精选理由
Ethan Mollick聊Codex和Claude Code的痛点:用户该能自己选副手干不同活,别让AI瞎路由。
Ethan Mollick指出Codex和Claude Code的一个问题是用户需要更多控制权来决定编排AI使用的子代理具体配置。用户希望自主选择将研究、写作或用户测试等任务委托给哪个模型。否则这又会退化成一个路由问题。该观点强调了用户对多模型协作的灵活调度需求。
原文 · Ethan Mollick
An issue with Codex and Claude Code is that users …
An issue with Codex and Claude Code is that users need more control over the particular configurations of subagents that orchestrator AIs use.
I want to decide whether to delegate research or writing or user testing, and to which models. Otherwise it is a router problem again.