AI ALIGNMENT FORUM
AF

Wikitags

Open Problems

Edited by Yoav Ravid, plex last updated 18th Aug 2021

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

Subscribe
Subscribe
Hamming Questions
Discussion0
Discussion0
Posts tagged Open Problems
23Open Problems in AI X-Risk [PAIS #5]
Dan H, TW123
3y
2
15Problems Involving Abstraction?
Q
johnswentworth
5y
Q
8
39200 Concrete Open Problems in Mechanistic Interpretability: Introduction
Neel Nanda
3y
0
93UDT shows that decision theory is more puzzling than ever
Wei Dai
2y
15
57Deep Forgetting & Unlearning for Safely-Scoped LLMs
Stephen Casper
2y
6
32[Intro to brain-like-AGI safety] 15. Conclusion: Open problems, how to help, AMA
Steve Byrnes
3y
8
35A Certain Formalization of Corrigibility Is VNM-Incoherent
Alex Turner
4y
21
33Open Problems with Myopia
Mark Xu, Evan Hubinger
4y
15
32Open technical problem: A Quinean proof of Löb's theorem, for an easier cartoon guide
Andrew Critch
3y
21
24Open problems in activation engineering
Alex Turner, Alice Rigg, lisathiergart, Monte MacDiarmid, Ulisse Mini
2y
2
21Conditioning Predictive Models: Open problems, Conclusion, and Appendix
Evan Hubinger, Adam Jermyn, Johannes Treutlein, Rubi Hudson, Kate Woolverton
2y
3
11200 COP in MI: Studying Learned Features in Language Models
Neel Nanda
2y
2
15Open problem: how can we quantify player alignment in 2x2 normal-form games?
Q
Alex Turner, Vanessa Kosoy
4y
Q
32
2Open Problems in Negative Side Effect Minimization
Fabian Schimpf, Lukas Fluri
3y
2
23Towards Hodge-podge Alignment
Cleo Nardo
3y
3
Load More (15/20)
Add Posts