The Mathematical AI Safety Institute wants to prove AI is safe the way cryptographers prove codes are unbreakable
Fields Medalist Jacob Tsimerman founds the Mathematical AI Safety Institute (MAISI) to pursue provable AI safety guarantees, launching January 2027.
Canadian mathematician and new Fields Medal recipient Jacob Tsimerman announced the Mathematical A.I. Safety Institute (MAISI), an independent Bay Area institute that will begin work in January 2027 with 10-30 mathematicians. Tsimerman is also joining OpenAI's safety team and argues AI needs a much higher safety standard. MAISI aims to formalize what safety means, prove multi-agent systems avoid unwanted outcomes, and explore tools like zero-knowledge proofs that let labs demonstrate correctness without exposing trade secrets.
- MAISI will employ 10-30 mathematicians in the San Francisco Bay Area starting January 2027
- Founder Jacob Tsimerman won a Fields Medal and is joining OpenAI's safety team
- Goals include rigorous definitions of safety and guarantees for multi-agent AI systems
- Zero-knowledge proofs cited as a potential tool for verifiable AI behavior
- Vendors
- OpenAI
- Countries
- CanadaUnited States
From the original article
1 min read at the-decoder.com
Canadian mathematician Jacob Tsimerman, a fresh Fields Medal recipient, has announced the founding of the Mathematical A. I. Safety Institute (MAISI).
By Manuel Uth · the-decoder.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.