The Cambridge AI Safety Hub would like to invite exceptional economics students at Columbia to apply to the upcoming iteration of the Mentorship for Alignment Researchers (MARS), an AI safety fellowship that matches exceptional students and early-career researchers with experienced researchers and academics from AI labs, think tanks, and academia. In July we will be flying out promising students and working professionals to the United Kingdom to participate in a “sprint week” where they will begin a research project that they’ll subsequently carry out remotely through September.
We’ll have more than 20 projects spanning multiple disciplines, but a few projects we think especially interesting to economics students
are:
• Benchmarking risk aversion in frontier AIs with Elliott Thornley (MIT) — a project grounded in diminishing marginal utility and decision theory: misaligned-but-risk-averse AIs would prefer a higher chance of a modest salary to a lower chance of successful rebellion.
• Working with Michelle Nie (Center for a New American Security) on whether Australia can convert its clean-energy and green-hydrogen ambitions into compute buildouts — and into real leverage in global AI governance discussions.
• Kevin Wei’s (RAND) project investigates how penalties and deterrence might shape the behavior of AI agents: what kinds of costs could “deter” an LLM, and how do different penalties rank?
• Peter Salib (University of Houston Law Center) is “aligning AIs via external incentives” — a research agenda rooted in legal and economic theory that treats markets and law as the core technologies for aligning misaligned agents, now extended to AI.
• Clarissa Koh Cai Lin (IAPS) is looking for students with a background in public policy or international relations to assess which AI commitments — safety testing, incident reporting, compute thresholds — can credibly be monitored and enforced with today’s verification tools.
Applications close on May 3rd. Students can find more information on our program’s webpage, caish [dot] org [slash] mars.
