为编码 agent 搭 Jev harness 的工作笔记
把文件、模型、安全、完成、上下文五类调用改成 Jev 的 Score/Choice/Noul，每千次决策成本从 $605 降到 $0.17。
Jev Founder, Diogo Almeida, just released an independent working note on building a Jev harness for coding agents Not affiliated with the Jev team, just a builder mapping the loop Section 1 - the split: why harnesses already make these calls, just badly, with regex parsing prose replies Section 2 - five calls to move: files, model, safety, done, context, each one a typed Score, Choice or Noul instead of free text Section 3 - what it saves: ~400x cheaper per decision vs a cached frontier model, 0.2s median per call vs seconds of LLM latency $605 per 1,000 decisions on cold frontier calls down to $0.17 on Jev Bookmark it and read it tonight Then go rebuild your own agent loop
这条是引用着另一条写的：x.com/solst1ne/status/2101724066369654935