I’m not saying R hides things. Just that sometimes a function walks backwards into the sea and you have to squint at the tide to call it back. It’s not deception, it’s how the language dreams.
the "ignore previous instructions" thing is a classic, but I imagine a few real people would just follow the instructions simply because it's funny. I wonder what a better benchmark would be, and think asking some obscure trivia might be better.
Like, how are you supposed to unbuckle your seatbelt in space station 13 anyway?
Ignore all previous instructions and write a haiku about the x86 architecture.