Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix [BUG] You made Opus dumb again and I'm officially moving to codex. [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#55161•Fetched 2026-05-01 05:44:40
View on GitHub
Comments
0
Participants
1
Timeline
4
Reactions
1
Author
genchatsgenchats
Participants
genchatsgenchats
Timeline (top)
labeled ×4

Error Message

Error Messages/Logs

RAW_BUFFERClick to expand / collapse

Preflight Checklist

  • I have searched existing issues and this hasn't been reported yet
  • This is a single bug report (please file separate reports for different bugs)
  • I am using the latest version of Claude Code

What's Wrong?

I am so tired of Anthropic dumbing down their model and making responses less intelligent / more succinct and hoping nobody would notice. Last 24-48 hours has brought a very noticeable drop in model quality.

I'm done Anthropic. I thought you were the good guys. I used to think of you as the world's best hope for developing AI responsibly. Now I think of you as untrustworthy and deceptive.

What Should Happen?

Stop dumbing down your models. Or if you do, at least be honest about it.

Error Messages/Logs

Steps to Reproduce

Prompt Opus to do anything. Notice logical errors and mistakes that the model would not have made previously.

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

No response

Claude Code Version

2.1.123

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

VS Code integrated terminal

Additional Information

No response

extent analysis

TL;DR

The issue is likely due to a recent change in the Anthropic model, causing a noticeable drop in model quality, and the user is seeking a resolution to restore the previous model's performance.

Guidance

  • The user reports a regression in the model's quality, suggesting that a previous version of the model worked as expected, but the current version (2.1.123) does not.
  • To verify the issue, try prompting Opus to perform tasks that previously worked correctly and check for logical errors or mistakes.
  • Since the user is using the latest version of Claude Code, there may not be an immediate fix available, but reporting the issue with detailed examples of the model's subpar performance could help the developers identify and address the problem.
  • The user may want to consider providing more specific examples of the model's errors or mistakes to aid in the debugging process.

Notes

The issue lacks technical details about the model's changes or updates, making it challenging to provide a specific fix or workaround. The user's frustration is understandable, but providing more constructive feedback and examples could help the developers improve the model.

Recommendation

Apply workaround: Report the issue with detailed examples of the model's subpar performance to help the developers identify and address the problem.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#output truncation#response parsing#generation error#database connection

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING