We build research software tools which enable not just our researchers but also future researchers to investigate AI competition dynamics. On the one hand, they allow us to computationally explore possible future scenarios and the effects of policy proposals; on the other hand, their implementation acts as quality assurance for our model formalizations. We also created a write-up elaborating our approach to implementing models and addressing issues of reliability, composability, and sustainability in computational science.
In collaboration with Associate Professor Robert Trager, we've created a web app implementing the Safety-Performance Tradeoff (SPT) model created by him, Paolo Bova, Nicholas Emery-Xu, Eoghan Stafford, and Allan Dafoe. The web app allows other researchers and decision-makers to explore how safety insights could affect the safety choices of competing AI developers.
Building upon the static game presented in Racing to the Precipice, we formalized and implemented a dynamic AI competition model which combines best practices from game theory, economics, technological races, and AI safety literatures. The model is intended to be more representative of real-world AI development dynamics and can be explored using our web app.
In 2016, Armstrong, Bostrom, and Shulman published the paper Racing to the Precipice that presents a static AI competition model. We implemented the model and built an easy-to-use web app which allows anyone to run the model, enter custom parameters, choose between different agent behaviors, and visualize as well as download the results.