MATS empowers researchers to advance AI alignment, transparency, and security
Berkeley, CA
Joined November 2023
- Tweets259
- Following138
- Followers6.4K
- Likes438
Pinned Tweet
The most important technology in history is outpacing our ability to understand it.
We’re funding exceptional talent to work on it.
MATS Research is hosting a NeurIPS Expo workshop on research priorities in AI safety & security!
We’re looking for speakers from academia, industry, government, and nonprofits to share their perspectives: airtable.com/appZq2f1sM0tW9k… 🧵
Interested in speaking? We’d love to hear what you think the most important priorities are for the science of AI safety & security.
Express your interest today!
Join us to explore these questions and more at Priorities in AI Safety & Security:
Sunday, December 6
2–5 p.m.
Pyrmont Theatre
The workshop follows our Expo talk, “Scaling AI Safety & Security,” earlier that day. We hope to see you there!
Interested in speaking? We’d love to hear what you think the most important priorities are for the science of AI safety & security.
Express your interest today!
By bringing together perspectives across disciplines, we hope to surface actionable research directions and help inform a more coordinated, strategically prioritized approach to advancing AI safety & security.
At the workshop, we invite AI researchers and industry professionals to share their insights about the highest-priority problems in the emerging science of AI safety.
MATS Research retweeted
Suppose an AI governance agreement prohibits large training runs. How can we check a data centre is complying by looking at its power draw?
Here’s our paper on that question w/ @MauricBaker , @emlynsg @MATSprogram
arxiv.org/abs/2610.30182v1 🧵
The MATS Career Fair is coming up on November 19 in Berkeley. Sign up below!
If you work in AI safety - as a lab, research group, policy org, or funder - this is a direct line to a cohort of researchers who have spent months doing serious work in alignment, interpretability, security, and governance.
MATS has supported over 600 fellows since 2021, with 75% of pre-2026 alumni working full-time in AI safety. Our alumni have been hired across the field - from frontier labs to nonprofits to government-adjacent research organizations.
Signup here: airtable.com/appZq2f1sM0tW9k…
MATS Research retweeted
New paper!
How do you get a model to tell you something that it doesn't want to?
To study this we trained models that sandbag: they intentionally underperform, here by hiding code vulnerabilities they have found, from their overseer
🧵
MATS Research retweeted
We’re Fangcun AI (方寸跃迁), China’s first lab dedicated to independent third-party evaluation & technique research on frontier AI safety.
Today we’re publishing our evaluation of DeepSeek V4.1 Flash-1017, the first report in our long-term third-party safety evaluation and research program.