[lukeschlather]

Did they ask any substantive questions? It sounds like they asked movie trivia questions, in a way that the LLM was almost guaranteed to be wrong. So extremely low-stakes where there is no conceivable downside to being wrong.

[tsimionescu]

That was exactly the point - there was no downside to saying you just don't know, people didn't know, but they still chose to use (what they thought was) AI and got it wrong that way.