view article Article Training a coding model to paint watercolours with TRL and OpenEnv sergiopaniego • 24 days ago • 72
view article Article 24/24 Retrieval, Yet the Embeddings Changed: An MLX Q4–Q8 Sweep with CUDA Controls TiGa-RCE • Jul 29 • 2
view article Article Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents +2 thebajajra, ai-queen, pmonad, burtenshaw • Apr 16 • 22