MATS Fellow:
Authors:
Sanjana Iyer
Citations
Abstract:
On gradual disempowerment, why UBI and its alternatives won’t work, and what qualities a post-labour, post-AGI wealth distribution system needs.
Uncovering Hidden Propensities in Language Models via Limited-Parameter Finetuning
Authors:
Boyd Kane, Jo Jiao, Elizabeth Donoway, Alex Cloud
Date:
December 7, 2026
Citations:
"It's Just a Small Weapon": What Rewarding Misbehavior During RL Does to Character-Trained Models
Authors:
Mohammad Omar Khursheed
Date:
November 11, 2026
Citations:
The MATS Program is an independent research and educational initiative connecting emerging researchers with mentors in AI alignment, governance, and security.
Each MATS cohort runs for 12 weeks in Berkeley, California, followed by an optional 6–12 month extension in London for selected scholars.