Jev 每 15 分钟过滤 400 亿数据点，替代逐条 LLM
研究团队把 LLM 移出热路径，改用 Jev 打分决定系统下一步查什么，p95 延迟各阶段明显下降。
JEV FILTERS 40 BILLION DATA POINTS EVERY 15 MINUTES. AN LLM ON EVERY RESULT COULDN'T DO IT a research team pushes that volume through their pipeline. the first version put an LLM on every result. it worked, and it was unusable: millions of explanations nobody read, latency stacking at every stage, inference bills growing with the dataset. so they moved the LLM out of the hot path and put a judge in it. jev doesn't explain the data. it scores it and decides what the system investigates next. this is the telemetry from that redesign. p95 latency before and after, stage by stage: planner -24ms, retriever -110ms, generate and verify pulled down with them. the flame strip at the top is a single agent step, 2,848 samples, and 27.6% of it is still sitting in read/poll. the pareto underneath is the part i keep coming back to. a handful of causes account for almost everything that fails. you don't fix those with a smarter model. you fix them with something cheap standing at the gate, deciding what gets through. i went through the whole decision layer. i'll show how the filtering actually works next.