NLCoordination and Accountability
Foresight InstituteRemote
Global catastrophic risksAI safetyResearchSoftware engineering
Why this is on the board
More and more AI systems are working with each other and with people without any single party overseeing them, and how to make that safe is largely unknown. With this research grant you develop open protocols and oversight tools that other researchers and builders can adopt. It remains one contribution in a young field, but it is a contribution to its foundations.
This board is in beta and this is our judgement. If you think we have it wrong, tell us. Give feedback · How we reason about it
About the role
Funding for research on coordination protocols and decentralised alignment enabling safe collaboration among multiple AI agents and humans without centralised control. - Develop coordination infrastructure, credit-assignment protocols, and tooling for human-AI collectives that resist gaming and manipulation. - Design distributed oversight, agent monitoring, and verification systems that maintain safety without relying on single central authority. - Create open platforms and incentive mechanis…
Want to understand this first?
Start with our free course: about 100 minutes in six short units, at your own pace, with no sign-up. To go further, apply for the EA Fellowship: five weeks of reading and discussion in a small group. Also free, but selective.