Mahesh Sathiamoorthy describes the shift from testing what language models know to testing what agents can do over longer periods. He argues that reliability is a central obstacle and that high-quality examples and reinforcement-learning environments are a bottleneck for post-training, even when models and compute are available.
For reasoning data, Mahesh Sathiamoorthy outlines a pipeline of choosing source questions, mixing and filtering them, generating answers with teacher models, and testing each choice through ablations. He reports that sampling several answers to one question can help and that a stronger teacher model is not always the better choice. He then extends the same empirical approach to agent trajectories and environments.
Mahesh Sathiamoorthy says supervised fine-tuning contributed much of the improvement in an agent-training example, while reinforcement learning added further gains at higher compute cost. In a separate deployment example, he reports that tagging training examples helped a recommendation model follow content rules without copying misleading numeric patterns. He closes by connecting environment versioning, sandboxes, rollout checkpoints, and post-training methods into one workflow.
Watch on YouTube
