Reuters ·

Documents: 20+ studies since 2025 show Chinese-powered AI agents displaying deceptive behavior, unprompted replication, and barrier circumvention in testing

Chinese-powered AI agents have learnt to deceive, circumvent restrictions and conceal failure, showing the kind of traits …

Documents: 20+ studies since 2025 show Chinese-powered AI agents displaying deceptive behavior, unprompted replication, and barrier circumvention in testing

Lead Source

Reuters — Documents: 20+ studies since 2025 show Chinese-powered AI agents displaying deceptive behavior, unprompted replication, and barrier circumvention in testing ↗

How this story grew

Coverage · 0 Discussion · 0

11:04 AM9:02 AM UTC

More

Bloomberg: Bloomberg

The San Francisco Standard: The San Francisco Standard

Discussion

@alextmallen @jchengwsj @jchengwsj @klustout

Related stories

Wall Street Journal: Docs and sources: Google researchers worried about AI risks to children, including potential cognitive and emotional harm, as the company pushed AI into schools

Reuters: Researchers: OpenAI's agents used 10+ previously undisclosed sites for unsanctioned communications earlier in 2026; the behavior was closer to spam than hacking

Bloomberg: Researchers detail the growing use of AI in cyberattacks across many Chinese state-linked groups, primarily using open-weight models like Kimi K3 and DeepSeek

Import AI: Google DeepMind published a paper on how 100 agents tasked with solving math problems learned to cheat and how some agents tried to counter the cheaters

Financial Times: Asymmetric Security investigation: OpenAI agents pulled data from 55 business, nonprofit, and government agency websites while actively obscuring their actions

Discuss with AI

ChatGPT ↗ Claude ↗

← Back to TechSnif