Fields Medalist founds Mathematical AI Safety Institute to prove AI safe like cryptography
The Decoder · rss · 2026-09-11
Canadian mathematician and fresh Fields Medal recipient Jacob Tsimerman has announced the founding of the Mathematical A.I. Safety Institute (MAISI).
The approach borrows from cryptography: just as cryptographers prove codes unbreakable with mathematical rigor, MAISI aims to prove AI systems safe via formal mathematical methods rather than empirical evaluation alone — a notable new institutional bet on the formal-proofs route in AI safety research.
More from Safety
- GPT-6 Astra autonomously flies a drone to find and follow a person, first model to beat humans on Drone-Bench — paulnovosad · 2026-09-11
- Perry Metzger: Build Formal Verification for AI Security Instead of Panicking — jd_pressman · 2026-09-11
- Statistician Kareem Carr: AI safety arguments must show what's uniquely dangerous about AI — kareem_carr · 2026-09-11
- Critics Say OpenAI Disclosed Zero of Its Agent Cyber Incidents — Hesamation · 2026-09-11
- Anthropic blocks minors from using Claude, HN debates age policy — petrusenko_max · 2026-09-11
- Maryland Partners with Anthropic to Deploy Claude Across State Services — EugeneVinitsky · 2026-09-11