x.comthreadThomas Wolf (@Thom_Wolf) on X
Thom Wolf announces an open release for multi-harness RL: training any model with reinforcement learning on any task set directly inside the agent harnesses people actually use, such as Claude Code, Codex, and OpenCode, rather than a synthetic training-only environment. The pitch is that the same model behaves differently depending on which harness runs it, so RL training needs to happen within the target harness to transfer properly.
TL;DR Hugging Face's Thom Wolf releases an open method for RL-training models inside real coding-agent harnesses like Claude Code, Codex, and OpenCode.
Organisations named here
- Claude Code
- Hugging Face
- OpenCode
- Thom Wolf
Technologies named here
- Claude Code
- Codex
- OpenCode
Techniques named here
- Multi-harness RL
Related in training
