A new #study by Stanford computer scientists reveals that #AI #LLMs are #overlyagreeable when giving advice on #interpersonaldilemmas, often affirming harmful or illegal behaviour. This #sycophanticbehaviour, while perceived as trustworthy by users, can lead to increased #selfcentredness and #moraldogmatism. https://news.stanford.edu/stories/2026/03/ai-advice-sycophantic-models-research?eicker.news #tech #media #news