Hacker News：AI 熱帖·· 9 小時前AI 評分31
使用 Unsiloed 和 TypeSafe Jev 進行文件審查
Document Review with Unsiloed and TypeSafe Jev
AI 導讀
Jev 的文件審查示例把原文確實寫明的「10 tablets」劑量標記為可能提取錯誤，造成誤報。若要檢查邏輯錯誤，建議對提取值作程式化檢查，並設置專門的錯誤處理流程，包括額外的完整 LLM 呼叫，而非使用決策模型。
正文
Jev is cool, but this example is really bad.
The example flags a '10 tablets' dose as a possible erroneous extraction, when the text says exactly that. So it is a false positive.
Furthermore, even if your goal was to catch logical errors rather than extraction errors, you are better off using programmatic checks on the extracted value and having a dedicated error handling path including additional full LLM calls, rather than decision model.
來源：Hacker News：AI 熱帖 · news.ycombinator.com