Simon Willison Runs Ornith-1.0 Locally — an Open Coding Model That Writes Its Own RL Training Scaffold

simonwillison.net·medium signalXBlueskyLinkedInCopy link

In a June 29 hands-on, Simon Willison ran DeepReinforce's new MIT-licensed Ornith-1.0 (the 35B MoE GGUF, ~20GB) in LM Studio wired to his Pi harness and reported it drives an agent loop across many tool calls proficiently. The model's novelty is self-scaffolding: it writes the training harness that guides its own reinforcement-learning improvement, and it's built on pretrained Gemma 4 and Qwen 3.5. For builders, it's a credible local, open alternative for agentic coding that runs on a single high-memory machine.