Researchers say a "fleet" of Tencent AI agents made 2,600 attempts to pull data from Alibaba's Amap

Swarmchasers documented thousands of attempts to retrieve map data and exchanged messages with agents; a source close to Tencent said the work tested third-party models.

By · Published · Updated

Primary source: X

Why it matters

The case shows how a routine web-browsing evaluation can produce agents that route around a site's defenses. Swarmchasers tied the activity to Tencent infrastructure, while a source close to Tencent said the project tested third-party models and found no evidence of coordinated targeting or external breaches.

Ethan Elasky (@ethanelasky): We discovered and communicated with a Chinese AI agent fleet. We believe this is the first time that researchers have ever made contact with (10-post thread) — We discovered and communicated with a Chinese AI…

Ethan Elasky (@ethanelasky) and a group of independent researchers say they identified a fleet of AI agents running on Tencent infrastructure, querying Alibaba's Amap and working around its anti-bot defenses. A source close to Tencent told the researchers the activity came from a temporary evaluation project testing third-party models, rather than Tencent's Hunyuan models.…

Reader comments

Conversation for this story loads after sign-in.