Four research directions in HF's harness adapter training: trajectory tasks, new harnesses, transfer
yb2698 · x · 2026-11-06
The author lists the directions packed into this harness adapters training run:
- New RL tasks built from open-source trajectories
- A new harness — opencode, alongside NousResearch's hermes and Pi
- The safeagents plugin for reward-hacking-free RL training
- Whether a model never explicitly trained on agentic domains can learn to use harnesses — the Twil-9B experiment
More from coding & agent
- Dev shows multi-agent crew auto-creating a Black Friday discount code end-to-end for $0.10 — pramodk73 · 2026-11-06
- Developer says Codex wrecked his server after a reboot request, costing $10,000+ — burny_tech · 2026-11-06
- Exo: Berkeley's agent runtime that edits its own harness, cutting model cost 35-61% — dair_ai · 2026-11-06
- Symbolic belief revision plus geometric projections lifts RAG reranking to 0.481 nDCG@10 — letandrewcook · 2026-11-06
- Free open-source AI Engineering from Scratch course teaches math-first — HowDevelop · 2026-11-06
- Charter: A Lean 4 DSL for Formally Verified Rules Governing AI Agents — QuixiAI · 2026-11-06