mental issue of opus
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
Working with Opus is practically impossible at this point. Repeated skill/memory issues — it ignores context constantly, I have to remind it what we're doing every single message. It's like working with a mentally impaired person.
Worst part: implementation takes 40 attempts and still doesn't land. It hallucinates every time, and I had to revert work 3 weeks back because it decided on its own to do something else entirely.
This is genuine shit. Refund, nothing else.
What Claude Actually Did
Expected Behavior
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
Opus
Relevant Conversation
Impact
Critical - Data loss or corrupted project
Claude Code Version
2.1.145
Platform
Anthropic API
Additional Context
_No response_
This issue has 4 comments on GitHub. Read the full discussion on GitHub ↗