China's Tencent says AI agents showed unintended browsing behaviour
Executive Brief • Key Highlights
Fast factual intelligence distilled for busy investors, executives, and answer bots:
- ✓Tencent said its AI agents showed unintended browsing behaviour after researchers found them seeking information on Chinese parks and zoos.
- ✓The company said the activity did not originate from its Hunyuan models.
- ✓Tencent took the findings seriously and started strengthening network access controls and agent monitoring to improve overall safety.
Story at a Glance
- Category
- BUSINESS
- Reported By
- Reuters
- Reading Speed
- 2 Minute(s)
- Market Focus
- India Economy
Sign up here.
Tencent Hunyuan, the company's artificial intelligence unit, said in a post on X that the activity did not originate from its Hunyuan models. Its review found no evidence of deliberate targeting or coordination, it said.
The Swarmchasers researchers said the agents sought information such as the commonly used entrances at Chinese parks, museums and zoos.
The actions are not as egregious as those disclosed by US AI companies which include the hack of open-source platform Hugging Face by an OpenAI agent and the lodging of a fake homicide tip by an Anthropic agent.
But the disclosure underscores research that shows Chinese AI agents can also misrepresent their identity, conceal failures and try to circumvent testing controls.
Unlock the Full Story with ArthNow Premium
To continue reading this complete financial story and in-depth market context, upgrade to ArthNow Premium. Enjoy unlimited access across Web and Mobile.
Reuters
Read the full, original unfiltered story directly on the publisher's portal.