jevPOST
Jev 做研究 agent 的判定器：比 LLM judge 更稳更便宜
有人用 You.com agent 监控商业风险，对比发现 Jev 与 LLM judge 报告质量相当，但 LLM 同一威胁评分反复横跳且漏掉 5/11 项调查，Jev 全中，还便宜 250 倍、快 3–6 倍。
TypeSafe AI
@typesafeai2026.10.02收录原推发布于 2026.10.02
TypeSafe AI @typesafeai原推发布于 2026.10.02
Jev is a huge power-up for research agents! @edwardirby built a @youdotcom agent that monitors business risks, and compared Jev to an ordinary LLM judge. • Same report quality • But the LLM flip-flopped: 0.35 -> 0.68 -> 0.50 on the same threat • the LLM missed 5 of 11 investigations. Jev missed none. • Jev was 250x cheaper, 3-6x faster Write-up 👇
这条是引用着另一条写的：「不用前沿模型搭风险 agent：Jev 做类型化判断」
x.com/typesafeai/status/2105733977147617750采集于 2026.10.02 10:03