Notion Page on Multi-Teacher On-Policy Distillation

@cwolferesearch posted a link to the Notion page, calling it a well-written blog that synthesizes work mostly from open-source model reports. The page is titled Multi-Teacher On-Policy Distillation: A New Post-Training Primitive. Its description states that frontier AI labs use the technique to merge capabilities, recover from RL forgetting, and scale post-training on models including MiMo-V2-Flash, GLM-5, Nemotron-Cascade 2, and DeepSeek-V4.