Interactive Research DemoUnicode Steganographyby Patrick VuscanHow invisible characters and visual lookalikes can carry secret messages through ordinary text, and what that means for LLM safety.A sufficiently capable model could embed covert signals in its outputs, invisible to human readers but recoverable by another model or process. Try it yourself below.Why This Matters for AI SafetyLLM steganography is a concrete example of how AI deception could work in practice. Both techniques demonstrat...