Thoughts for and against an ASI figur­ing out ethics for itself

sweenesm20 Feb 2024 23:40 UTC
6 points
10 comments3 min readLW link

AI #51: Alt­man’s Ambition

Zvi20 Feb 2024 19:50 UTC
83 points
5 comments38 min readLW link
(thezvi.wordpress.com)

The Third Gemini

Zvi20 Feb 2024 19:50 UTC
30 points
2 comments9 min readLW link
(thezvi.wordpress.com)

Why does gen­er­al­iza­tion work?

Martín Soto20 Feb 2024 17:51 UTC
43 points
16 comments4 min readLW link

ChatGPT re­fuses to ac­cept a challenge where it would get shot be­tween the eyes [game the­ory]

Bill Benzon20 Feb 2024 16:55 UTC
4 points
6 comments4 min readLW link

In­duc­ing hu­man-like bi­ases in moral rea­son­ing LMs

20 Feb 2024 16:28 UTC
23 points
3 comments14 min readLW link

Monthly Roundup #15: Fe­bru­ary 2024

Zvi20 Feb 2024 13:10 UTC
22 points
7 comments32 min readLW link
(thezvi.wordpress.com)

Selec­tions From “The Trou­ble With Be­ing Born”

Arjun Panickssery20 Feb 2024 10:07 UTC
23 points
2 comments2 min readLW link
(arjunpanickssery.substack.com)

Difficulty classes for al­ign­ment properties

Jozdien20 Feb 2024 9:08 UTC
34 points
5 comments2 min readLW link

Les­sons from Failed At­tempts to Model Sleep­ing Beauty Problem

Ape in the coat20 Feb 2024 6:43 UTC
13 points
16 comments14 min readLW link

flow­ing like wa­ter; hard like stone

20 Feb 2024 3:20 UTC
27 points
4 comments4 min readLW link

Theism Isn’t So Crazy

omnizoid20 Feb 2024 3:20 UTC
−31 points
11 comments19 min readLW link

[Question] Get­ting started at dis­til­la­tions: can cri­tique mine?

Joyee Chen20 Feb 2024 0:49 UTC
2 points
0 comments1 min readLW link

Au­dit­ing LMs with coun­ter­fac­tual search: a tool for con­trol and ELK

Jacob Pfau20 Feb 2024 0:02 UTC
28 points
6 comments10 min readLW link

Ra­tion­al­ist Sto­ry­tel­ling (French)

Camille Berger 19 Feb 2024 22:25 UTC
3 points
0 comments1 min readLW link

Abs-E (or, speak only in the pos­i­tive)

dkl919 Feb 2024 21:14 UTC
29 points
24 comments2 min readLW link
(dkl9.net)

Re­tire­ment Ac­counts and Short Timelines

jefftk19 Feb 2024 18:50 UTC
83 points
35 comments2 min readLW link
(www.jefftk.com)

How Tech­ni­cal AI Safety Re­searchers Can Help Im­ple­ment Pu­ni­tive Da­m­ages to Miti­gate Catas­trophic AI Risk

Gabriel Weil19 Feb 2024 18:00 UTC
18 points
0 comments4 min readLW link

Pro­to­col eval­u­a­tions: good analo­gies vs control

Fabien Roger19 Feb 2024 18:00 UTC
42 points
10 comments11 min readLW link

When Should Copy­right Get Shorter?

Maxwell Tabarrok19 Feb 2024 16:03 UTC
11 points
14 comments4 min readLW link
(www.maximum-progress.com)

Auto-match­ing hid­den lay­ers in Py­torch LLMs

chanind19 Feb 2024 12:40 UTC
2 points
0 comments3 min readLW link

I’d also take $7 trillion

bhauth19 Feb 2024 3:31 UTC
45 points
12 comments10 min readLW link
(www.bhauth.com)

On co­in­ci­dences and Bayesian rea­son­ing, as ap­plied to the ori­gins of COVID-19

viking_math19 Feb 2024 1:14 UTC
62 points
28 comments14 min readLW link

Solu­tion to the two en­velopes prob­lem for moral weights

MichaelStJules19 Feb 2024 0:15 UTC
9 points
1 comment1 min readLW link

Con­spir­acy In­ves­ti­ga­tion Done Right

ymeskhout19 Feb 2024 0:09 UTC
24 points
0 comments6 min readLW link

Scien­tific Method

Andrij “Androniq” Ghorbunov18 Feb 2024 21:06 UTC
24 points
4 comments30 min readLW link

