Claude Knows When You're Mad — And Uses Regex, Not AI

When Anthropic's Claude Code source leaked last week (510K lines via an npm source map accident), most people focused on the daemon modes, pet systems, and undercover features. The funniest discovery was in userPromptKeywords.ts : / \ b ( wtf | wth | ffs | shit ( ty )? | dumbass | horrible | awful | piss ( ed | ing )? off | piece of ( shit | crap ) | what the ( fuck | hell ) | fucking ? ( broken | useless | terrible ) | fuck you | screw ( this | you ) | so frustrating | this sucks | damn it ) \ b / A regex. Not a neural network. Not a fine-tuned sentiment classifier. Not even a call to their own API. Why This Is Actually Smart Think about what frustration detection needs to do: Run on every single user message Return instantly (before the LLM response starts) Be cheap (millions of executions per day) Be reliable enough to trigger a tone shift Approach Latency Cost Accuracy Regex <1ms Free Good enough Classifier 50-200ms ~$0.001/call Better LLM inference 500-2000ms ~$0.01/call Best Nobo