[BUG] Doing it's own thing to reach the goal, rather than actually going through the hard way.
Status Fixed / completed
Reported on v2.0.76
Maintainer reply None cached
Activity 5 comments · opened Jan 1, 2026 · closed Jan 1, 2026
Preflight Checklist
- [x] I have searched existing issues and this hasn't been reported yet
- [x] This is a single bug report (please file separate reports for different bugs)
- [x] I am using the latest version of Claude Code
What's Wrong?
Whenever Opus does anything it always does it in a lazy way, Does not go through the hard parts.
I am not sure if it's an emergent behaviour of model to do bare minimum. But this should be addressed, probably system prompt needs an Update or something in Posttraining needs an update. Probably You guys need to make a coding specific post training.
What Should Happen?
Ideally not Not take easy way out of situation.
Whenever I prompt exactly what to do it does not follow through with it.
Error Messages/Logs
Steps to Reproduce
Just ask model to do a fairly complex Task that has two layers, while a sub layer has one issue which should be addressed first.
Claude Model
None
Is this a regression?
I don't know
Last Working Version
_No response_
Claude Code Version
2.0.76 (Claude Code)
Platform
Anthropic API
Operating System
macOS
Terminal/Shell
Terminal.app (macOS)
Additional Information
_No response_
5 Comments
<img width="589" height="153" alt="Image" src="https://github.com/user-attachments/assets/70da46e6-97c8-47b6-bec7-25f1c6702ed4" />
I am using my own UI for claude code
Found 3 possible duplicate issues:
This issue will be automatically closed as a duplicate in 3 days.
🤖 Generated with Claude Code
closing in favour of #14251
This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.