Microsoft Research Blog
Technical approach for classifying human-AI interactions at scale
Semantic Telemetry helps LLMs run efficiently, reliably, and in near real-time. Learn about the engineering behind that system, including the trade-offs and lessons learned along the way—from batching strategies to token optimization and orchestration.
Video
Against Softmaxing Culture: Understanding Relational Practices in Expert and Ordinary Forms of Work
What can human-AI interaction research learn from the practices of fundi wa simu (phone repair technicians)? In this talk, Daniel will show how everyday practices of collaboration and exchange are structured by multiple and overlapping…