Don't be a meat proxy

Don’t be a meat proxy / 别做“肉身代理”

Don’t be a meat proxy 别做“肉身代理”

Aug 03, 2026 2026年8月3日

Too often I ask a question in Slack or leave feedback under a merge/pull request or argue with friends in a WhatsApp group and get back: Claude said: [giant response verbatim] 我经常在 Slack 上提问、在合并请求（merge/pull request）下留下反馈，或者在 WhatsApp 群组里与朋友争论时，收到的回复却是：“Claude 说：[一大段原封不动的回复]”。

Please don’t do this. I mean, I’ve done this. But I’ve been on the receiving end too many times now. This is not adding value. I can talk to Claude myself. It’s going to be faster and I get to control the context. I don’t need a meat proxy in between. 请不要这样做。我是说，我自己也曾这样做过。但现在我作为接收方，已经经历过太多次了。这根本没有增加任何价值。我自己就能去问 Claude，那样更快，而且我还能掌控上下文。我不需要中间有个“肉身代理”。

Reading AI output is extra effort. It’s verbose, frequently contains all too plausible nonsense, and is increasingly jargon dense. I recently got this sentence from Claude: NATS control-plane events: stream leader election / R3 quorum re-form during pod churn. Jesus. I had to lookup almost every word to make sense of this. 阅读 AI 的输出是一种额外的负担。它冗长啰嗦，经常包含听起来头头是道但实则胡扯的内容，而且术语密度越来越高。最近我从 Claude 那里收到了这样一句话：“NATS 控制平面事件：Pod 搅动期间的流领导者选举 / R3 法定人数重组”。天哪，我几乎查了每一个词才弄懂它在说什么。

By all means, prompt AI. But don’t just relay the output. Read it, understand it, validate it, and then write a response in your own words (a decent certificate that you’ve done the prior steps). Making that effort is value you can add. 当然，你可以使用 AI，但不要只是简单地转发它的输出。请阅读它、理解它、验证它，然后用你自己的话写出回复（这能证明你确实完成了上述步骤）。付出这种努力，才是你能贡献的价值。

Take code review in particular. Shipping some code can be done with close to zero effort now: Copy/paste the ticket description into Claude Code. Don’t look at the code or read what Claude has written. If there’s any feedback from reviewers, copy/paste that into Claude Code as well. If necessary, iterate. That works. But who has done the implementation? The reviewers did, using Claude Code, and you as a meat proxy. 以代码审查为例。现在交付代码几乎不需要费什么力气：把工单描述复制粘贴进 Claude Code，不用看代码，也不用读 Claude 写了什么。如果有审查者的反馈，也把它复制粘贴进 Claude Code。如果有必要，再迭代几次。这确实行得通。但到底是谁完成了实现？是审查者们，他们通过 Claude Code 完成了工作，而你，只是一个“肉身代理”。