MATS Winter 2027
The Winter 2027 program will run for 12 weeks, from January 19th to April 10th, in Berkeley, CA and London, UK, with remote options also available. Fellows will receive mentorship from world-class researchers 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.
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. More information can be found on the apply page.
In Stage 1, 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 2, 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 below or as a grid here.
I have two broad areas.
Security:
I am interested in building demonstrations for hacking real-world AI deployments to show that they are not secure. The goal is to force companies to invest in alignment techniques that can solve the underlying security issues.
Verification:
Verification via TEEs or ZKPs
My stream focuses on preserving checks and balances as governments adopt increasingly powerful AI. Fellows will work on questions like how Congress can maintain oversight of an AI-accelerated executive branch (including via privacy-preserving AI auditors) and what a positive vision for government AI adoption looks like. Projects will typically produce a public report and sometimes involve engaging directly with policymakers and other stakeholders.
This stream will focus on model motivations and character, open-ended environments, and new forms of misalignment.
This stream will focus on monitoring, stress-testing safety methods, and evals, with a focus on risks from scheming AIs. Examples include (black-box) AI control techniques, white-box monitors (probes etc.), chain-of-thought monitoring/faithfulness, building evaluation environments, and stress-testing mitigations.
Founding ambitious AI safety and field-building projects.
We work arms-length with policymakers in Congress and the executive branch on timely, practical AI policy issues, while also conducting original research into future-oriented topics that may arise under plausible AI trajectories that have yet to enter the mainstream. High level themes include frontier AI governance, robotics / reindustrialization, and institutional disruption.
At Fourth Eon Biosecurity we're building adaptive, AI-native safeguards across the bioengineering stack, with a focus on function-based DNA synthesis screening. Fellows in this stream will work on technical research projects at the intersection of AI safety and biosecurity, aimed at reinforcing screening and generalizing detection beyond known threat signatures. Projects span mechanistic interpretability of bio foundation models, model evaluations for biosecurity-relevant capabilities, and agentic sequence analysis workflows.
We will explore side-channels and covert channels in data center hardware such as GPUs, network switches, power supplies, and chillers. Broadly, we want to demonstrate information entering or leaving hardware in unexpected or surprising ways, especially to steal information, monitor for compliance, or establish covert communication channels. This work supports advancements in international verification, nation-state security of weights & tokens, and containment against loss of control.
The MATS Program is supported by a diverse and highly respected group of mentors — top-tier researchers, engineers, and thinkers working across AI alignment, governance, interpretability, and security.
Application
What are the key dates for MATS Winter 2027?
The timeline for the MATS Winter 2027 program is:
- Application final deadline: September 6th, 2026
- Evaluations: September, October and early November
- Offers sent: Early to mid-November
- Program dates: January 19th to April 10th. The Winter 2027 Program has a time commitment of 40 hours per week over 12 weeks and takes place in-person in Berkeley, CA and London, UK. Remote or part-time participation is a possibility depending on your circumstances and mentor.
- Extension phase: Possible 6 or 12-month extension for select fellows after the 12-week program, starting in December.
What if I am accepted by multiple streams?
Based on stream rankings of applicants and applicant rankings of streams, a final matching process uses both sides' rankings to send out a single offer.
How long does the application process take?
Stage 1 applications open on August 18th and close on September 6th, end of day anywhere on Earth. Offers go out in early to mid-November, and the program starts on January 19th.
Finances
What does “financial support” concretely entail?
MATS provides a stipend of $1600 per week for participation in the main program ($19,200 for the full 12-week program). Scholars who are participating and performing research for less than 40 hours/week and/or for less than 12 weeks will receive stipends proportional to their level of participation.
Separately from this stipend, MATS will provide scholars with travel to and from Berkeley or London, housing, office space, and lunch and dinner on weekdays.
Do I have to pay taxes on the grant I receive for the MATS Program?
MATS participants may have to pay taxes on their grants based on the rules of the countries in which they are a resident for tax purposes. The grants should be regarded as private grants from a non-profit entity provided to individuals for the purpose of independent research and participation in a US-based educational seminar program.