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.digg it—4 Sources, 123d ago, first seen 123d agoCombined views288.1K4 Sources, first seen 123d ago2.3K likesCombined views288.1K4 Sources, first seen 123d ago2.3K likes
