从词袋到 Jev：文本分类语言模型简史
原标题：Language Models for Text Classification: From Bag-of-Words to Jev
AI 摘要
作者回顾了文本分类从词袋模型（朴素贝叶斯、逻辑回归、XGBoost）到基于 Transformer 的语言模型的历史演进，并以此背景分析近期在技术社区引发热议的 Jev AI 模型。作者认为 Jev 本质上是一个文本分类器，但比任务专用分类器更通用，比通用大模型更快更便宜，因此并非“只是一个分类器”。文章旨在帮助读者理解围绕 Jev 的炒作，作者声明与 Jev 无任何关联。
正文节选
The recently released Jev AI model has been quite a cultural phenomenon in technical communities in the past 2 weeks. While Jev aims to classify things, it’s easy to dismiss Jev as “just a classifier,” and my own view of Jev has evolved quite a bit over the past few days. In particular, my thoughts went from “classifiers used to be my bread & butter; I can easily build this myself” (more on this later) to “wow, this actually works better than I thought.” Sure, the latest state-of-the-art GPT and