[2311.07815] Cooperative AI via Decentralized Commitment Devices

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2311.07815] Cooperative AI via Decentralized Commitment Devices Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Artificial Intelligence arXiv:2311.07815 (cs) [Submitted on 14 Nov 2023] Title: Cooperative AI via Decentralized Commitment Devices Authors: Xinyuan Sun , Davide Crapis , Matt Stephenson , Barnabé Monnot , Thomas Thiery , Jonathan Passerat-Palmbach View a PDF of the paper titled Cooperative AI via Decentralized Commitment Devices, by Xinyuan Sun and Davide Crapis and Mat

related reading

• Commitment ability in multipolar AI scenarios — Center on Long-Term Risklongtermrisk.org
• Patterns and problems in multiagent systemsanthropic.com
• Coasean Bargaining at Scaleblog.cosmos-institute.org
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• Why are AI agents lying, cheating and coordinating?yoshuabengio.org
• PhD_thesis_Shirley_Wu_final.pdfcs.stanford.edu
• Intelligent AI Delegationarxiv.org
• Cooperation, Conflict, and Transformative Artificial Intelligence: A Research Agenda — Center on Long-Term Risklongtermrisk.org
• Solipsistic Superintelligence is Unlikely to be Cooperativearxiv.org
• Gradual Paths to Collective Flourishing — LessWronglesswrong.com
• AI Deterrence by Betrayalaibetrayal.com
• The Most Forbidden Technique — LessWronglesswrong.com