token 用量暴涨10倍,模型质量下降,代码改了一遍又一遍改不对

Resolved 💬 1 comment Opened Apr 25, 2026 by L940527 Closed May 29, 2026

Preflight Checklist

  • [x] I have searched existing issues for similar behavior reports
  • [x] This report does NOT contain sensitive information (API keys, passwords, etc.)

Type of Behavior Issue

Claude modified files I didn't ask it to modify

What You Asked Claude to Do

我是 Claude Pro 用户,最近几天明显感觉到:

  1. token 用量暴涨:同样的任务,以前几百 token 搞定,现在动辄几万

token,一小时用完5小时的额度。

  1. 代码能力下降:以前能准确理解需求、几百 token 修好的问题,现在花了8万 token

还没修好,改了一遍又一遍,越改越乱。

  1. 模型行为变了:感觉是内部悄悄换了配置或者模型,但没有通知用户,直接让用户用更多

token、得到更差的结果。

这种体验完全不值这个价格。希望 Anthropic 能正视这个问题,给用户一个说法。

What Claude Actually Did

花了8万 token,同一个问题改了四五遍没改好,
越改越乱,最后还原也没完全恢复原状。

Expected Behavior

几百 token 内准确理解需求,一次改好。
之前版本可以做到,最近几天明显变差。

Files Affected

Permission Mode

Accept Edits was ON (auto-accepting changes)

Can You Reproduce This?

Yes, every time with the same prompt

Steps to Reproduce

_No response_

Claude Model

Sonnet

Relevant Conversation

Impact

Critical - Data loss or corrupted project

Claude Code Version

2.1.119

Platform

Anthropic API

Additional Context

_No response_

View original on GitHub ↗

This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