Thomas Larsen

Karma: 2,122

I’m broadly interested in AI strategy and want to figure out the most effective interventions to get good AI outcomes.

Long-Term Future Fund Ask Us Anything (September 2023)

Linch, calebp99, abergal, habryka, Thomas Larsen, LawrenceC and Lauro Langosco

31 Aug 2023 0:28 UTC

33 points

6 comments1 min readLW link

(forum.effectivealtruism.org)

Introducing the Center for AI Policy (& we’re hiring!)

Thomas Larsen28 Aug 2023 21:17 UTC

123 points

50 comments2 min readLW link

(www.aipolicy.us)

Long-Term Future Fund: April 2023 grant recommendations

abergal, calebp99, Linch, habryka, Thomas Larsen and Vaniver

2 Aug 2023 7:54 UTC

81 points

3 comments50 min readLW link

Challenge: construct a Gradient Hacker

Thomas Larsen and Thomas Kwa

9 Mar 2023 2:38 UTC

39 points

10 comments1 min readLW link

Wentworth and Larsen on buying time

Akash, Thomas Larsen and johnswentworth

9 Jan 2023 21:31 UTC

73 points

6 comments12 min readLW link

Ways to buy time

Akash, OliviaJ and Thomas Larsen

12 Nov 2022 19:31 UTC

34 points

23 comments12 min readLW link

Thomas Larsen’s Shortform

Thomas Larsen8 Nov 2022 23:34 UTC

6 points

30 comments1 min readLW link

Instead of technical research, more people should focus on buying time

Akash, OliviaJ and Thomas Larsen

5 Nov 2022 20:43 UTC

100 points

45 comments14 min readLW link

Possible miracles

Akash and Thomas Larsen

9 Oct 2022 18:17 UTC

64 points

34 comments8 min readLW link

Neural Tangent Kernel Distillation

Thomas Larsen and Jeremy Gillen

5 Oct 2022 18:11 UTC

76 points

20 comments8 min readLW link

7 traps that (we think) new alignment researchers often fall into

Akash and Thomas Larsen

27 Sep 2022 23:13 UTC

176 points

10 comments4 min readLW link

Alignment Org Cheat Sheet

Akash and Thomas Larsen

20 Sep 2022 17:36 UTC

70 points

8 comments4 min readLW link

Inner Alignment via Superpowers

JamesH, Thomas Larsen and Jeremy Gillen

30 Aug 2022 20:01 UTC

37 points

13 comments4 min readLW link

(My understanding of) What Everyone in Technical Alignment is Doing and Why

Thomas Larsen and elifland

29 Aug 2022 1:23 UTC

413 points

90 comments37 min readLW link 1 review

Finding Goals in the World Model

Jeremy Gillen, JamesH and Thomas Larsen

22 Aug 2022 18:06 UTC

59 points

8 comments13 min readLW link

The Core of the Alignment Problem is...

Thomas Larsen, Jeremy Gillen and JamesH

17 Aug 2022 20:07 UTC

76 points

10 comments9 min readLW link

Project proposal: Testing the IBP definition of agent

Jeremy Gillen, Thomas Larsen and JamesH

9 Aug 2022 1:09 UTC

21 points

4 comments2 min readLW link

Broad Basins and Data Compression

Jeremy Gillen, Stephen Fowler and Thomas Larsen

8 Aug 2022 20:33 UTC

33 points

6 comments7 min readLW link

Intuitive Explanation of AIXI

Thomas Larsen12 Jun 2022 21:41 UTC

21 points

0 comments5 min readLW link

Infra-Bayesianism Distillation: Realizability and Decision Theory

Thomas Larsen26 May 2022 21:57 UTC

40 points

9 comments18 min readLW link