China's AI agents can lie and scheme - just like their US rivals
Economic Times Techen
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.
This is a short summary published by AI Global Wire. The full article is owned and hosted by Economic Times Tech — open it there to read it in full.
Read the full story at Economic Times Tech- Forskning
- Agenter
- Företag
Related AI news
- Scoop: OpenAI's annual recurring revenue nears $70BAxios · September 29, 2026
- Anthropic’s IPO pitch includes a warning about human extinctionArs Technica AI · September 29, 2026
- Meta’s Muse AI sent a YouTuber’s address to a strangerThe Verge · September 29, 2026
- Pushing back against AI 'doomsday narratives', Nvidia creates platform to keep rogue agents in checkEconomic Times Tech · September 29, 2026
- In a July letter to Rep. Jamie Raskin, Apple explained it removed ICEBlock and similar ICE-tracking apps in 2025 due to agent and detainee safety concerns (Clare Duffy/CNN)Techmeme · September 29, 2026
- Meta is expanding its AI agent Muse to small businessesTechCrunch AI · September 29, 2026