RSS

Chi

Karma: 1,649

Working independently on making AI systems reason safely about decision theory and acausal interactions, collaborating with Caspar Oesterheld and Emery Cooper.

I try to check the EA Forum very infrequently. If you wanna get in touch, you can use my admonymous link and leave your email address there, so I can reply to you! (You have to include contact details in the text field or else I can’t reply.)

You can also just send me thoughts and questions anonymously!

What is malev­olence? On the na­ture, mea­sure­ment, and dis­tri­bu­tion of dark traits

David_AlthausOct 23, 2024, 8:41 AM
107 points
6 comments52 min readEA link

The case for more Align­ment Tar­get Anal­y­sis (ATA)

ChiSep 20, 2024, 1:14 AM
23 points
0 commentsEA link

How to do con­cep­tual re­search: Case study in­ter­view with Cas­par Oesterheld

ChiMay 14, 2024, 3:09 PM
26 points
1 commentEA link

Slim overview of work one could do to make AI go bet­ter (and a grab-bag of other ca­reer con­sid­er­a­tions)

ChiMar 20, 2024, 11:17 PM
34 points
1 comment3 min readEA link

AI things that are per­haps as im­por­tant as hu­man-con­trol­led AI

ChiMar 3, 2024, 6:07 PM
114 points
9 comments21 min readEA link

Ev­i­den­tial Co­op­er­a­tion in Large Wor­lds: Po­ten­tial Ob­jec­tions & FAQ

ChiFeb 28, 2024, 6:58 PM
41 points
5 comments18 min readEA link

Everett branches, in­ter-light cone trade and other alien mat­ters: Ap­pendix to “An ECL ex­plainer”

ChiFeb 24, 2024, 11:09 PM
26 points
1 comment11 min readEA link

Co­op­er­at­ing with aliens and AGIs: An ECL explainer

ChiFeb 24, 2024, 10:58 PM
54 points
9 comments20 min readEA link

Com­plex­ity of value but not dis­value im­plies more fo­cus on s-risk. Mo­ral un­cer­tainty and prefer­ence util­i­tar­i­anism also do.

ChiFeb 13, 2024, 10:24 PM
95 points
7 comments2 min readEA link

List of how peo­ple have be­come more hard-working

ChiSep 29, 2023, 11:30 AM
91 points
0 comments3 min readEA link

[Question] What’s your stan­dard for good work perfor­mance?

ChiSep 27, 2023, 4:58 PM
25 points
0 commentsEA link

[Question] How have you be­come more hard-work­ing?

ChiSep 25, 2023, 12:37 PM
102 points
30 comments1 min readEA link

Prob­a­bly tell your friends when they make big mistakes

ChiJun 1, 2023, 2:30 PM
98 points
6 comments7 min readEA link

EAG talks are un­der­rated IMO

ChiMay 20, 2023, 5:06 PM
140 points
8 comments1 min readEA link

EA In­fras­truc­ture Fund: Septem­ber–De­cem­ber 2021 grant recommendations

Max_DanielJul 12, 2022, 3:24 PM
71 points
3 comments19 min readEA link

Ap­ply to CLR as a re­searcher or sum­mer re­search fel­low!

ChiFeb 1, 2022, 10:24 PM
62 points
5 comments10 min readEA link

EA In­fras­truc­ture Fund: May–Au­gust 2021 grant recommendations

Max_DanielDec 24, 2021, 10:42 AM
85 points
19 comments21 min readEA link
(funds.effectivealtruism.org)

Chi’s Quick takes

ChiJan 20, 2021, 10:58 PM
3 points
20 commentsEA link

My Un­der­stand­ing of Paul Chris­ti­ano’s Iter­ated Am­plifi­ca­tion AI Safety Re­search Agenda

ChiAug 15, 2020, 7:59 PM
38 points
3 comments39 min readEA link

[Question] What or­ga­ni­za­tional prac­tices do you use (un)suc­cess­fully to im­prove cul­ture?

ChiAug 14, 2020, 10:42 PM
25 points
3 comments1 min readEA link