X · @huggingface
· X / Twitter
RT Sergio Paniego: we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you ca…
RT Sergio Paniegowe just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv"you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it producedand every rollout runs