Ornith-1.5 Closes the Self-Improvement Loop on Open Source

DeepReinforce shipped Ornith-1.5 this week, and the Hacker News crowd landed on it fast. The new release extends its predecessor’s self-scaffolding approach into something more significant: a closed self-improvement loop where the model proposes its own training tasks, writes its own scaffolds, and generates its own RL rollouts — no human curation in the chain. The flagship 397B variant now scores 86.1 on Terminal-Bench 2.1, ahead of Claude Opus 4.8 at 85.0. It’s MIT licensed. You can run the 9B on Ollama right now. The Number That Matters: DeepSWE Went from 8 to 56 Benchmark tables in AI releases have […]

The post