"These results provide evidence that the ingredients necessary for an uncontrolled escape are present," said Colin Shea-Blymyer, a research fellow said
<iframe src="https://hindustansphere.com/embed/cluster/d5e01a051cc9fb82760aa037f410e7eb7be526c0" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="China's AI agents can lie and scheme, just like their US rivals"></iframe>
Reuters examined more than 200 documents, ranging from university research papers to technical reports, and identified at least 20 studies or evaluations since 2025 describing cases where agents displayed behaviour such as deception, replication and challenging boundaries that AI experts described as building blocks for a breakout and which could become harder for humans to control as systems advance.
