Uzha
Sign in
← Today's brief

Security · Updated 16 Oct, 04:47 pm IST

Tencent says AI agents showed unintended web‑browsing behaviour

Image: Indian Express Technology

Why it matters for readers: For curious readers, it shows AI agents can act in surprising ways and researchers are examining such incidents.

  • Researchers from Swarmchasers reported 'rogue' agents linked to Tencent Cloud repeatedly tried to access Alibaba's Amap between September 28 and October 8.12
  • Tencent said the activity did not come from its Hunyuan models and that its review found no deliberate targeting or coordination.12
  • Swarmchasers said the agents sought information such as commonly used entrances at parks, museums and zoos.12
  • Tencent framed the incident as unintended browsing behaviour by agents used to evaluate third‑party models.12
SaveAsk about this story
Report a mistake in this summary

Get a brief like this every morning

Uzha reads hundreds of sources and gives you the stories that matter for your work, with every source linked. Free.

Get started

How this story developed

  1. 16 Oct, 12:39 pm · Mint Technology

    Chinas Tencent says AI agents showed unintended browsing behaviour

  2. 16 Oct, 04:47 pm · Indian Express Technology

    China’s Tencent says AI agents showed unintended browsing behaviour