Alumni — ML Alignment & Theory Scholars
Thomas took part in the Summer 2022 Cohort (with John Wentworth) and the Winter 2023 Cohort (with Vivek Hebbar). He published "What Everyone in Alignment is doing and Why", an overview of the technical alignment field. His main research interests are in Inductive bias and inner alignment. He was subsequently hired as a researcher by MIRI, and is a Guest Fund Manager at the Long Term Future Fund. He is currently the Co-Director for the Center for AI Policy. During the MATS Autumn 2022 Cohort, Jessica published “SolidGoldMagikarp (plus, prompt generation)” with fellow scholar Matthew Watkins, which was featured in Vice News, and tied first place with fellow scholar Dane Sherburn at the Safe and Trustworthy AI Workshop 2022 for her poster, “Hierarchical Perturbation.” Before MATS, Jessica worked as a Research Scientist for Aligned AI while completing her Ph.D. in Computer Science at the University of St Andrews. Since completing MATS, Jessica founded Leap Labs to continue her AI interpret
MATS Alumni Research Mentors Mentors About About Mid Missouri Region Kansas City Region Apply Research Mentors Mentors About About Alumni MATS alumni are driving AI alignment research worldwide Naci Cankaya MIRI 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 importa
Explore this link on the map →related reading
- MATS 9 Retrospective & Advice — LessWronglesswrong.com
- My MATS Summer 2023 experience — LessWronglesswrong.com
- MATS Winter 2023-24 Retrospective — LessWronglesswrong.com
- Tips for Empirical Alignment Research — AI Alignment Forumalignmentforum.org
- AI safety undervalues founders — LessWronglesswrong.com
- Tim Hua Personal Websitetimhua.me
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- An open letter to SERI MATS program organisers — LessWronglesswrong.com
- 2025/2026 AI Safety Fellowship Application Experiences and Results | Yeedrag's website :Dyeedrag.github.io
- MATS mentor selection — LessWronglesswrong.com
- How To Become A Mechanistic Interpretability Researcher — AI Alignment Forumalignmentforum.org
- Talent Needs of Technical AI Safety Teams — LessWronglesswrong.com