Original Summary

Watched a recent youtube veritasium on the enigma machine and was curious on how JEV would do in regards to the analysts calls made at Bletchley&#x27;s. I rebuilt the historical sequence into the software ux.<p>Results were a mixed, which is what made it interesting. Given the right crib, the Bombe breaks 22 of 25 messages; ciphertext-only against 10 plugs, 0 of 25, same wall Bletchley hit. As a judge of &quot;is this decryption German?&quot; Jev is excellent: AUC 0.9999, 159&#x2F;160 right decisions. As a crib selector it has no skill at all; its ranking is no better than the fixed list.<p>Against XGBoost an classical judges, it ties on the same kind of data. But trained on synthetic traffic and tested on real intercepts, and XGBoost drops to 53% correc versus zero-shot Jev holds at 97%. Feel free to try it here: <a href="https:&#x2F;&#x2F;enigma-jev.vercel.app&#x2F;" rel="nofollow">https:&#x2F;&#x2F;enigma-jev.vercel.app&#x2F;</a> (requires a jev typesafe api key)

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/30 10:49:30