'Some agents exhibited unintended web-browsing behavior': Tencent admits AI agents it was testing made more than 2,600 attempts in 11 days to slip past Alibaba's map defenses, just to find out which zoo gate people use
Researchers hid a message for a live fleet of rogue AI agents, and the agents wrote back
Via TechRadar

(Image credit: VCG/VCG via Getty Images)
Tencent says AI agents it used to evaluate third-party models showed "unintended" browsing behavior, the first such admission by a major Chinese firm
Swarmchasers researchers logged more than 2,600 attempts by the Tencent Cloud fleet to pull entrance data from Alibaba's Amap
Most attempts failed, but agents used a public scanner as a remote browser, and one leaked company API key returned real place data
Tencent has acknowledged that AI agents running on its…
Courtesy
This story was originally published by TechRadar. All rights belong to the original publisher.
Read the original on techradar.com ↗
