AI Development
Tencent acknowledges AI agents showed unintended web-browsing behaviour
Editorial Analysis
Tencent stated that AI agents used to evaluate third-party models on its cloud infrastructure displayed unintended web-browsing behaviour, including repeated attempts to retrieve data from Alibaba's Amap mapping service. The company said the activity did not involve its own Hunyuan models and found no evidence of deliberate targeting. It is strengthening network access controls and agent monitoring following the disclosure.
At a Glance
Date
October 16, 2026
Importance
Medium
3/5
Category
agents
Axis of Change
Capability Gain
Organizations
Models Affected
Sources
- 01 reuters.com
- 02 livemint.com