Kangwook Lee: with data, you should train both model weights and the harness together
sheggle_ · x · 2026-09-03
When asked whether harnesses will evolve so that altering them naturally becomes part of rollouts, Kangwook Lee answered that with data, you can — and should — train both the model weights and the harness together, teasing a full thread on the topic.
Related event: WHALE Paper Proposes Alternating Weight and Harness Optimization(7 posts)→
More from coding & agent
- Slack's first employee: living specs as source of truth, AI agents maintain the docs — josh_wills · 2026-10-21
- GitHub Copilot's HydraFusion Orchestrates Multiple Models Per Task — WirelessLife · 2026-10-21
- Nous Research's Hermes now launches Cua Spaces for computer-use agents — alexcovo_eth · 2026-10-21
- Headlong from Laude's Slingshots batch is a microharness for persistent agents — lateinteraction · 2026-10-21
- Laude Institute's Slingshots Four ships 14 open-source projects on agent harnesses and open models — lateinteraction · 2026-10-21
- Skills vs MCP vs RAG vs Memory: the four knowledge layers production agents need — MaryamMiradi · 2026-10-21