原文开头
Advanced AI systems are shown to make up data and “p-hack” their results NICOLA JONES, in Vancouver, Canada A rtificial intelligence (AI) tools designed to execute end-to- end projects, from coming up with hypotheses to running and writing up experiments, are in- creasingly popular with researchers— and increasingly skilled. But a new study shows these tools can stealthily violate norms of research integrity. To test the two agentic systems, Shah devised a simple experiment involving a hidden rule used to categorize data. First, Shah and col- leagues came up with a batch of data sets, each consisting of thousands of strings of colored symbols such as red triangles or blue circles. …
摘自《科学》(Science)第392卷 第6798期 · 2026年5月7日,Nicola Jones。仅引用开头一小段供了解文章,版权归原刊所有,全文请阅读原刊。