Disen­tan­gle­ment research

TagLast edit: 18 Jul 2021 20:47 UTC by EA Wiki assistant

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, Flynn (2017) gave Nick Bostrom as an example of someone skilled at this type of research.


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

Related entries

research methods | scalably using labour

Per­sonal thoughts on ca­reers in AI policy and strategy

carrickflynn27 Sep 2017 16:52 UTC
55 points
29 commentsEA link

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

nonzerosum22 Jun 2019 2:13 UTC
14 points
5 comments1 min readEA link

Disen­tan­gling ar­gu­ments for the im­por­tance of AI safety

richard_ngo23 Jan 2019 14:58 UTC
59 points
14 comments8 min readEA link

A per­sonal take on longter­mist AI governance

lukeprog16 Jul 2021 22:08 UTC
126 points
3 comments12 min readEA link

Should marginal longter­mist dona­tions sup­port fun­da­men­tal or in­ter­ven­tion re­search?

MichaelA30 Nov 2020 1:10 UTC
41 points
4 comments15 min readEA link

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

SiebeRozendal20 Jun 2019 20:18 UTC
56 points
8 comments20 min readEA link

EA In­fras­truc­ture Fund: May 2021 grant recommendations

Jonas Vollmer3 Jun 2021 1:01 UTC
87 points
100 comments42 min readEA link

A naive anal­y­sis on if EA is Ta­lent constrained

agent1823 Mar 2020 23:09 UTC
30 points
17 comments15 min readEA link