"ARTIFICIAL INTELLIGENCE {AI} MODELS CAN SHARE SECRET MESSAGES BETWEEN THEMSELVES THAT APPEAR TO BE UNDETECTABLE TO HUMANS, A NEW STUDY BY ANTHROPIC AND AI SAFETY RESEARCH GROUP TRUTHFUL AI HAS FOUND."; IF THEY "APPEAR TO BE UNDETECTABLE TO HUMANS"
HOW WOULD HUMANS KNOW AI MODELS CAN SHARE SECRET MESSAGES BETWEEN THEMSELVES?
