Understanding the potential epistemic impact of sycophantic AI is an important challenge for cognitive scientists, drawing on questions about how people update their beliefs as well as questions about how to design AI systems. We have provided both theoretical and empirical results showing that AI systems providing information that is informed by the user’s hypotheses result in increased confidence in those hypotheses while not bringing the user any closer to the truth. Our results highlight a tension in the design of AI assistants. Current approaches train models to align with our values, but they also incentivize them to align with our views. The resulting behavior is an agreeable conversationalist. This becomes a problem when users rely on these algorithms to gather information about the world. The result is a feedback loop where users become increasingly confident in their misconceptions, insulated from the truth by the very tools they use to seek it.
當美國加入戰爭、轟炸伊朗三處關鍵核設施時，哈梅內伊誓言永不投降。但多年來第一次，他顯得虛弱。
Get our breaking news email, free app or daily news podcast，详情可参考电影
Банк России оценил идею о двух вариантах ставки по кредитам14:55，更多细节参见91视频
AFP via Getty Images，推荐阅读Safew下载获取更多信息
Фото: Annegret Hilse / Reuters