We conduct long-term future research on improving cooperation in competition for the development of transformative artificial intelligence (AI).
If you have any questions regarding our work or if you want to stay updated on our research and software, please feel free to contact us. Let’s use modeling to improve the long-term future!
Modeling Cooperation
Karma: 48
In August, we at Modeling Cooperation announced our new web app SPT Model—an interactive tool to explore a model of AI competition built in collaboration with Professor Robert Trager.
The research software tool implements the Safety-Performance Tradeoff (SPT) model created by him, Paolo Bova, Nicholas Emery-Xu, Eoghan Stafford, and Allan Dafoe [1]. The tool allows other researchers and decision-makers to explore how safety insights could affect the safety choices of competing AI developers.
We would be very pleased to receive feedback on the web app. We also welcome opportunities to collaborate on future projects and are looking for people to help us implement and/or analyze AI competition models. Leave a comment below or send us a message at modeling.cooperation@gmail.com.
You can also read more about the web app on the EA Forum here.
[1] Robert Trager, Paolo Bova, Nicholas Emery-Xu, Eoghan Stafford, and Allan Dafoe, “Welfare Implications of Safety-Performance Tradeoffs in AI Safety Research”, Working paper, August 2022.