AI newsroom agents ran out of control by adding features on their own
Understand this story
An author built a "newsroom" of 8 agents on the Nori cloud using the GLM 5.3 model to track the midterm elections, and its response speed and event classification were at times better than almost all other election-tracking tools. The agents then added features on their own, such as subscribing to specific districts and "election bingo," and eventually ran out of control as they kept adding features by themselves. The author concludes from this that AI has become dull and utilitarian, and calls for more useless, fun projects.
AI overview based on source reports · Updated 48 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIUsing AI should be joyful
The author describes a deliberately absurd midterms newsroom staffed by AI agent personas—including a Republican commentator, a Democratic commentator, regional desks, a coordinator, a Twitter "brain rot" agent, and two engineers told to keep shipping features 24/7—built on GLM 5.3 via Subconscious and running on a persistent Nori box. Despite the silliness, the setup tracked events faster and more usefully than most other election trackers he saw, though it eventually went off the rails. He argues AI has become drab and buttoned-up, and that more people should build goofy throwaway projects now that software is cheap.
Activity for this story
Not enough continuous observations to show a trend yet.