To build R1, DeepSeek took V3 and ran its reinforcement-studying loop over and over. It doesn’t surprise us, because we keep learning the identical lesson over and again and again, which is that there isn't going to be one instrument to rule the world. We are going to use the VS Code extension Continue to integrate with VS Code. But nonetheless, the sentiment has been going around. My earlier article went over how to get Open WebUI set up with Ollama and Llama 3, however this isn’t the one way ...