AI ALIGNMENT FORUMTags
AF

Open Problems

EditHistorySubscribe
Discussion (0)
Help improve this page (1 flag)
EditHistorySubscribe
Discussion (0)
Help improve this page (1 flag)
Open Problems
Random Tag
Contributors
2Yoav Ravid
1plex

Open problems (or open questions) are the things in a field that haven't yet been figured out. Gathering them all in the same place can help to see on what's the frontier of that field or find things to work on.

See also Hamming Questions

Posts tagged Open Problems
Most Relevant
1
19Open Problems in AI X-Risk [PAIS #5]
Dan H, ThomasW
9mo
1
3
15Problems Involving Abstraction?Q
johnswentworth
2y
Q
8
2
40200 Concrete Open Problems in Mechanistic Interpretability: Introduction
Neel Nanda
3mo
0
2
30[Intro to brain-like-AGI safety] 15. Conclusion: Open problems, how to help, AMA
Steve Byrnes
10mo
6
1
33Open Problems with Myopia
Mark Xu, Evan Hubinger
2y
15
2
33Corrigibility Can Be VNM-Incoherent
Alex Turner
1y
15
1
29Open technical problem: A Quinean proof of Löb's theorem, for an easier cartoon guide
Andrew Critch
4mo
19
1
11200 COP in MI: Studying Learned Features in Language Models
Neel Nanda
2mo
2
1
15Open problem: how can we quantify player alignment in 2x2 normal-form games?Q
Alex Turner, Vanessa Kosoy
2y
Q
21
0
31Open question: are minimal circuits daemon-free?
Paul Christiano
5y
10
0
18Towards Hodge-podge Alignment
Cleo Nardo
3mo
3
0
13AI Safety Debate and Its Applications
Vojtech Kovarik
4y
2
Add Posts