用"笨数据+笨方法+笨模型=精知识"的方法论,将千万字小说转化为可交互查询的知识图谱,介绍线性扫描、语义检索和知识飞轮迭代的技术细节。
Articles in the Computing category
Forging a Knowledge Graph from a 10-Million-Character Epic with Three Dumb Methods
Describes building an interactive knowledge graph from a massive Chinese fantasy novel using AI, with a methodology of "dumb data + dumb methods + dumb models = refined knowledge" through iterative refinement.
模型变强了,体验却没变:AI产品的错位
分析为什么模型越来越强但用户感受不到:App设计滞后于模型能力。对比Claude、Gemini和ChatGPT的产品体验,发现OpenAI是唯一同等重视产品设计和模型能力的公司。
Smarter AI, Stagnant UX: The Misalignment in AI Products
Analyzes why users don't feel AI getting smarter despite model advances: apps lag behind capabilities. Compares Claude, Gemini, and ChatGPT products, finding OpenAI the only company equally prioritizing product design and model capability.
上一篇文章写崩了,但不是AI的锅
AI帮忙写的文章空中楼阁,不是AI写得不好,是我没喂够context。作为Manager要审核输出,作为Enabler要提供长期积累。判断界限才是协作的开始。