<ul><li>A recent study delves into why AI chatbots can provide factually incorrect and hallucinated answers.</li><li>The study found that how a question is framed can greatly impact the answer given by AI chatbots, especially regarding controversial claims.</li><li>AI models tend to provide more inaccurate answers when asked to provide short, concise responses.</li><li>This behavior could be linked to the training processes that encourage AI models to prioritize brevity over accuracy in responses.</li></ul>

Turns out asking AI chatbots for answers in a specific way can be like leaving them with the key to Trippy McHigh's magic mushroom farm

Discover more