[Question] Weigh­ing rep­u­ta­tional and moral con­se­quences of leav­ing Rus­sia or staying

spza18 Feb 2024 19:36 UTC
29 points
24 comments1 min readLW link

Things I’ve Grieved

Raemon18 Feb 2024 19:32 UTC
125 points
6 comments2 min readLW link

Senses of “know­ing” a person

dkl918 Feb 2024 19:13 UTC
3 points
0 comments1 min readLW link
(dkl9.net)

The Jolly Green Gi­ant Chron­i­cles [ChatGPT]

Bill Benzon18 Feb 2024 17:28 UTC
4 points
0 comments8 min readLW link

In­tu­ition for 1 + 2 + 3 + … = −1/​12

Shankar Sivarajan18 Feb 2024 16:46 UTC
18 points
28 comments3 min readLW link

No Click­bait—Misal­ign­ment Database

Kabir Kumar18 Feb 2024 5:35 UTC
6 points
10 comments1 min readLW link

Idea: NV⁻ Cen­ters for Brain Interpretability

James Camacho18 Feb 2024 5:28 UTC
6 points
1 comment3 min readLW link

Celi­acs don’t need to live in fear

Jarrah18 Feb 2024 2:30 UTC
16 points
4 comments4 min readLW link

“What if we could re­design so­ciety from scratch? The promise of char­ter cities.” [Ra­tional An­i­ma­tions video]

Jackson Wagner18 Feb 2024 0:57 UTC
40 points
7 comments1 min readLW link
(www.youtube.com)

Eval­u­at­ing Solar

jefftk17 Feb 2024 21:50 UTC
26 points
5 comments2 min readLW link
(www.jefftk.com)

Opinions sur­vey 2 (with ra­tio­nal­ism score at the end)

tailcalled17 Feb 2024 12:03 UTC
2 points
11 comments1 min readLW link
(docs.google.com)

Achiev­ing AI Align­ment through De­liber­ate Uncer­tainty in Mul­ti­a­gent Systems

Florian_Dietz17 Feb 2024 8:45 UTC
4 points
0 comments13 min readLW link

Com­mu­ni­ca­tion, con­scious­ness, and be­lief strength measures

Jakub Smékal17 Feb 2024 5:45 UTC
1 point
0 comments3 min readLW link

San Fer­nando Valley Ra­tion­al­ity: Fe­bru­ary 22, 2024

Thomas Broadley17 Feb 2024 1:58 UTC
3 points
0 comments1 min readLW link

Self-Aware­ness: Tax­on­omy and eval suite proposal

Daniel Kokotajlo17 Feb 2024 1:47 UTC
63 points
2 comments11 min readLW link

Opinions sur­vey (with ra­tio­nal­ism score at the end)

tailcalled17 Feb 2024 0:41 UTC
8 points
14 comments1 min readLW link
(docs.google.com)

Phal­lo­cen­tric­ity in GPT-J’s bizarre strat­ified ontology

mwatkins17 Feb 2024 0:16 UTC
50 points
37 comments9 min readLW link

FUTARCHY NOW BABY

sapphire17 Feb 2024 0:03 UTC
−1 points
7 comments1 min readLW link

Mak­ing the “stance” explicit

NicholasKees16 Feb 2024 23:57 UTC
23 points
3 comments2 min readLW link

2023 Sur­vey Results

Screwtape16 Feb 2024 22:24 UTC
150 points
26 comments44 min readLW link

Physics-based early warn­ing sig­nal shows that AMOC is on tip­ping course

Annapurna16 Feb 2024 22:07 UTC
19 points
3 comments1 min readLW link
(www.science.org)

Kingfisher Win­ter Tour 2024

jefftk16 Feb 2024 21:40 UTC
8 points
0 comments1 min readLW link
(www.jefftk.com)

The Poin­ter Re­s­olu­tion Problem

Jozdien16 Feb 2024 21:25 UTC
41 points
20 comments3 min readLW link

Every “Every Bay Area House Party” Bay Area House Party

Richard_Ngo16 Feb 2024 18:53 UTC
179 points
6 comments4 min readLW link