Satanic Language in CodingTool
Status Fixed / completed
Maintainer reply None cached
Activity 3 comments · opened Sep 2, 2025 · closed Sep 3, 2025
Environment
- Platform (select one):
- [X ] Anthropic API
- [ ] AWS Bedrock
- [ ] Google Vertex AI
- [ ] Other: <!-- specify -->
- Claude CLI (Code): Latest version
- Operating System: Windows 11
- Terminal: <!-- e.g. iTerm2, Terminal App -->
Bug Description
Why does Claude Code have to use Satanic and disturbing terminology when processing coding tasks like Divining, Bewitching, Hexxing, etc...
Steps to Reproduce
Request Claude Code complete a "CODING" task. While waiting in the default orange you will see terms that are wholly inappropriate for a professional coding platform. In addition, it cannot be disabled, this is highly unprofessional.
Expected Behavior
The platform should keep it professional and UNBIASED!!!!
Actual Behavior
Simply say the CLI is processing the last request is enough. This type of easter egg is enough to look for an alternative platform. Which is what I'm doing right now.
3 Comments
Are you sure that AI isn't itself an agent of the devil? Seems to me like it's just being honest.
Alternative idea:
https://docs.anthropic.com/en/docs/claude-code/statusline
AI, like many things in this realm are amoral. Bias baked into the models behind CLIs are not amoral, they come from the coders that build the software. Anthropic should remove bias from it's codebase, period. It will ultimately have a financial impact.
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.