Why swapping in Jev for context compaction underperforms: models are trained on their own strategy

pvncher · x · 2026-09-18

Responding to mitsuhiko's idea of using Jev for agent context compaction, pvncher pushes back on two fronts: first, as Theo noted, Jev lacks the reasoning trace as context for why a tool was called; second, models are deeply trained on their own compaction strategy, so even a good alternative idea will underperform what the model was trained to use well.

Related event: Agent Authors Debate Jev Compaction: Multiple Framework Builders Question Its Context Compression Value(5 posts)→

Original post →

More from coding & agent

coding & agent channel →