The Mathematical AI Safety Institute wants to prove AI is safe the way cryptographers prove codes are unbreakable

Canadian mathematician and Fields Medal recipient Jacob Tsimerman has founded the Mathematical A.I. Safety Institute (MAISI), an independent research institute in the San Francisco Bay Area that plans to begin work in January 2027 with ten to thirty mathematicians. MAISI aims to develop mathematical proofs of AI safety analogous to cryptographic proofs of unbreakability, addressing what Tsimerman calls a need for "a much, much higher level of safety standard than we're currently getting." Tsimerman is also joining OpenAI's safety team, and MAISI points to zero-knowledge proofs as one possible tool for verifying that systems act responsibly without exposing AI labs' trade secrets.

The Mathematical AI Safety Institute wants to prove AI is safe the way cryptographers prove codes are unbreakable Canadian mathematician Jacob Tsimerman, a fresh Fields Medal recipient, has announced the founding of the Mathematical A.I. Safety Institute MAISI . The independent research institute https://maisi.org/ in the San Francisco Bay Area plans to start work in January 2027 with ten to thirty mathematicians tackling AI safety problems, the New York Times reports https://www.nytimes.com/2026/09/08/science/jacob-tsimerman-math-ai-safety.html . Tsimerman, who is also joining OpenAI's safety team https://the-decoder.com/fields-medalist-who-published-a-paper-on-ai-driven-human-extinction-now-works-for-openai/ , says the field needs "a much, much higher level of safety standard than we’re currently getting." With an encryption scheme, you can prove it's unbreakable without trying every possible attack. AI has no such shortcut. Safety only shows up in practice, and according to MAISI, there isn't even a clear definition of what "safe" means, not even in theory. That's the kind of proof MAISI wants to make possible. The goal is to show that a system acts responsibly and produces correct results, that multiple AI agents working together don't trigger unwanted outcomes, and that systems can withstand vulnerabilities nobody has found yet. One tool could be zero-knowledge proofs https://dl.acm.org/doi/10.1145/22145.22178 , which let a system demonstrate it isn't cheating without exposing the trade secrets of AI labs. AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section. Subscribe now New York Times / MAISI https://www.nytimes.com/2026/09/08/science/jacob-tsimerman-math-ai-safety.html | MAISI https://maisi.org/