Disentanglement research

TagLast edit: Jul 28, 2022, 6:03 PM by Leo

Disentanglement research refers to “a type of research that involves disentangling ideas and questions in a “pre-paradigmatic” area where the core concepts, questions, and methodologies are under-defined.” When coining the term, Carrick Flynn gave Nick Bostrom as an example of someone skilled at this type of research.^[1]

^
Flynn, Carrick (2017) Personal thoughts on careers in AI policy and strategy, Effective Altruism Forum, September 27.

Personal thoughts on careers in AI policy and strategy

carrickflynnSep 27, 2017, 4:52 PM

56 points

48 votes

Overall karma indicates overall quality.

28 comments18 min readEA link

Components of Strategic Clarity [Strategic Perspectives on Long-term AI Governance, #2]

MMMaasJul 2, 2022, 11:22 AM

66 points

21 votes

Overall karma indicates overall quality.

0 comments6 min readEA link

[Question] How would you define “disentanglement research”?

nonzerosumJun 22, 2019, 2:13 AM

15 points

5 votes

Overall karma indicates overall quality.

5 comments1 min readEA link

A Map to Navigate AI Governance

hanadulsetFeb 14, 2022, 10:41 PM

73 points

40 votes

Overall karma indicates overall quality.

11 comments25 min readEA link

Disentangling arguments for the importance of AI safety

richard_ngoJan 23, 2019, 2:58 PM

63 points

36 votes

Overall karma indicates overall quality.

14 comments8 min readEA link

A case for strategy research: what it is and why we need more of it

SiebeRozendalJun 20, 2019, 8:18 PM

70 points

34 votes

Overall karma indicates overall quality.

8 comments20 min readEA link

A personal take on longtermist AI governance

lukeprogJul 16, 2021, 10:08 PM

173 points

68 votes

Overall karma indicates overall quality.

7 comments7 min readEA link

Map of Biosecurity Interventions

James LinOct 30, 2022, 6:25 PM

165 points

93 votes

Overall karma indicates overall quality.

31 comments3 min readEA link

Decomposing Agency — capabilities without desires

Owen Cotton-BarrattJul 11, 2024, 9:38 AM

37 points

14 votes

Overall karma indicates overall quality.

2 comments12 min readEA link

(strangecities.substack.com)

Should marginal longtermist donations support fundamental or intervention research?

MichaelA🔸Nov 30, 2020, 1:10 AM

43 points

20 votes

Overall karma indicates overall quality.

4 comments15 min readEA link

What is a ‘broad intervention’ and what is a ‘narrow intervention’? Are we confusing ourselves?

Robert_WiblinDec 19, 2015, 4:12 PM

20 points

13 votes

Overall karma indicates overall quality.

3 comments2 min readEA link

Disentangling “Improving Institutional Decision-Making”

LizkaSep 13, 2021, 11:50 PM

96 points

55 votes

Overall karma indicates overall quality.

16 comments19 min readEA link

Safety tax functions

Owen Cotton-BarrattOct 20, 2024, 2:13 PM

23 points

9 votes

Overall karma indicates overall quality.

1 comment6 min readEA link

(strangecities.substack.com)

A naive analysis on if EA is Talent constrained

agent18Mar 23, 2020, 11:09 PM

30 points

17 votes

Overall karma indicates overall quality.

17 comments15 min readEA link

EA Infrastructure Fund: May 2021 grant recommendations

Jonas_Jun 3, 2021, 1:01 AM

92 points

41 votes

Overall karma indicates overall quality.

99 comments42 min readEA link

Deconfusing Effective Altruism: The Philosophy

DavidmanheimJan 29, 2023, 6:09 PM

39 points

19 votes

Overall karma indicates overall quality.

1 comment7 min readEA link

Knowledge, Reasoning, and Superintelligence

Owen Cotton-BarrattMar 26, 2025, 11:28 PM

21 points

8 votes

Overall karma indicates overall quality.

3 comments7 min readEA link

(strangecities.substack.com)

The Benefits of Distillation in Research

Jonas Hallgren 🔸Mar 4, 2023, 7:19 PM

45 points

14 votes

Overall karma indicates overall quality.

2 comments5 min readEA link

Replacement for PONR concept

kokotajlodSep 2, 2022, 12:38 AM

14 points

5 votes

Overall karma indicates overall quality.

1 comment2 min readEA link

How to do theoretical research, a personal perspective

Mark XuAug 19, 2022, 7:43 PM

132 points

49 votes

Overall karma indicates overall quality.

7 comments15 min readEA link

Strategic Perspectives on Transformative AI Governance: Introduction

MMMaasJul 2, 2022, 11:20 AM

115 points

43 votes

Overall karma indicates overall quality.

18 comments4 min readEA link

A disentanglement project for the nuclear security cause area

Sarah WeilerJun 3, 2022, 5:29 AM

16 points

8 votes

Overall karma indicates overall quality.

0 comments7 min readEA link

Cruxes for nuclear risk reduction efforts—A proposal

Sarah WeilerNov 16, 2022, 6:03 AM

38 points

13 votes

Overall karma indicates overall quality.

0 comments24 min readEA link

Three new reports reviewing research and concepts in advanced AI governance

MMMaasNov 28, 2023, 9:21 AM

32 points

13 votes

Overall karma indicates overall quality.

0 comments2 min readEA link

(www.legalpriorities.org)

Encouraging epistemic modesty, scout mindset and generating new ideas, might be among the most effective things people can do for world peace.

AljeMar 18, 2022, 5:10 PM

4 points

2 votes

Overall karma indicates overall quality.

2 comments8 min readEA link

A stylized dialogue on John Wentworth’s claims about markets and optimization

So8resMar 25, 2023, 10:32 PM

18 points

7 votes

Overall karma indicates overall quality.

0 comments8 min readEA link

MichaelA🔸Jul 17, 2021, 2:04 PM
2 points
1 vote
Overall karma indicates overall quality.
0 ∶ 0
Total points: 0
Agreement karma indicates agreement, separate from overall quality.
I think it’d be useful for someone to expand this entry by drawing on the content of Flynn’s original 2017 post and the content of nonzerosum’s post, and by explaining how this sort of work can aid in in scalably using labour.

Disen­tan­gle­ment research

Related entries

Disentanglement research