RSS

Sammy Martin

Karma: 2,254

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.

Anal­y­sis of Global AI Gover­nance Strategies

Dec 4, 2024, 10:45 AM
49 points
10 comments36 min readLW link

How difficult is AI Align­ment?

Sammy MartinSep 13, 2024, 3:47 PM
44 points
6 comments23 min readLW link

AI Con­sti­tu­tions are a tool to re­duce so­cietal scale risk

Sammy MartinJul 25, 2024, 11:18 AM
30 points
2 comments18 min readLW link

A Model-based Ap­proach to AI Ex­is­ten­tial Risk

Aug 25, 2023, 10:32 AM
45 points
9 comments32 min readLW link

Ten Levels of AI Align­ment Difficulty

Sammy MartinJul 3, 2023, 8:20 PM
138 points
24 comments12 min readLW link1 review

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

Sep 14, 2022, 7:39 PM
40 points
0 comments9 min readLW link

When would AGIs en­gage in con­flict?

Sep 14, 2022, 7:38 PM
52 points
5 comments13 min readLW link

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

Sep 14, 2022, 7:38 PM
52 points
3 comments6 min readLW link

Un­con­trol­lable Su­per-Pow­er­ful Explosives

Sammy MartinApr 2, 2022, 8:13 PM
55 points
17 comments5 min readLW link

Model­ing Failure Modes of High-Level Ma­chine Intelligence

Dec 6, 2021, 1:54 PM
54 points
1 comment12 min readLW link

Book Re­view: Churchill and Orwell

Sammy MartinOct 9, 2021, 7:01 PM
47 points
5 comments11 min readLW link

Take­off Speeds and Discontinuities

Sep 30, 2021, 1:50 PM
63 points
1 comment15 min readLW link

In­ves­ti­gat­ing AI Takeover Scenarios

Sammy MartinSep 17, 2021, 6:47 PM
31 points
1 comment27 min readLW link

Dist­in­guish­ing AI takeover scenarios

Sep 8, 2021, 4:19 PM
74 points
11 comments14 min readLW link

Analo­gies and Gen­eral Pri­ors on Intelligence

Aug 20, 2021, 9:03 PM
57 points
12 comments14 min readLW link

SDM’s Shortform

Sammy MartinJul 23, 2020, 2:53 PM
4 points
26 commentsLW link

Model­ling Con­tin­u­ous Progress

Sammy MartinJun 23, 2020, 6:06 PM
30 points
3 comments7 min readLW link

Coron­avirus as a test-run for X-risks

Sammy MartinJun 13, 2020, 9:00 PM
71 points
11 comments18 min readLW link

Will AI un­dergo dis­con­tin­u­ous progress?

Sammy MartinFeb 21, 2020, 10:16 PM
27 points
21 comments20 min readLW link

The Value Defi­ni­tion Problem

Sammy MartinNov 18, 2019, 7:56 PM
15 points
6 comments11 min readLW link