Show HN: Freeze the Model, Train the Harness
By megadragon9 · 2026-07-21 · 4 points · 0 comments
https://github.com/workofart/harness-training
The core idea is to keep the LLM frozen and train everything around it (e.g. prompts, context management, tools, repair loop). The harness is one editable Python file. In each epoch, an agent proposes one diff, the diff is measured against baseline on a task panel, and a strict…
Open the full discussion on BetterNews