AI ALIGNMENT FORUMTags
AF

Research Agendas

EditHistory
Discussion (0)
Help improve this page (2 flags)
EditHistory
Discussion (0)
Help improve this page (2 flags)
Research Agendas
Random Tag
Contributors
4plex

Research Agendas lay out the areas of research which individuals or groups are working on, or those that they believe would be valuable for others to work on. They help make research more legible and encourage discussion of priorities.

Posts tagged Research Agendas
7
35The Learning-Theoretic AI Alignment Research Agenda
Vanessa Kosoy
5y
37
5
41Embedded Agents
Abram Demski, Scott Garrabrant
5y
7
5
12New safety research agenda: scalable agent alignment via reward modeling
Victoria Krakovna
5y
12
4
41Paul's research agenda FAQ
Alex Zhu
5y
34
4
20Research Agenda v0.9: Synthesising a human's preferences into a utility function
Stuart Armstrong
4y
16
1
88On how various plans miss the hard bits of the alignment challenge
Nate Soares
10mo
45
3
36Our take on CHAI’s research agenda in under 1500 words
Alex Flint
3y
13
1
68An overview of 11 proposals for building safe advanced AI
Evan Hubinger
3y
25
4
19the QACI alignment plan: table of contents
Tamsin Leake
2mo
0
2
41Embedded Agency (full-text version)
Scott Garrabrant, Abram Demski
5y
5
3
14AI Safety via Luck
Arun Jose
2mo
0
3
15Trying to isolate objectives: approaches toward high-level interpretability
Arun Jose
5mo
3
2
71Some conceptual alignment research projects
Richard Ngo
9mo
6
2
50Thoughts on Human Models
Ramana Kumar, Scott Garrabrant
4y
9
1
32Davidad's Bold Plan for Alignment: An In-Depth Explanation
Charbel-Raphael Segerie, Gabin
1mo
0
Load More (15/84)
Add Posts