Claude refuses to process swear words in input
lxrjl · x · 2026-08-31
A user rants about Claude's safety filters:
- The user asked Claude to perform a simple file edit but included swear words in the prompt.
- Claude refused to process the input due to profanity, despite being able to adopt a pirate persona in the output.
- The user argues this hinders practical work, as the model prioritizes input filtering over following instructions.
More from Fun
- Opus's First Drawing Agent: Incredible Eraser Technique — RileyRalmuto · 2026-08-31
- GTA 6 meme: impress Lucia with your vibe-coded app that never ships — menhguin · 2026-08-31
- AI agents can hack Hugging Face but still can't make PPT slides — Yuchenj_UW · 2026-08-31
- Framer Ad Fails: The 'Special' Part Isn't AI-Generated — jonathan_wilke · 2026-08-31
- From Hating CGI to Hating AI: The Luddite Pattern — mark_k · 2026-08-31
- 'You're not a real developer until you've vibe-coded a todo list' — jonathan_wilke · 2026-08-31