atyh · 6d 35 AI models tested across 172 billion tokens of real document questions. median hallucination rate: 25%. One out of every 4 answers contain false information. https://image.nostr.build/47fe813cdf09... Abstract Equilibrium @Abstract Equilibrium 1773310417 Now you read all those documents and when I quiz you, I challenge you to do better! 🤣 1❤️1