Think your AI is reliable? Think again. Hallucination rates fluctuate wildly...

https://reidyxab469.iamarrows.com/the-confidence-paradox-why-your-best-llms-sound-more-certain-when-they-are-wrong

Think your AI is reliable? Think again. Hallucination rates fluctuate wildly across benchmarks, making it tough to compare models. HalluHard now shows a 30.2% error rate even with web search enabled