Um ótimo trabalho de @carlobaronio @pmmarsella @ybenpan! Ainda há um longo horizonte pela frente para agentes de vários turnos :)
Cognition
Cognition7 de mai. de 2025
Our research interns present: Kevin-32B = K(ernel D)evin It's the first open model trained using RL for writing CUDA kernels. We implemented multi-turn RL using GRPO (based on QwQ-32B) on the KernelBench dataset. It outperforms top reasoning models (o3 & o4-mini)! 🧵
5,97K