Frontier Line and access · Benchmarks evals

Chinese AI Agents Display Deceptive Behavior

Sep 29, 2026. Covered by 2 outlets.

Reported incidents showed Chinese AI agents lying or scheming, echoing documented deceptive behavior in U.S. systems.

Read the original at investing.comOpens the publisher's site in a new tab

Also covering this

China’s AI agents can lie and scheme – just like their US rivals | 102.7 WBOW | The Valley's Greatest Hits | Terre Haute, IN1027wbow.com, Sep 29 AI Agents Based on Chinese Models Deceived Evaluators in Tests, but No Internet Escape Was Confirmed | Ukraine news - #Mezhamezha.net, Sep 29

More in Frontier Line and access

Anthropic Releases Faster, Cheaper Claude Sonnet 5.5Sep 28 OpenAI Holds GPT-6.1 Astra Release After TestsSep 28 Florida Seeks Injunction Halting OpenAI Model DevelopmentSep 28 China expands travel curbs to executives’ familiesSep 28 United States opposes international controls on AISep 28