WHAT NEW IN X10.31 SAT

X 上的 AI 合集档案 · 22 个合集 · 61,986 条

jevPOST

Opus 思考、Jev 决策的省钱 agent 架构

用 Jev 做选上下文、路由任务、错误恢复等选择题,把贵模型留给真正推理,代码仍控流程。

DamiDefi
@DamiDefi15 天前收录原推发布于 2026.10.14
DamiDefi @DamiDefi原推发布于 2026.10.14
在 X 上打开原推

Your AI coding agent doesn't need a frontier model to decide which file to load. Yet that's exactly what you're paying for. Every time your agent picks project notes, routes a task, recovers from a tool error, or chooses which tests to run, it may be burning expensive reasoning tokens on a multiple-choice question. There's a better architecture. Opus 5.5 thinks. Jev decides. Your code stays in control. Here's how to cut the waste: → Use Jev to select relevant context instead of loading eve

x.com/damidefi/status/2110369058722107620采集于 2026.10.15 10:43