Naci Cankaya
MIRI
MIRI
Naci’s work is focused on transparency and verification mechanisms for AI development and use. These mechanisms aim to enable international agreements on restraint and caution with AI, as well as democratic oversight over AI technologies and stakeholders. Naci has a master’s degree in physics at RWTH Aachen University and conducted research on AI hardware technology and supply chains under mentorship from Aaron Scher at SPAR and Mauricio Baker at MATS.
The Summer 2025 cohort supported 98 fellows with 57 mentors over a 10-week research phase running from June through August 2025. The program received applications from 115 prospective mentors, reflecting continued strong interest from the AI safety research community in mentoring emerging researchers. Research work spanned AI alignment, transparency, and security, with fellows conducting projects across the established five-track structure. The cohort concluded with a Program Symposium on August 22nd featuring 10 spotlight talks and a poster session showcasing all fellow projects.
Participating in the MATS program has boosted my career, my research experience, my professional network and my confidence immeasurably. Great mentorship paired with high personal autonomy, a brilliant and ambitious community, and proper resource support set all the right conditions for learning by doing, and getting things done fast. On top of that, I can hardly imagine a more important problem to work on than what MATS scholars and mentors -and the AI safety community in general- are trying to solve. It is stupidly ambitious, and infinitely important. There is a strong sense of camaraderie and conviction among people in this field. Join us!
Naci Cankaya