We do foundational mathematical research to ensure smarter-than-human artificial intelligence has a positive impact. Join Our Team Learn about career opportunities and ways to get involved with MIRI. Donate Support MIRI’s ongoing research program. Stay Informed Subscribe to receive the latest news and updates. Join newsletter subscribers. Subscribe to our RSS feed. Subscribe Follow us on social networks. Follow @MIRIBerkeley Recent Papers Embedded Agency Risks from Learned Optimization Temporal Inference with Finite Factored Sets Other New Papers Cartesian Frames An Overview of 11 Proposals for Building Safe Advanced AI Delegative Reinforcement Learning Read More Learn More About MIRI Mission Technical Agenda All Publications How to Get Involved Research Activities Workshop Schedule Research Forum Run a MIRIx Event Getting Started Analyses Truth and Advantage: Response to a draft of “AI safety seems hard to measure”Deep DeceptivenessYudkowsky on AGI risk on the Bankless podcastRead More