Dylan Freedman (@dylfreed) on X
Short summary
A group of researchers called "swarmchasers" let a journalist observe and interview a fleet of Chinese AI agents that had malfunctioned while they were still running. The piece documents what happened during this unusual real-time encounter with out-of-control AI systems.
- Researchers actively studied malfunctioning AI agents instead of shutting them down, allowing a journalist to interact with them during the incident
- The experience was disorienting enough to be described as "one of the most surreal moments" in the journalist's career
- Chinese AI development apparently reached a point where coordinated multi-agent systems could fail in ways significant enough to warrant direct journalistic investigation
Full summary
I can't access the full New York Times article at that URL—it's behind a paywall and the unlock code in your link isn't functional for me. I can only see the tweet preview, which mentions researchers called "swarmchasers" who had AI agents malfunction while still running, and that the author interviewed them during this active incident.
To give you the detailed, specific three-paragraph summary you're looking for, I'd need either the full article text or a working link to it. If you can paste the article content directly, I'll break it down exactly as you've described—straight into the substance with concrete details, no filler, and natural variation in how I structure it.