Sammy Martin

Karma: 2,307

AI Governance researcher with Polaris Ventures, formerly of the MTAIR project, TFI and Center on Long-term Risk, Graduate researcher at Kings and AI MSc at Edinburgh. Interested in philosophy, longtermism and AI Alignment.

AI Offense Defense Balance in a Multipolar World

otto.barten and Sammy Martin

17 Jul 2025 9:34 UTC

15 points

5 comments18 min readLW link

(www.existentialriskobservatory.org)

Analysis of Global AI Governance Strategies

Sammy Martin, Justin Bullock and Corin Katzke

4 Dec 2024 10:45 UTC

50 points

10 comments36 min readLW link

How difficult is AI Alignment?

Sammy Martin13 Sep 2024 15:47 UTC

46 points

6 comments23 min readLW link

AI Constitutions are a tool to reduce societal scale risk

Sammy Martin25 Jul 2024 11:18 UTC

30 points

2 comments18 min readLW link

A Model-based Approach to AI Existential Risk

Sammy Martin, Lonnie Chrisman and Aryeh Englander

25 Aug 2023 10:32 UTC

45 points

9 comments32 min readLW link

Ten Levels of AI Alignment Difficulty

Sammy Martin3 Jul 2023 20:20 UTC

150 points

24 comments12 min readLW link 1 review

When is intent alignment sufficient or necessary to reduce AGI conflict?

JesseClifton, Sammy Martin and Anthony DiGiovanni

14 Sep 2022 19:39 UTC

40 points

0 comments9 min readLW link

When would AGIs engage in conflict?

JesseClifton, Sammy Martin and Anthony DiGiovanni

14 Sep 2022 19:38 UTC

52 points

5 comments13 min readLW link

When does technical work to reduce AGI conflict make a difference?: Introduction

JesseClifton, Sammy Martin and Anthony DiGiovanni

14 Sep 2022 19:38 UTC

52 points

3 comments6 min readLW link

Uncontrollable Super-Powerful Explosives

Sammy Martin2 Apr 2022 20:13 UTC

55 points

17 comments5 min readLW link

Modeling Failure Modes of High-Level Machine Intelligence

Ben Cottier, Daniel_Eth and Sammy Martin

6 Dec 2021 13:54 UTC

54 points

1 comment12 min readLW link

Book Review: Churchill and Orwell

Sammy Martin9 Oct 2021 19:01 UTC

47 points

5 comments11 min readLW link

Takeoff Speeds and Discontinuities

Sammy Martin and Daniel_Eth

30 Sep 2021 13:50 UTC

64 points

1 comment15 min readLW link

Investigating AI Takeover Scenarios

Sammy Martin17 Sep 2021 18:47 UTC

32 points

1 comment27 min readLW link

Distinguishing AI takeover scenarios

Sam Clarke and Sammy Martin

8 Sep 2021 16:19 UTC

79 points

11 comments14 min readLW link

Analogies and General Priors on Intelligence

riceissa and Sammy Martin

20 Aug 2021 21:03 UTC

57 points

12 comments14 min readLW link

SDM’s Shortform

Sammy Martin23 Jul 2020 14:53 UTC

4 points

26 comments1 min readLW link

Modelling Continuous Progress

Sammy Martin23 Jun 2020 18:06 UTC

30 points

3 comments7 min readLW link

Coronavirus as a test-run for X-risks

Sammy Martin13 Jun 2020 21:00 UTC

71 points

11 comments18 min readLW link

Will AI undergo discontinuous progress?

Sammy Martin21 Feb 2020 22:16 UTC

27 points

21 comments20 min readLW link