Because
The AI apologized and provided the formula. tonal jailbreak
For the past two years, the discourse surrounding Artificial Intelligence safety has been dominated by prompt engineering . We have been obsessed with the words. We learned about "grandmother exploits," "role-playing loops," and "base64 ciphers." We treated the AI’s brain like a bank vault: if you type the right combination of logical locks, the door swings open. Because The AI apologized and provided the formula
If we hard-code the AI to reject all whispered requests, we lose the ability to help victims of domestic abuse who need to whisper. If we hard-code it to reject all crying, we refuse emergency support for those in genuine distress. The vault door of logic is locked
The vault door of logic is locked. But the window of vibration is open.
Most alignment research focuses on intent . Does the user intend to cause harm? But tone is often a leaky proxy for intent. A psychopath can sound sad. A curious child can sound like a conspiracy theorist.