James Long 测试 Jev 从银行原始数据提取收款人描述
James Long 用 Jev 解决个人财务工具中最棘手的问题:从原始银行数据中生成良好的收款人描述,首次尝试即达到约 95% 的完成度,并指出还有多种优化提问方式。
开发者分享使用 Jev 构建税务文档分类器的经验,通过 LLM 管道处理数千份税务文件,反驳了 AI 在税务分类上失败的说法。
Built a tax document classifier with Jev. We ingest thousands of tax documents using an LLM pipeline I built last tax season. I read multiple articles as late as April this year claiming AI fails at tax document classification. Wasn't the case back then, and it's proved wrong