prime-rl

Fermisense, a consultancy, spent roughly $500 of GPU time fine-tuning a Qwen3.5-9B open model with reinforcement learning and claims it beat GPT-5.5, Gemini 3.1 Pro, Claude Opus 4.8, and Claude Fable …

Prime Intellect released prime-rl 0.6.0, an open framework for asynchronous reinforcement learning on trillion-parameter Mixture-of-Experts models, enabling training on agentic RL workloads with optim…