workofart/harness-training
Train a harness to improve its model-agnostic and task-env-agnostic capabilities with PyTorch-like APIs
4 best points · 0 comments · 3 Hacker News posts · 24 GitHub stars · View on GitHub
Hacker News discussions
- Show HN: Freeze the Model, Train the Harness (4 points, 0 comments, by megadragon9, 2026-07-21)
- Show HN: Auto-train the harness, not the LLM. cross-model, cross-benchmark gains (4 points, 0 comments, by megadragon9, 2026-08-14)
- Train a Harness to improve model/env-agnostic capabilities with PyTorch-like API (3 points, 0 comments, by megadragon9, 2026-07-20)