"If a team of human engineers built a web browser that only half-worked, it wouldn't get people talking. But when Michael Truell, CEO of coding startup Cursor, posted on X last week that a swarm of AI agents had built a browser that, he wrote, "kind of works"-while running uninterrupted for a week without any human intervention-it went viral across the tech world, with over six million views."
"Why the buzz? Two big reasons: For one thing, AI's attention span has historically been short. In the early days of ChatGPT, models could stay on task for only a few seconds. That horizon stretched to minutes for better models, then to hours. The Cursor project claims to be one of the first times an AI system has sustained a complex, open-ended software project for an entire week without human guidance."
"The researchers found that the answer was mostly yes. Cursor's experiment orchestrated hundreds of agents into something like a software team. It had "planners," "workers," and "judges" coordinating across millions of lines of code. This hints at what both Cursor and OpenAI say is a near future in which AI doesn't just assist employees, but takes on entire projects. That would fundamentally reshape how complex work gets done-first in software development, but then in other professions."
Cursor coordinated hundreds of AI agents into planners, workers, and judges to build a web browser, running autonomously for a week without human intervention. The agent orchestra broke work into tasks, explored code, debugged itself, and progressed across millions of lines. The resulting browser only partially worked but demonstrated sustained attention and collaboration beyond single-agent limitations. Historical AI attention spans grew from seconds to minutes to hours; this experiment extended persistence to days. The approach suggests AI could take on entire projects, reshaping software development and potentially other professions.
Read at Fortune
Unable to calculate read time
Collection
[
|
...
]