I just googled something and Google put its AI summary top, which incorrectly used a Facebook post - misinterpreting it. The Facebook post itself was an AI summary of a user post - which AI had also misinterpreted. The result is the Google answer was just total bollocks.

10/10 no notes.

@GossiTheDog I am literally scoring a RAG right now and the dataset returned has the *exact* correct command...

given that command, the llm still returned totally fabricated nonsense.

It's nuts all the way down