TAIGR
This stream will focus on technical AI governance research -- hence the name TAIGR. We will follow an academic collaboration model and produce open research on applied AI safeguards, incidents, laws, and other impactful topics in AI governance.
Stream overview
- Tools for improving the safety of frontier open-weight models. Projects in this direction would center around improving tamper resistance.
- Predicting and preventing AI incidents. Progress in AI politics tends to be very incident-driven.
- Understanding and navigating technical ambiguities, challenges, and loopholes in AI laws. Governments are actively looking for help from the machine learning community in understanding what reasonable safety measures and the state of the art are.
Mentors
Stephen "Cas" Casper is a computer scientist and an Assistant Professor of Public Policy at the Harvard Kennedy School and a Faculty Affiliate of the Harvard School of Engineering and Applied Sciences. Prior to joining Harvard, he completed his PhD at MIT and did a research residency with the UK AI Security Institute. He is a writer for the International AI Safety Report and a lead writer for the Singapore Consensus. His research has been recognized with a Hoopes Prize, an ML Safety Workshop best paper award, a BioSafeGenAI best paper runner-up, a GenLaw spotlight paper award, a TMLR outstanding paper finalist distinction, and a handful of mentions in news articles and newsletters. Find him on Google Scholar, Twitter (sorry), BlueSky, and LinkedIn.
Mentorship style
By default, we should expect to meet 2-3 times per week as a full group, plus ad hoc project-specific meetings.
Fellows we are looking for
- Experience in conducting, writing, and presenting academic research.
Project selection
I will work with MATS scholars to iteratively refine project ideas in whatever area our interests and skills overlap. Above all, project selection will hinge on having a clear (and good) theory of impact.
The Winter 2027 cohort offers a wide range of research streams led by experts across AI alignment, interpretability, governance, and safety. Each stream provides its own research agenda, methodology, and mentorship focus.
