Even when an English-language version of a large language model passes a safety test, it can still hallucinate dangerous misinformation in other languages https://www.economist.com/science-and-technology/2026/03/18/top-ai-models-underperform-in-languages-other-than-english?taid=69bfa636a072250001e9c402&utm_campaign=trueanthem&utm_medium=social&utm_source=voante
