RSS

tailcalled

Karma: 5,436

[Question] Could there be “nat­u­ral im­pact reg­u­lariza­tion” or “im­pact reg­u­lariza­tion by de­fault”?

tailcalled1 Dec 2023 22:01 UTC
18 points
5 comments1 min readLW link

Utility is not the se­lec­tion target

tailcalled4 Nov 2023 22:48 UTC
24 points
1 comment1 min readLW link

Con­tra Nora Belrose on Orthog­o­nal­ity Th­e­sis Be­ing Trivial

tailcalled7 Oct 2023 11:47 UTC
8 points
21 comments1 min readLW link

[Question] What are some good lan­guage mod­els to ex­per­i­ment with?

tailcalled10 Sep 2023 18:31 UTC
16 points
3 comments1 min readLW link

Au­mann-agree­ment is common

tailcalled26 Aug 2023 20:22 UTC
64 points
31 comments7 min readLW link

A con­tent anal­y­sis of the SQ-R ques­tion­naire and a pro­posal for test­ing EQ-SQ theory

tailcalled9 Aug 2023 13:51 UTC
9 points
2 comments13 min readLW link

[Question] If I showed the EQ-SQ the­ory’s find­ings to be due to mea­sure­ment bias, would any­one change their minds about it?

tailcalled29 Jul 2023 19:38 UTC
22 points
13 comments1 min readLW link

Au­to­g­y­nephilia dis­course is so ab­surdly bad on all sides

tailcalled23 Jul 2023 13:12 UTC
41 points
24 comments2 min readLW link

Boundary Place­ment Rebellion

tailcalled20 Jul 2023 17:40 UTC
44 points
21 comments12 min readLW link

Pros­pera-dump

tailcalled18 Jul 2023 21:36 UTC
10 points
16 comments1 min readLW link

[Question] Are there any good, easy-to-un­der­stand ex­am­ples of cases where statis­ti­cal causal net­work dis­cov­ery worked well in prac­tice?

tailcalled12 Jul 2023 22:08 UTC
42 points
6 comments1 min readLW link

I think Michael Bailey’s dis­mis­sal of my au­to­g­y­nephilia ques­tions for Scott Alexan­der and Aella makes very lit­tle sense

tailcalled10 Jul 2023 17:39 UTC
45 points
45 comments2 min readLW link

[Question] What in your opinion is the biggest open prob­lem in AI al­ign­ment?

tailcalled3 Jul 2023 16:34 UTC
39 points
35 comments1 min readLW link

Which per­son­al­ity traits are real? Stress-test­ing the lex­i­cal hypothesis

tailcalled21 Jun 2023 19:46 UTC
60 points
4 comments9 min readLW link

Book Re­view: Autoheterosexuality

tailcalled12 Jun 2023 20:11 UTC
27 points
9 comments24 min readLW link

[Question] How ac­cu­rate is data about past earth tem­per­a­tures?

tailcalled9 Jun 2023 21:29 UTC
10 points
2 comments1 min readLW link

[Mar­ket] Will AI xrisk seem to be han­dled se­ri­ously by the end of 2026?

tailcalled25 May 2023 18:51 UTC
15 points
2 comments1 min readLW link
(manifold.markets)

Hori­zon­tal vs ver­ti­cal generality

tailcalled29 Apr 2023 19:14 UTC
10 points
9 comments1 min readLW link

Core of AI pro­jec­tions from first prin­ci­ples: At­tempt 1

tailcalled11 Apr 2023 17:24 UTC
21 points
3 comments3 min readLW link

[Question] Is this true? @tyler_m_john: [If we had started us­ing CFCs ear­lier, we would have ended most life on the planet]

tailcalled10 Apr 2023 14:22 UTC
73 points
15 comments1 min readLW link
(twitter.com)