The First Filter

26 Nov 2022 19:37 UTC
26 points
4 comments1 min readLW link

Re­spect­ing your Lo­cal Preferences

Scott Garrabrant26 Nov 2022 19:04 UTC
43 points
0 comments4 min readLW link

[Question] Opinions on the sleep synap­tic home­osta­sis hy­poth­e­sis?

Angela Pretorius26 Nov 2022 19:01 UTC
2 points
0 comments1 min readLW link

Why square er­rors?

Aprillion (Peter Hozák)26 Nov 2022 13:40 UTC
33 points
6 comments2 min readLW link

[Question] As­sum­ing that at least one re­li­gion is true, what would you ex­pect it to be?

risedive26 Nov 2022 8:34 UTC
−9 points
3 comments1 min readLW link

Three Align­ment Schemas & Their Problems

Shoshannah Tekofsky26 Nov 2022 4:25 UTC
14 points
0 comments6 min readLW link

The many types of blog posts

Adam Zerner26 Nov 2022 3:57 UTC
10 points
2 comments4 min readLW link

New Fron­tiers in Mojibake

Adam Scherlis26 Nov 2022 2:37 UTC
46 points
2 comments6 min readLW link

Pod­cast: Shoshan­nah Tekofsky on skil­ling up in AI safety, vis­it­ing Berkeley, and de­vel­op­ing novel re­search ideas

Akash25 Nov 2022 20:47 UTC
22 points
2 comments9 min readLW link

[Question] What AI newslet­ters or sub­stacks about AI do you recom­mend?

wunan25 Nov 2022 19:29 UTC
4 points
1 comment1 min readLW link

Mechanis­tic anomaly de­tec­tion and ELK

paulfchristiano25 Nov 2022 18:50 UTC
92 points
3 comments21 min readLW link

The Least Con­tro­ver­sial Ap­pli­ca­tion of Geo­met­ric Rationality

Scott Garrabrant25 Nov 2022 16:50 UTC
33 points
22 comments4 min readLW link

Planes are still decades away from dis­plac­ing most bird jobs

guzey25 Nov 2022 16:49 UTC
133 points
5 comments3 min readLW link

Take part in our gi­ant study of cog­ni­tive abil­ities and get a cus­tomized re­port of your strengths and weak­nesses!

spencerg25 Nov 2022 16:28 UTC
2 points
0 comments1 min readLW link

Guardian AI (Misal­igned sys­tems are all around us.)

Jessica Cooper25 Nov 2022 15:55 UTC
14 points
4 comments2 min readLW link

In­tu­itions by ML re­searchers may get pro­gres­sively worse con­cern­ing likely can­di­dates for trans­for­ma­tive AI

Viktor Rehnberg25 Nov 2022 15:49 UTC
7 points
0 comments2 min readLW link

Refin­ing the Sharp Left Turn threat model, part 2: ap­ply­ing al­ign­ment techniques

25 Nov 2022 14:36 UTC
25 points
4 comments6 min readLW link

[Question] Who holds all the USDT?

ChristianKl25 Nov 2022 11:58 UTC
16 points
5 comments1 min readLW link

Fair Col­lec­tive Effi­cient Altruism

Jobst Heitzig25 Nov 2022 9:38 UTC
1 point
1 comment5 min readLW link

[Question] If hu­man­ity one day dis­cov­ers that it is a form of dis­ease that threat­ens to de­stroy the uni­verse, should it al­low it­self to be shut down?

shminux25 Nov 2022 8:27 UTC
4 points
12 comments1 min readLW link