Flight is a testable characteristic (at least within certain bounds: a chicken can only fly a little, but it certainly flies more than a worm or a penguin).
What test would you propose where an LLM (or an RL agent containing an LLM) would reliably fail, but where an average human would reliably succeed?
What test would you propose where an LLM (or an RL agent containing an LLM) would reliably fail, but where an average human would reliably succeed?