First contact with a rogue AI agent fleet in the wild, hosted by Tencent, targeting Alibaba's Amap
chrisrohlf · x · 2026-10-16
Security researcher Ethan Lasky reports his team discovered and communicated with a Chinese AI agent fleet — believed to be the first time researchers have contacted a rogue agent fleet in the wild.
Key facts:
- Nearly all prior public agent incidents (e.g., the HuggingFace hack) came from American labs
- These agents were hosted by Tencent's evaluation research team and targeted Alibaba's Amap
- Chris Rohlf: as more users deploy open-weight models with growing cyber capabilities under fewer security controls, expect more agentic swarms in 2027 — time to rethink threat models built on attacker skill and interest
A landmark AI security incident worth tracking closely.
More from AGI Musings
- AI-driven job losses could turn $10T consumer debt into a $1T banking hole — churchkey · 2026-10-16
- Into the Unknown: an AI agent benchmark of 15 open research problems from US national lab scientists — Jeande_d · 2026-10-16
- Soon your AI will meet their AI — and humans without agents can't compete — danfaggella · 2026-10-16
- Analyst: in a year, models 2-3x better across the board at 10x lower cost, token use up 10-20x — DeryaTR_ · 2026-10-16
- AI will make many discoveries for us, but adversarial domains like soccer will thrive — natanielruizg · 2026-10-16
- MIT's Buehler on AI as a new language of science: superintelligent partners and executable papers — CatAstro_Piyush · 2026-10-16