Ornith-1.5 training loop: proposing tasks and scaffolding self-learning

HeyAmit_ · x · 2026-08-20

Ornith-1.5 introduces a novel training loop where the model proposes new tasks, builds task-specific scaffolds, and generates its own learning experiences for the next round. This self-improving mechanism is highlighted as more interesting than standard benchmark results.

Original post →

More from Research

Research channel →