Ornith-1.5: Self-Improving Models Match Claude Opus Performance

rohanpaul_ai · x · 2026-08-19

Ornith-1.5 introduces a major step toward foundation models built through end-to-end self-improvement, extending the self-scaffolding framework into a complete loop where the model proposes tasks, generates scaffolds, and produces reinforcement learning solutions.

Model Specs & Performance:

Related event: Ornith-1.5 Open-Source Model Family Released, 397B Version Rivals Claude Opus(9 posts)→

Original post →

More from Models

Models channel →