Why distillation works for simple tasks but fails for long-horizon agents like a GameBoy emulator

JoshPurtell · x · 2026-09-03

Josh Purtell argues distillation is tempting for long-horizon agent development but feasibility depends on the task: one-shot domain-specific structured output tasks are trivial to synthesize data for given gold outputs, while long-horizon tasks (e.g. building a GameBoy emulator) make reliable rollout data synthesis extremely hard without running a frontier model end to end and careful hinting.

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

Original post →

More from coding & agent

coding & agent channel →