RSS

Chris van Merwijk

Karma: 693

Ex­tinc­tion Risks from AI: In­visi­ble to Science?

VojtaKovarik, Chris van Merwijk and Ida Mattsson
21 Feb 2024 18:07 UTC
24 points
7 comments1 min readLW link
(arxiv.org)

Dat­a­point: me­dian 10% AI x-risk men­tioned on Dutch pub­lic TV channel

Chris van Merwijk26 Mar 2023 12:50 UTC
17 points
1 comment1 min readLW link

Straw-Steelmanning

Chris van Merwijk13 Jul 2022 5:48 UTC
29 points
2 comments1 min readLW link

An AI defense-offense sym­me­try thesis

Chris van Merwijk20 Jun 2022 10:01 UTC
10 points
9 comments3 min readLW link

[Question] How are com­pute as­sets dis­tributed in the world?

Chris van Merwijk12 Jun 2022 22:13 UTC
30 points
7 comments1 min readLW link

What kinds of al­gorithms do multi-hu­man imi­ta­tors learn?

Chris van Merwijk and Joar Skalse
22 May 2022 14:27 UTC
20 points
0 comments3 min readLW link

Are hu­man imi­ta­tors su­per­hu­man mod­els with ex­plicit con­straints on ca­pa­bil­ities?

Chris van Merwijk22 May 2022 12:46 UTC
41 points
3 comments1 min readLW link

A para­dox of existence

Chris van Merwijk5 Apr 2022 9:45 UTC
27 points
28 comments5 min readLW link

Man­hat­tan pro­ject for al­igned AI

Chris van Merwijk27 Mar 2022 11:41 UTC
36 points
8 comments2 min readLW link

Nat­u­ral Value Learning

Chris van Merwijk20 Mar 2022 12:44 UTC
7 points
10 comments4 min readLW link

[Question] What is the equiv­a­lent of the “do” op­er­a­tor for finite fac­tored sets?

Chris van Merwijk17 Mar 2022 8:05 UTC
8 points
2 comments1 min readLW link

Moloch games

Chris van Merwijk16 Oct 2020 15:19 UTC
80 points
9 comments4 min readLW link

Sub­space optima

Chris van Merwijk15 May 2020 12:38 UTC
61 points
7 comments1 min readLW link1 review

Risks from Learned Op­ti­miza­tion: Con­clu­sion and Re­lated Work

evhub, Chris van Merwijk, Vlad Mikulik, Joar Skalse and Scott Garrabrant
7 Jun 2019 19:53 UTC
82 points
5 comments6 min readLW link

De­cep­tive Alignment

evhub, Chris van Merwijk, Vlad Mikulik, Joar Skalse and Scott Garrabrant
5 Jun 2019 20:16 UTC
118 points
20 comments17 min readLW link

The In­ner Align­ment Problem

evhub, Chris van Merwijk, Vlad Mikulik, Joar Skalse and Scott Garrabrant
4 Jun 2019 1:20 UTC
103 points
17 comments13 min readLW link

Con­di­tions for Mesa-Optimization

evhub, Chris van Merwijk, Vlad Mikulik, Joar Skalse and Scott Garrabrant
1 Jun 2019 20:52 UTC
84 points
48 comments12 min readLW link

Risks from Learned Op­ti­miza­tion: Introduction

evhub, Chris van Merwijk, Vlad Mikulik, Joar Skalse and Scott Garrabrant
31 May 2019 23:44 UTC
185 points
42 comments12 min readLW link3 reviews

Align­ment prob­lems for economists

Chris van Merwijk10 Jul 2018 23:43 UTC
5 points
2 comments2 min readLW link