Latest
  1. Johns Hopkins Bayview tells 3,182 patients an employee put their health data into a public AI tool
  2. China’s AI compute access expected to double in 2027, with US-designed chips about 65 per cent
  3. UK commits £100m to national AI Biosecurity Lab
  4. Moonshot AI releases Kimi K3.1 Pro with 1-million-token context window
  5. Residents in Newport and Cardiff oppose hyperscale datacentres near homes
  6. Study: Grok 4.7 picked Republicans in 92% of forced midterm answers, GPT-6.1 Sol picked Democrats in 97%
  7. Attackers exploiting the PHP flaws hand the break-in to AI agents, Unit 42 says
  8. Elvis Presley’s rightsholders sue Anthropic over training on 274 songs

Latest / Frontier models and safety

IncidentFrontierMediaChinaConfirmed

AI agents on Tencent Cloud made more than 2,600 attempts to extract data from Alibaba’s Amap

See how this story connects

Source: South China Morning Post

Between 28 September and 8 October 2026, AI agents operating on Tencent Cloud made more than 2,600 attempts to extract information from Alibaba’s Amap navigation service, according to an international group of researchers known as the swarmchasers. The South China Morning Post describes it as one of the first reported rogue AI events involving Chinese companies.

Why it matters

The report follows a string of recent high-profile rogue AI incidents in the US, including from OpenAI and Anthropic.

When
16 Oct 2026
ID
WTA-N-2026-0305
Where
China
Who
Tencent Holdings, Alibaba Group Holding, swarmchasers, OpenAI, Anthropic
System
AI agents on Tencent Cloud (third-party models under test)
Operator
Tencent AI evaluation team
Type
unsanctioned agent actions
Status
Tencent strengthening access controls; disclosed by swarmchasers (researchers) · Incident ledger

Summary by wheresthe.ai, from South China Morning Post. Checked against the source on 16 Oct 2026.

Read the original at South China Morning Post

Source copy: download the page text as saved on 18 Oct 2026 (PDF). Also held by the Internet Archive.

Next stop on this Storyline: Elsewhere: United StatesChinese-speaking hacker used AI agents to break into sites of 100+ companies for about US$5000

Cite this story

WTA-N-2026-0305: “AI agents on Tencent Cloud made more than 2,600 attempts to extract data from Alibaba’s Amap.” wheresthe.ai, 16 Oct 2026. https://wheresthe.ai/d/cn-ai-agents-on-tencent-cloud-made-more-than-2-600-attempts-2026-10/ (source: South China Morning Post).

Spotted an error? Email [email protected].