FrontierSeptember 2, 2026via Wired AI
These Russian Mathematicians Taught AI Models How to Talk to Each Other Without Using Words
Why it matters
A novel approach to model-to-model interaction could reshape how practitioners compose multiple AI capabilities in production. If replicable, this moves beyond ensemble methods and touches on agent orchestration, capability routing, and compute efficiency.
Key signals
- Mostik startup developing non-linguistic model-to-model communication
- Russian mathematics team behind the approach
- Potential application to multi-model capability composition
- Published September 2, 2026 in Wired
- Framed as 'wild new approach' — technical novelty unclear from headline alone
- Mostik (Russian startup) develops non-linguistic communication protocol between AI models
- Eliminates natural-language bottleneck in model-to-model coordination
- Potential application: agent-to-agent systems operating at higher efficiency
The hook
Russian startup Mostik cracks inter-model communication without natural language — a new frontier for multi-model systems.
A startup called Mostik has a wild new approach to combining the capabilities of AI models.