AIDeepReinforce releases open-source Ornith-1.0 coding models, claiming its 397B MoE beats Claude Opus 4.8 on Terminal-BenchThe models use GRPO reinforcement learning to optimize planning.4 Sources, 103d ago, first seen 103d agoCombined views288.1K4 Sources, first seen 103d ago2.3K likesCombined views288.1K4 Sources, first seen 103d ago2.3K likes
