Originally published on rohitraj.tech
DeepReinforce shipped Ornith-1.0 on June 25, 2026 — an MIT-licensed family of coding models that learn to write their own agentic scaffold during RL instead of using a human-designed harness. The 397B flagship hits 82.4 on SWE-bench Verified (DeepReinforce reports it edges past Claude Opus 4.7); the 9B runs on a single 24GB card. This is the builder\'s read: what self-scaffolding actually is, real vLLM and Ollama run commands, an honest comparison table, when to skip it, and the chat-template gotcha that will send your local copy into a runaway loop.
Read the full version with code samples, diagrams, and architecture details: Ornith-1.0: The Self-Improving Open-Source Coding Model, Tested (2026)
More engineering notes: rohitraj.tech/en/notes
Top comments (0)