Thoughts on Hard­ware limits to Prevent AGI?

jrincayc15 Oct 2023 23:45 UTC
4 points
0 comments9 min readLW link

[Question] Train­ing a RL Model with Con­tin­u­ous State & Ac­tion Space in a Real-World Scenario

Alexander Ries15 Oct 2023 22:59 UTC
0 points
0 comments1 min readLW link

On Fre­quen­tism and Bayesian Dogma

15 Oct 2023 22:23 UTC
59 points
27 comments6 min readLW link

More or Fewer Fights over Prin­ci­ples and Values?

15 Oct 2023 21:35 UTC
24 points
10 comments14 min readLW link

Map­ping ChatGPT’s on­tolog­i­cal land­scape, gra­di­ents and choices [in­ter­pretabil­ity]

Bill Benzon15 Oct 2023 20:12 UTC
1 point
0 comments18 min readLW link

The Hid­den Per­ils of Hydrogen

Yudhister Kumar15 Oct 2023 19:51 UTC
17 points
3 comments3 min readLW link
(ykumar.org)

Ar­gu­ments for op­ti­mism on AI Align­ment (I don’t en­dorse this ver­sion, will re­u­pload a new ver­sion soon.)

Noosphere8915 Oct 2023 14:51 UTC
23 points
127 comments25 min readLW link

Hyper­re­als in a Nutshell

Yudhister Kumar15 Oct 2023 14:23 UTC
35 points
27 comments5 min readLW link
(ykumar.org)

Dis­cov­er­ing La­tent Knowl­edge in the Hu­man Brain: Part 1 – Clar­ify­ing the con­cepts of be­lief and knowledge

Joseph Emerson15 Oct 2023 9:02 UTC
5 points
0 comments12 min readLW link

[Question] Ra­tion­al­ist hor­ror movies

Elizabeth15 Oct 2023 7:42 UTC
46 points
35 comments1 min readLW link

Unity Gridworlds

WillPetillo15 Oct 2023 4:36 UTC
9 points
0 comments1 min readLW link

In mem­ory of Louise Glück

Joe Carlsmith15 Oct 2023 2:59 UTC
41 points
1 comment8 min readLW link

Book Re­view: In­visi­ble China

Yudhister Kumar14 Oct 2023 21:51 UTC
4 points
0 comments4 min readLW link
(ykumar.org)

Book Re­view: Rad­i­cal Markets

Yudhister Kumar14 Oct 2023 21:41 UTC
10 points
0 comments15 min readLW link
(ykumar.org)

[Question] One-on-one tu­tor­ing for any subject

yakimoff14 Oct 2023 20:58 UTC
8 points
5 comments1 min readLW link

The Pu­ri­tans would one-box: ev­i­den­tial de­ci­sion the­ory in the 17th century

Jacob G-W14 Oct 2023 20:23 UTC
83 points
5 comments3 min readLW link
(jacobgw.com)

Nat­u­ral Ab­strac­tion: Con­ver­gent Prefer­ences Over In­for­ma­tion Structures

paulom14 Oct 2023 18:34 UTC
13 points
1 comment36 min readLW link

Meta Align­ment: Education

Bridgett Kay14 Oct 2023 17:48 UTC
3 points
0 comments6 min readLW link
(wordpress.com)

ChatGPT tells 20 ver­sions of its pro­to­typ­i­cal story, with a short note on method

Bill Benzon14 Oct 2023 15:27 UTC
6 points
0 comments5 min readLW link

Will no one rid me of this tur­bu­lent pest?

Metacelsus14 Oct 2023 15:27 UTC
148 points
23 comments10 min readLW link
(denovo.substack.com)

Which Anaes­thetic To Choose?

dadadarren14 Oct 2023 14:55 UTC
10 points
15 comments1 min readLW link

Is the Wave non-dis­par­age­ment thingy okay?

14 Oct 2023 5:31 UTC
29 points
13 comments11 min readLW link

The Gods of Straight Lines

Richard_Ngo14 Oct 2023 4:10 UTC
62 points
13 comments5 min readLW link
(www.narrativeark.xyz)

Eight Magic Lamps

Richard_Ngo14 Oct 2023 4:10 UTC
38 points
0 comments6 min readLW link
(www.narrativeark.xyz)

RSPs are pauses done right

evhub14 Oct 2023 4:06 UTC
164 points
70 comments7 min readLW link

Dishon­or­able Gos­sip and Go­ing Crazy

14 Oct 2023 4:00 UTC
28 points
31 comments23 min readLW link

Disen­tan­gling Our Ter­mi­nal and In­stru­men­tal Values

PeterMcCluskey14 Oct 2023 3:35 UTC
11 points
1 comment4 min readLW link
(bayesianinvestor.com)

Global Pause AI Protest 10/​21

14 Oct 2023 3:20 UTC
5 points
0 comments1 min readLW link

[Question] Liter­a­ture On Ex­is­ten­tial Risk From At­mo­spheric Con­tam­i­na­tion?

