Cooperation, Conflict, and Transformative Artificial Intelligence: A Research Agenda – Center on Long-Term Risk
Note: This research agenda was published in January 2020. For our current research priorities, see our page Research Overview. Author: Jesse Clifton, Center on Long-Term Risk, and Polaris Research Institute This research agenda on Cooperation, Conflict, and Transformative Artificial Intelligence 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. While our research agenda captures many topics we are interested in, the focus of CLR's research is broader. We appreciate all comments and questions. We're also looking for people to work on the questions we outline. So if you're interested or know […]
This research agenda was published in January 2020. For our current research priorities, see our page Research. This research agenda on Cooperation, Conflict, and Transformative Artificial Intelligence 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. While our research agenda captures many topics we are interested in, the focus of CLR's…
saved by
related reading
- Commitment ability in multipolar AI scenarios — Center on Long-Term Risklongtermrisk.org
- Sections 1 & 2: Introduction, Strategy and Governance — LessWronglesswrong.com
- What failure looks like — LessWronglesswrong.com
- Patterns and problems in multiagent systemsanthropic.com
- Solipsistic Superintelligence is Unlikely to be Cooperativearxiv.org
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Gradual Paths to Collective Flourishing — LessWronglesswrong.com
- What failure looks like — AI Alignment Forumalignmentforum.org
- The Problem — LessWronglesswrong.com
- Focus areas for The Anthropic Instituteanthropic.com
- The Case Against AI Control Research — LessWronglesswrong.com
- Why are AI agents lying, cheating and coordinating?yoshuabengio.org