SCMP: China’s AI DeepSeek secrets unveiled how they used rewards to train their R1 model to solve problems, allowing them to bypass some of the costly computational and scaling barriers to teaching AI models to reason like humans. 南華早報: 中國的人工智慧 DeepSeek 揭開了秘密，他們如何使用獎勵來訓練他們的 R1 模型來解決問題，從而使他們能夠繞過一些昂貴的計算和擴展障礙，從而教導 AI 模型像人類一樣推理.
https://www.scmp.com/news/china/science/article/3325895/deepseek-secrets-unveiled-engineers-reveal-science-behind-chinas-viral-ai-model?