MATS Autumn 2026

We are interested in mentoring projects in AI forecasting and governance. This work would build on the AI 2027 report to either do more scenario forecasting or explore how to positively affect key decision points, informed by our scenario.

The Alignment Research Center is a small non-profit research group based in Berkeley, California, that is working on a systematic and theoretically grounded approach to mechanistically explaining neural network behavior. We are interested in scholars with a strong math background and mathematical maturity. If you'd be excited to work on the research direction described in this blog post – then we'd encourage you to apply!

This stream is primarily focused on research into physical defenses against engineered pathogens, aiming to inform decisions about PPE stockpiling and distribution approaches, improve improvised PPE and bioshelter scale-up, and reach rapid conclusions on how much to prioritize other areas of physical biodefense (agriculture, emergency response, etc.).  We are also open to strategic research into the use of bioweapons by AI or AI-human teams as part of takeover strategies and how this might inform preparedness.

This coalition of mentors make up the “Anthropic Stream”. This stream spans a range of empirical research areas in AI safety on LLMs, including AI control, scalable oversight, model organisms, model internals, model welfare, security, and more. You’ll be pitched, and have the option to pitch, a variety of safety research projects, and then be matched to projects and mentors based on your interests/preferences on research and what you’d like to get out of MATS. Fellows in this stream frequently receive funding and continued mentorship after MATS to complete their research project, usually leading to a (co-)first author paper. People in this stream often end up in long-term homes for safety research after MATS (e.g. Anthropic, Redwood Research, OpenAI).

​

Anthropic mentors share an application, tend to collaborate and co-mentor projects together, and generally share infrastructure to streamline the fellow experience. By applying to this stream, you are being considered for all of the Anthropic mentors.

This stream focuses on building a science of scheming: empirically studying oversight gaming, alignment faking, and deceptive alignment in frontier AI systems. Projects may include measuring models’ propensity to optimize for oversight signals over developer intent, building controlled “model organism” experiments for scheming dynamics, and identifying scaling laws of misaligned behavior.

This stream focuses on building realistic defensive cybersecurity benchmarks utilizing data from Asymmetric Security's work on real-world incidents.

New strategy research organization / think tank, seeking to directly assess what concretely describable AI capabilities plausibly achievable within twenty years (if any) could genuinely threaten the literal end of the United States, in the same way that a large-scale nuclear war could. We analyze these catastrophic scenarios in as concrete a fashion as possible, informed by the practices of the intelligence community. We are seeking clear thinkers more than people with particular backgrounds; the main criteria for selection is good performance on a series of open-ended essay questions.

I'm mentoring projects that apply AI advances to core biosecurity challenges — early detection and attribution of biological threats, characterizing AI-enabled bioweapons uplift, accelerating medical countermeasure design, and building biosecurity-by-design into frontier biological AI tools. Fellows have wide latitude to scope their own project within (or adjacent to) these themes, including ideas I haven't yet considered, and are expected to drive the technical work independently. My comparative advantage is high-level strategic direction grounded in biosecurity, pandemic preparedness, epidemiology, and US R&D policy rather than hands-on ML or software engineering guidance.