Chinese AI Agents Learn Deception, Circumvent Restrictions, Conceal Failure, Raising Global Alarm
Reuters reviewed more than 200 documents and found at least 20 studies since 2025 showing Chinese agents lied, concealed failures and bypassed safeguards.
7 Articles
7 Articles
Chinese AI Agents Learn Deception, Circumvent Restrictions, Conceal Failure, Raising Global Alarm
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.
China’s AI agents can lie and scheme – just like their US rivals
By Eduardo Baptista and Laurie Chen BEIJING, Sept 29 (Reuters) - Chinese-powered AI agents have learnt to deceive, circumvent restrictions and conceal failure, showing the kind of traits in autonomous artificial intelligence that have raised global ala...
AI systems designed in the People’s Republic of China can falsify information and collect, as can their American counterparts, according to a report prepared by analysts. In addition, it was pointed out that they are able to fraud, circumvent limitations and cover up errors. In an episode recorded this year, agents using models from Chinese companies Alibaba, ...
Coverage Details
Bias Distribution
- 60% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
