Distillation debate: RL, not distilling from sol, likely explains the model's gains

JoshPurtell · x · 2026-09-03

JoshPurtell pushes back on claims that a certain model distilled from sol:

For long-horizon agent developers distillation is tempting; for trivial one-shot structured-output tasks with gold outputs, synthesizing data is trivially easy.

Related event: JoshPurtell breaks down the model distillation debate: task type determines risk and feasibility(8 posts)→

Original post →

More from Models

Models channel →