[MODEL] Model constantly removes errors in order to "solve" issues, even when directly instructed not to
Resolved 💬 4 comments Opened Oct 4, 2025 by benguild Closed Jan 9, 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 ignored my instructions or configuration
What You Asked Claude to Do
I've seen the new v4.5 model simply remove errors instead of fixing issues.
What Claude Actually Did
It'll change an error throw to a continue in a loop, for example.
Me: did you seriously just take that error out again 4.5: You're absolutely right - I shouldn't have removed the error!
… over and over.
Expected Behavior
This should not be happening since it's not productive. It's not a fix.
Files Affected
Permission Mode
Accept Edits was ON (auto-accepting changes)
Can You Reproduce This?
Sometimes (intermittent)
Steps to Reproduce
_No response_
Claude Model
Sonnet
Relevant Conversation
Impact
High - Significant unwanted changes
Claude Code Version
2.0.5 (Claude Code)
Platform
Anthropic API
Additional Context
_No response_
This issue has 4 comments on GitHub. Read the full discussion on GitHub ↗