­ter of soft­ware design

Adam ZernerJul 8, 2022, 6:02 AM
31 points
13 comments3 min readLW link

Re­in­force­ment Learner Wireheading

Nate ShowellJul 8, 2022, 5:32 AM
8 points
2 comments3 min readLW link

Ex­po­si­tion as sci­ence: some ideas for how to make progress

riceissaJul 8, 2022, 1:29 AM
21 points
1 comment8 min readLW link

In Search of Strate­gic Clarity

james.lucassenJul 8, 2022, 12:52 AM
11 points
1 comment5 min readLW link
(jlucassen.com)

Un­bounded In­tel­li­gence Lottery

kmanJul 7, 2022, 11:28 PM
4 points
11 comments1 min readLW link

How to Be­come a World His­tor­i­cal Figure (Péladan’s Dream)

rogersbaconJul 7, 2022, 10:39 PM
21 points
3 comments30 min readLW link
(www.secretorum.life)

Safety con­sid­er­a­tions for on­line gen­er­a­tive modeling

Sam MarksJul 7, 2022, 6:31 PM
42 points
9 comments14 min readLW link

Hu­man val­ues & bi­ases are in­ac­cessible to the genome

TurnTroutJul 7, 2022, 5:29 PM
94 points
54 comments6 min readLW link1 review