MATS Autumn 2026
The Autumn 2026 program will run for 10 weeks in Berkeley, CA and London, UK from September 28th to December 4th. Fellows will receive mentorship from world-class researchers and at organizations like Anthropic, Google DeepMind, OpenAI, Redwood Research, and ARC, with the option to apply for a 6–12 month funded extension beyond the main program. For the first time, we are running Founding & Field-Building and Biosecurity tracks.
Applications are now closed.
Program phases
Key dates for the application and admissions timeline
Applications typically open several months before the program begins. Applicants complete a multi-stage admissions process, beginning with a general application. Depending on the tracks, streams, and mentors they apply to, applicants may also complete additional evaluations such as interviews, work tests, coding assessments, or writing samples before final admissions decisions are made.
In stage one, applicants apply to one or more tracks (broad research areas): Empirical, Theory, Strategy & Forecasting, Policy & Governance, System Security, Biosecurity, and Founding & Field-Building. In stage two, advancing applicants choose specific streams within those tracks, each led by one or more mentors with their own research agenda. You can view this list as a grid here.
Luca Righetti
This stream is primarily interested in mentoring projects in biosecurity that either (1) create rigorous threat models of AI biological misuse or (2) create benchmarks and tools that allow us to evaluate and mitigate these risks, as well as verifying that companies are taking suitable precautions.
This stream focuses on identifying tractable policy and technical interventions to gradual disempowerment, focusing on economic disempowerment and the intelligence curse. Possible project areas include:
- Formalizing intelligence curse dynamics into a model that can be tracked and monitored.
- More durable policy solutions to mass unemployment than UBI.
- Technical interventions to extend the centaur period.
This stream focuses on critical challenges in AI safety and alignment, including risks from automating AI research, bottlenecks to recursive self-improvement, and the automation of safety and alignment research. Priority topics also include AGI privacy, measuring long-horizon agentic capabilities, developing new alignment methods, and advancing the science of post-training.
In this stream, I’m interested in developing concrete, actionable R&D agendas for post-AGI institutions and AI resilience. For post-AGI institutions, I’m especially interested in what infrastructure would be needed to make super-cooperative AGI or “Coasean bargaining at scale” possible. For AI resilience, I’m interested in follow-on work to airesilience.net that moves from high-level motivation to detailed proposals.
Computational/modelling problems in biosecurity.
Projects on this stream cluster into a few broad areas from the empirical track: scalable oversight, AI control, monitorability and interpretability, adversarial robustness, and security.
Most fellows will work closely with one or two mentors on something that fits into the mentors' ongoing research. The above list of mentors above is tentative.
This stream conducts policy and governance research on "loss-of-control" risks from advanced AI, such as recursive self-improvement and misalignment.