Researchers argue LLMs don't actually understand anything.
They call it "Potemkin Understanding."
For years, we’ve evaluated AI using human tests. The Bar Exam. AP Tests. The MMLU.
When a model aces these tests, we assume it understands the concepts. Because if a human passes
i hope that in the 24th century they still sell the ghirardelli chocolate sundae in the little plastic baseball helmets at oracle park so deanna troi can get one whenever she visits san francisco
