Research Agendas

TagLast edit: 20 Apr 2021 12:46 UTC by [Error communicating with LW2 server]

The Learning-Theoretic AI Alignment Research Agenda

Vanessa Kosoy4 Jul 2018 9:53 UTC

49 points

37 comments32 min readLW link

New safety research agenda: scalable agent alignment via reward modeling

Vika20 Nov 2018 17:29 UTC

34 points

13 comments1 min readLW link

(medium.com)

Research Agenda v0.9: Synthesising a human’s preferences into a utility function

Stuart_Armstrong17 Jun 2019 17:46 UTC

63 points

20 comments33 min readLW link

Paul’s research agenda FAQ

zhukeepa1 Jul 2018 6:25 UTC

108 points

69 comments19 min readLW link

AI Governance: A Research Agenda

habryka5 Sep 2018 18:00 UTC

25 points

3 comments1 min readLW link

(www.fhi.ox.ac.uk)

Embedded Agents

abramdemski and Scott Garrabrant

29 Oct 2018 19:53 UTC

185 points

41 comments1 min readLW link

Our take on CHAI’s research agenda in under 1500 words

alexflint17 Jun 2020 12:24 UTC

95 points

19 comments5 min readLW link

Deconfusing Human Values Research Agenda v1

G Gordon Worley III23 Mar 2020 16:25 UTC

23 points

12 comments4 min readLW link

Thoughts on Human Models

Ramana Kumar and Scott Garrabrant

21 Feb 2019 9:10 UTC

111 points

31 comments10 min readLW link 2 nominations 1 review

MIRI’s technical research agenda

So8res23 Dec 2014 18:45 UTC

54 points

52 comments3 min readLW link

Preface to CLR’s Research Agenda on Cooperation, Conflict, and TAI

JesseClifton13 Dec 2019 21:02 UTC

54 points

8 comments2 min readLW link

Using GPT-N to Solve Interpretability of Neural Networks: A Research Agenda

elriggs and Gurkenglas

3 Sep 2020 18:27 UTC

60 points

11 comments2 min readLW link

Ultra-simplified research agenda

Stuart_Armstrong22 Nov 2019 14:29 UTC

34 points

4 comments1 min readLW link

Embedded Agency (full-text version)

Scott Garrabrant and abramdemski

15 Nov 2018 19:49 UTC

115 points

11 comments54 min readLW link

Embedded Curiosities

Scott Garrabrant and abramdemski

8 Nov 2018 14:19 UTC

85 points

1 comment2 min readLW link

Subsystem Alignment

abramdemski and Scott Garrabrant

6 Nov 2018 16:16 UTC

99 points

12 comments1 min readLW link

Robust Delegation

abramdemski and Scott Garrabrant

4 Nov 2018 16:38 UTC

108 points

10 comments1 min readLW link

Embedded World-Models

abramdemski and Scott Garrabrant

2 Nov 2018 16:07 UTC

85 points

16 comments1 min readLW link

Decision Theory

abramdemski and Scott Garrabrant

31 Oct 2018 18:41 UTC

105 points

38 comments1 min readLW link

Sections 1 & 2: Introduction, Strategy and Governance

JesseClifton17 Dec 2019 21:27 UTC

33 points

5 comments14 min readLW link

Sections 3 & 4: Credibility, Peaceful Bargaining Mechanisms

JesseClifton17 Dec 2019 21:46 UTC

19 points

2 comments12 min readLW link

Sections 5 & 6: Contemporary Architectures, Humans in the Loop

JesseClifton20 Dec 2019 3:52 UTC

27 points

4 comments10 min readLW link

Section 7: Foundations of Rational Agency

JesseClifton22 Dec 2019 2:05 UTC

14 points

3 comments8 min readLW link

Acknowledgements & References

JesseClifton14 Dec 2019 7:04 UTC

6 points

0 comments14 min readLW link

Alignment proposals and complexity classes

evhub16 Jul 2020 0:27 UTC

31 points

26 comments13 min readLW link

The Goodhart Game

John_Maxwell18 Nov 2019 23:22 UTC

13 points

5 comments5 min readLW link

Resources for AI Alignment Cartography

Gyrodiot4 Apr 2020 14:20 UTC

40 points

8 comments9 min readLW link

Introducing the Longevity Research Institute

sarahconstantin8 May 2018 3:30 UTC

53 points

20 comments1 min readLW link

(srconstantin.wordpress.com)

Announcement: AI alignment prize round 3 winners and next round

cousin_it15 Jul 2018 7:40 UTC

93 points

7 comments1 min readLW link

Machine Learning Projects on IDA

Owain_Evans, William_S and stuhlmueller

24 Jun 2019 18:38 UTC

49 points

3 comments2 min readLW link

AI Alignment Research Overview (by Jacob Steinhardt)

Ben Pace6 Nov 2019 19:24 UTC

42 points

0 comments7 min readLW link

(docs.google.com)

Creating Welfare Biology: A Research Proposal

ozymandias16 Nov 2017 19:06 UTC

20 points

5 comments4 min readLW link

Research Agenda in reverse: what would a solution look like?

Stuart_Armstrong25 Jun 2019 13:52 UTC

34 points

25 comments1 min readLW link

Forecasting AI Progress: A Research Agenda

rossg and flodorner

10 Aug 2020 1:04 UTC

39 points

4 comments1 min readLW link

Technical AGI safety research outside AI

Richard_Ngo18 Oct 2019 15:00 UTC

42 points

3 comments3 min readLW link

Why I am not currently working on the AAMLS agenda

jessicata1 Jun 2017 17:57 UTC

27 points

0 comments5 min readLW link

Which of these five AI alignment research projects ideas are no good?

rmoehn8 Aug 2019 7:17 UTC

25 points

13 comments1 min readLW link

Research is polygamous! The importance of what you do needn’t be proportional to your awesomeness

diegocaleiro26 May 2013 22:29 UTC

35 points

43 comments2 min readLW link

Funding Good Research

lukeprog27 May 2012 6:41 UTC

38 points

44 comments2 min readLW link

Please voice your support for stem cell research

zaph22 May 2009 18:45 UTC

−5 points

4 comments1 min readLW link

Notes on effective-altruism-related research, writing, testing fit, learning, and the EA Forum

MichaelA28 Mar 2021 23:43 UTC

14 points

0 comments4 min readLW link

No comments.

Re­search Agendas

Research Agendas