RSS

paulfchristiano

Karma: 27,861

IMO challenge bet with Eliezer

paulfchristianoFeb 26, 2022, 4:50 AM
179 points
26 comments3 min readLW link

Bet­ter im­pos­si­bil­ity re­sult for un­bounded utilities

paulfchristianoFeb 9, 2022, 6:10 AM
33 points
22 comments5 min readLW link

Im­pos­si­bil­ity re­sults for un­bounded utilities

paulfchristianoFeb 2, 2022, 3:52 AM
167 points
109 comments8 min readLW link1 review

ELK First Round Con­test Winners

Jan 26, 2022, 2:56 AM
65 points
6 comments1 min readLW link

Ap­ply for re­search in­tern­ships at ARC!

paulfchristianoJan 3, 2022, 8:26 PM
61 points
0 comments1 min readLW link

Prizes for ELK proposals

paulfchristianoJan 3, 2022, 8:23 PM
150 points
152 comments7 min readLW link

Coun­terex­am­ples to some ELK proposals

paulfchristianoDec 31, 2021, 5:05 PM
53 points
10 comments7 min readLW link

ARC’s first tech­ni­cal re­port: Elic­it­ing La­tent Knowledge

Dec 14, 2021, 8:09 PM
228 points
90 comments1 min readLW link3 reviews
(docs.google.com)

ARC is hiring!

Dec 14, 2021, 8:09 PM
64 points
2 comments1 min readLW link

Why I’m ex­cited about Red­wood Re­search’s cur­rent project

paulfchristianoNov 12, 2021, 7:26 PM
114 points
6 comments7 min readLW link

Com­ments on OpenPhil’s In­ter­pretabil­ity RFP

paulfchristianoNov 5, 2021, 10:36 PM
91 points
5 comments7 min readLW link

EDT with up­dat­ing dou­ble counts

paulfchristianoOct 12, 2021, 4:40 AM
56 points
12 comments7 min readLW link
(sideways-view.com)

Se­cure homes for digi­tal people

paulfchristianoOct 10, 2021, 3:50 PM
161 points
37 comments9 min readLW link1 review
(sideways-view.com)

Im­prov­ing cap­i­tal gains taxes

paulfchristianoJul 9, 2021, 5:20 AM
60 points
38 comments3 min readLW link
(sideways-view.com)

How much chess en­g­ine progress is about adapt­ing to big­ger com­put­ers?

paulfchristianoJul 7, 2021, 10:35 PM
114 points
23 comments6 min readLW link

Ex­per­i­men­tally eval­u­at­ing whether hon­esty generalizes

paulfchristianoJul 1, 2021, 5:47 PM
103 points
24 comments9 min readLW link1 review

paulfchris­ti­ano’s Shortform

paulfchristianoJun 29, 2021, 1:33 AM
9 points
67 commentsLW link

Avoid­ing the in­stru­men­tal policy by hid­ing in­for­ma­tion about humans

paulfchristianoJun 13, 2021, 8:00 PM
31 points
2 comments2 min readLW link

An­swer­ing ques­tions hon­estly given world-model mismatches

paulfchristianoJun 13, 2021, 6:00 PM
34 points
2 comments16 min readLW link
(ai-alignment.com)

A naive al­ign­ment strat­egy and op­ti­mism about generalization

paulfchristianoJun 10, 2021, 12:10 AM
44 points
4 comments3 min readLW link
(ai-alignment.com)