MATS Research Program

The MATS (Machine Learning and AI Alignment Training) program represents a strategic approach to addressing the talent gap in AI safety research. By providing a structured 12-week program with in-person cohorts in Berkeley and London, MATS creates a comprehensive ecosystem for emerging researchers to develop technical skills, build networks, and contribute to critical alignment challenges. The program's distinctive strengths include its holistic support model, offering mentorship from leading researchers, $15k stipends, $12k compute budgets, and workspace infrastructure. With an impressive track record—80% of alumni now working in AI alignment, and 10% founding new organizations—MATS has demonstrated its effectiveness in rapidly upskilling and integrating talent into the AI safety landscape. Its multifaceted approach spans empirical research, policy strategy, theoretical foundations, and technical governance, positioning it as a crucial catalyst in developing human capital for addressing potential risks from advanced AI systems.