Applied AI research lab building RL environments and infrastructure to train reliable long-horizon agents for frontier labs and enterprises. Known for OpenThoughts, an open reasoning dataset downloaded over 500,000 times, a contributor to Terminal-Bench, and GEPA, a genetic-evolutionary optimizer for automated prompt and policy search.
Bespoke Labs' new 12-task benchmark separates two things: what a team gains from extra agents and what it gains from actually coordinating. For frontier models today, coordination adds almost nothing.