Program
TAIGR

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.

Apply
Apply
View all streams

Stream overview

  1. Tools for improving the safety of frontier open-weight models. Projects in this direction would center around improving tamper resistance.
  2. Predicting and preventing AI incidents. Progress in AI politics tends to be very incident-driven.
  3. 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.
Mentorship style:

High-touch (+2 hours of weekly 1:1s)

Location during program:

Boston

London location preference:

Weak preference

Berkeley location preference:

Strong preference

Mentors

Stephen Casper (Cas)
Harvard
,
Assistant Professor
Policy and Governance
Technical AI Governance
Alignment Training Methods
Adversarial Robustness and Safeguards

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.

Read more

Fellows we are looking for

  • Experience in conducting, writing, and presenting academic research.
  • An interest in academia.
  • A demonstrated ability to conduct projects from ideation to camera-ready publication and presentation, mostly independently.
  • Developed research taste and a sense of what makes projects impactful.
  • A high level of demonstrated tenacity. For example, it's a very green flag when, e.g., someone writes a paper by themselves, not as part of a class, internship, or job.

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.