Traces the evolution from Transformer to ChatGPT, arguing that foundation models' core features are few-shot learning without fine-tuning and conversational UI, with large-scale training being the means rather than the goal.
华山派剑宗气宗实力错位现象：一个多维度的学术探析
展示Claude V3.5长上下文和不偷懒特性的创意实验，以"剑宗的师叔气功好，气宗的徒儿剑法高"为题，让AI撰写了一篇13000字的学术论文，探讨金庸武侠中华山派的能力发展机制。
5分钟给全天相机加上云量识别功能
5分钟用AI给全天相机加上云量识别功能：利用GPT-4V理解云量，让AI自动编写调用API的代码，展示AI时代开发效率的革命性提升。
关于AI知识引擎的随想
构想一个AI知识引擎：自动收集会议和日常对话、提取有价值的知识并索引、在输出时及时提醒。三大挑战是数据采集、知识提取和实时参与。
Reflections on AI Knowledge Engines
Envisioning an AI knowledge engine that records conversations, extracts insights, and surfaces relevant knowledge when needed. Three key challenges: data collection, knowledge extraction, and real-time participation.