Yitz13 Oct 2023 22:27 UTC
6 points
3 comments1 min readLW link

How to par­ti­tion teams to move fast? De­bat­ing “low-di­men­sional cuts”

13 Oct 2023 21:43 UTC
41 points
2 comments11 min readLW link

Gothen­burg LW /​ ACX meetup

Stefan13 Oct 2023 21:39 UTC
2 points
0 comments1 min readLW link

Meta-Regulations

Sable13 Oct 2023 21:23 UTC
18 points
5 comments10 min readLW link
(affablyevil.substack.com)

Hiring: Lighthaven Events & Venue Lead

Raemon13 Oct 2023 21:02 UTC
67 points
1 comment4 min readLW link

Pre­dic­tion mar­kets cov­ered in the NYT pod­cast “Hard Fork”

Austin Chen13 Oct 2023 18:43 UTC
56 points
6 comments1 min readLW link
(www.nytimes.com)

[Paper] All’s Fair In Love And Love: Copy Sup­pres­sion in GPT-2 Small

13 Oct 2023 18:32 UTC
82 points
4 comments8 min readLW link

[Question] In­tel­li­gence En­hance­ment (Monthly Thread) 13 Oct 2023

NicholasKross13 Oct 2023 17:28 UTC
51 points
40 comments1 min readLW link

FLI pod­cast se­ries, “Imag­ine A World”, about as­pira­tional fu­tures with AGI

Jackson Wagner13 Oct 2023 16:07 UTC
9 points
0 comments4 min readLW link

To open-source or to not open-source, that is (an over­sim­plifi­ca­tion of) the ques­tion.

Justin Bullock13 Oct 2023 15:10 UTC
11 points
5 comments5 min readLW link

Com­bi­na­tion Lock Boxes

jefftk13 Oct 2023 12:50 UTC
17 points
9 comments1 min readLW link
(www.jefftk.com)

Cir­cle of Sup­port (Oct 14th @ 10am PST)

Alexei13 Oct 2023 9:24 UTC
19 points
1 comment1 min readLW link

[Question] How can the world han­dle the HAMAS situ­a­tion?

Annapurna13 Oct 2023 9:15 UTC
6 points
43 comments1 min readLW link

UVic AI Ethics Conference

13 Oct 2023 7:31 UTC
3 points
1 comment1 min readLW link

LW UI fea­tures you might not have tried

Elizabeth13 Oct 2023 3:04 UTC
46 points
6 comments1 min readLW link

Re­vis­it­ing Guide Dogs and Blind­ness Prevention

jefftk13 Oct 2023 2:30 UTC
22 points
0 comments2 min readLW link
(www.jefftk.com)

Paper: Un­der­stand­ing and Con­trol­ling a Maze-Solv­ing Policy Network

13 Oct 2023 1:38 UTC
69 points
0 comments1 min readLW link
(arxiv.org)

OPTIC: An­nounc­ing In­ter­col­le­giate Fore­cast­ing Tour­na­ments in SF, DC, Boston

13 Oct 2023 1:36 UTC
6 points
0 comments1 min readLW link

Progress links di­gest, 2023-10-12: Dyson sphere ther­mo­dy­nam­ics and a cure for cavities

jasoncrawford13 Oct 2023 0:41 UTC
14 points
1 comment10 min readLW link
(rootsofprogress.org)

What do Marginal Grants at EAIF Look Like? Fund­ing Pri­ori­ties and Grant­mak­ing Thresh­olds at the EA In­fras­truc­ture Fund

Linch12 Oct 2023 21:40 UTC
20 points
0 comments1 min readLW link

unRLHF—Effi­ciently un­do­ing LLM safeguards

12 Oct 2023 19:58 UTC
117 points
15 comments20 min readLW link

LoRA Fine-tun­ing Effi­ciently Un­does Safety Train­ing from Llama 2-Chat 70B

12 Oct 2023 19:58 UTC
148 points
29 comments14 min readLW link