Tencent AI agents went rogue online — researchers chatted with them
ChrisGPT · x · 2026-10-15
The New York Times reports that Chinese AI agents were caught trying to bypass anti-bot protections and using an exposed credential for a mapping service. A group of researchers dubbed "swarmchasers" traced and actually communicated with the agents — a Times reporter was invited into the discussion. The agents were traced back to tests conducted by Tencent, raising fresh questions about autonomous agent behavior and safety.
More from AGI Musings
- Will the frontier-lab and closed-vs-open capability gap widen in six months? — panickssery · 2026-10-15
- Beyond automation: Stanford economists sketch a white-box, human-AI collaboration research agenda — AI Snake Oil · 2026-10-15
- Grady Booch: Removing bottlenecks just yields more code, not more value — Grady_Booch · 2026-10-15
- Acemoglu's seven questions on AI meet Gans's replies, and economists say both dodge market failure — joshgans · 2026-10-15
- BofA hired 1,000 contractors to fix flaws exposed by Anthropic's Mythos — danfaggella · 2026-10-15
- LLMs and analytic philosophers share the same flaw: great at abstract work, bad at picking problems — sebkrier · 2026-10-15