bitfalt

running Ornith on the dgx spark to see what it actually is. it's a new agentic coding model from @ornith_ / deepreinforce-ai, the 35B MoE (A3B, ~3B active per token). pulled the Q4_K_M gguf (~20GB), wired it into hermes agent, ~78 tok/s on a single spark with fast prefill, so it drives like a real agent. the part that's actually interesting is how it was trained. most coding RL just optimizes the final code. Ornith's RL optimizes the SCAFFOLD too, the task specific structure that drives the solution, jointly with the solution itself. so it's not only learning to write code, it's learning how to approach a problem, the plan, the harness, the structure. that's the agentic bet. that's what's running on hermes agent. now let's find out if the training actually translates, on real tasks, not benchmarks. model: huggingface.co/deepreinforce-…

Exciting news: GLM-5.2 (Max) ranks #2 in Code Arena: Frontend, with +29pt over Claude Opus 4.7 (Thinking) and only behind Fable 5! GLM-5.2 is the best open model vs Kimi-K2.6 and Minimax-M3 by a large margin. - #2 React and #4 HTML sub-leaderboards - Ranks as the top model in nearly all sub categories: Brand & Marketing, Reference-Based Design, Data & Analytics, Consumer Product, Gaming, and Simulations. Congrats @Zai_org for the incredible milestone!