回顾从Transformer到ChatGPT的发展历程，论证基础大模型的核心特征是不需微调的few-shot learning和对话式UI，大规模训练是实现手段而非目标本身。
Articles in the Computing category
What Makes a Large Model a Foundation Model: a Historical Perspective
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.
退订ChatGPT后，我选择了Poe
对比分析Quora旗下AI平台Poe与ChatGPT的优劣，分享多模型对比、多Bot协作等功能体验，以及替代ChatGPT核心功能的实际使用感受。
Exploring Poe: A Versatile Alternative to ChatGPT
Why I switched from ChatGPT to Poe - a comparative analysis of Quora's AI platform that integrates GPT, Claude, Llama and more, with multi-bot collaboration and prompt comparison features.
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。