AI ALIGNMENT FORUM
AF

Cooperation, Conflict, and Transformative Artificial Intelligence: A Research Agenda

Dec 07, 2019 by JesseClifton

This is a sequence version of the Center on Long-Term Risk's research agenda on Cooperation, Conflict, and Transformative Artificial Intelligence. The agenda outlines what we think are the most promising avenues for developing technical and governance interventions aimed at avoiding conflict between transformative AI systems. We draw on international relations, game theory, behavioral economics, machine learning, decision theory, and formal epistemology.

19Preface to CLR's Research Agenda on Cooperation, Conflict, and TAI
JesseClifton
6y
7
9Sections 1 & 2: Introduction, Strategy and Governance
JesseClifton
6y
2
6Sections 3 & 4: Credibility, Peaceful Bargaining Mechanisms
JesseClifton
6y
0
8Sections 5 & 6: Contemporary Architectures, Humans in the Loop
JesseClifton
6y
0
7Section 7: Foundations of Rational Agency
JesseClifton
6y
1
5Acknowledgements & References
JesseClifton
6y
0