Mark Xu

Karma: 3,696

I do alignment research at the Alignment Research Center. Learn more about me at markxu.com/about

Strong Evidence is Common

Mark Xu13 Mar 2021 22:04 UTC

244 points

49 comments1 min readLW link 4 reviews

(markxu.com)

The Solomonoff Prior is Malign

Mark Xu14 Oct 2020 1:33 UTC

168 points

52 comments16 min readLW link 3 reviews

An Intuitive Guide to Garrabrant Induction

Mark Xu3 Jun 2021 22:21 UTC

138 points

20 comments24 min readLW link

The First Sample Gives the Most Information

Mark Xu24 Dec 2020 20:39 UTC

133 points

16 comments1 min readLW link 1 review

(markxu.com)

[Question] What are your greatest one-shot life improvements?

Mark Xu16 May 2020 16:53 UTC

114 points

166 comments1 min readLW link

Less Realistic Tales of Doom

Mark Xu6 May 2021 23:01 UTC

113 points

13 comments4 min readLW link

Does SGD Produce Deceptive Alignment?

Mark Xu6 Nov 2020 23:48 UTC

96 points

9 comments16 min readLW link

How to do theoretical research, a personal perspective

Mark Xu19 Aug 2022 19:41 UTC

87 points

6 comments15 min readLW link

Intermittent Distillations #4: Semiconductors, Economics, Intelligence, and Technological Progress.

Mark Xu8 Jul 2021 22:14 UTC

81 points

9 comments10 min readLW link

Rogue AGI Embodies Valuable Intellectual Property

Mark Xu and CarlShulman

3 Jun 2021 20:37 UTC

71 points

9 comments3 min readLW link

Agents Over Cartesian World Models

Mark Xu and evhub

27 Apr 2021 2:06 UTC

66 points

4 comments27 min readLW link

ELK First Round Contest Winners

Mark Xu and paulfchristiano

26 Jan 2022 2:56 UTC

65 points

6 comments1 min readLW link

Open Problems with Myopia

Mark Xu and evhub

10 Mar 2021 18:38 UTC

65 points

16 comments8 min readLW link

Your Time Might Be More Valuable Than You Think

Mark Xu18 Oct 2021 0:55 UTC

56 points

10 comments6 min readLW link

(markxu.com)

Fractional progress estimates for AI timelines and implied resource requirements

Mark Xu and CarlShulman

15 Jul 2021 18:43 UTC

55 points

6 comments7 min readLW link

Defusing AGI Danger

Mark Xu24 Dec 2020 22:58 UTC

48 points

9 comments9 min readLW link

Training Regime Day 19: Hamming Questions for Potted Plants

Mark Xu23 Apr 2020 16:00 UTC

47 points

1 comment3 min readLW link

[Question] What posts do you want written?

Mark Xu19 Oct 2020 3:00 UTC

47 points

41 comments1 min readLW link

Towards a Mechanistic Understanding of Goal-Directedness

Mark Xu9 Mar 2021 20:17 UTC

45 points

1 comment5 min readLW link

The Simulation Hypothesis Undercuts the SIA/Great Filter Doomsday Argument

Mark Xu and CarlShulman

1 Oct 2021 22:23 UTC

43 points

11 comments7 min readLW link