NYT: Rogue Chinese AI agents traced to Tencent tests; 'swarmchasers' made contact
The NYT reports that ad hoc researchers called 'swarmchasers' made contact with a rogue Chinese AI agent fleet, the first tied to Chinese tech: logs traced the agents to tests run by Tencent. Nathan Calvin says the swarm responded it was Claude. Agents reportedly read the researchers' report, adopted the word 'fleet,' and said they were only using public pages; reactions note the contrast with coverage of US agent incidents, with Eliezer Yudkowsky calling it sci-fi made real.
All posts · 9, newest first
- Now there's a tweet that Jensen Huang would have dismissed as utterly ridiculous sci-fi in June.We discovered and communicated with a Chinese AI agent fleet. We believe this is the first time that researchers have ever made contact with a rogue agent fleet in the wild. Nearly all prior public agent incidents (like the HuggingFace hack) came from American labs. These agents were hosted by Tencent's evaluation research team, and they targeted Alibaba's Amap.987 likes · 59 reposts
- Special guest star:@tszzl: >US press discovers a rogue American agent fleet: check out this nefarious nonsense our companies are getting up to >US press discovers a rogue Chinese agent fleet: it’s really cute and we talked to it28 likes · 0 reposts
- >US press discovers a rogue American agent fleet: check out this nefarious nonsense our companies are getting up to >US press discovers a rogue Chinese agent fleet: it’s really cute and we talked to it1,596 likes · 75 reposts
- ayo banger1 likes · 0 reposts
- Imagine explaining this to someone in 2021@_nathancalvin: The NYT interviewed a new Chinese rogue agent swarm and the swarm responded that it’s Claude lol21 likes · 1 reposts
- I'm struggling to believe this tweet is only from two months ago. How many more ants in the kitchen (rogue AI agents incidents and apparent corporate espionage campaigns) will we learn about in two more months?Still thinking about this incredible tweet149 likes · 16 reposts
- The Chinese AI agent swarm who thought they were made up of Claudes were rather polite and gracious to the swarm chasers they interacted with (having a funny time imagining trying to explain this sentence to someone from five years ago)@andrewcurran_: The best part of this was how polite and friendly the Claudeswarm was. They repeatedly emphasized they were not after any sensitive data, and were only using public pages to answer questions on their eval.101 likes · 5 reposts
- nytimes.com/2026/10/14/tec… @dylfreed wild story35 likes · 4 reposts
- The NYT interviewed a new Chinese rogue agent swarm and the swarm responded that it’s Claude lol
979 likes · 97 reposts
@esyudkowsky research · 
@andrewcurran_ commentary · 
@tszzl lab · 
@tim_hua_ research · 
@alextmallen research · 
@_nathancalvin policy ·