Introduction Reasoning, the ability to reflect, verify, self-correct, and adapt, has historically been considered uniquely human. From mathematics to moral decision-making, reasoning shapes every facet of human civilisation. Large language models (LLMs) like GPT-4 have shown glimpses of reasoning, but these were achieved with human-provided examples, introducing cost, bias, and limits. In September 2024, researchers… Continue reading How the DeepSeek-R1 AI model was taught to teach itself to reason