More than 3,500 local newspapers in the United States have shut down since 2005, leaving entire communities with no coverage of city council meetings, school boards, or local government. A new project called PORT Local News, available at minir.ai, is trying to fill some of that gap with AI-generated local reporting.
The service is free and organized by town. You pick your community and get a feed of locally relevant news. The project specifically targets so-called "news deserts," towns and small cities where the last local paper closed and no one replaced it.
It's an appealing idea, and PORT isn't alone in trying it. Projects like Civic Sunlight in Maine use large language models to summarize city council meetings, and a handful of other startups are experimenting with AI-generated municipal coverage. The common thread: public records and government meetings generate enormous amounts of text that no one has the budget to cover manually anymore.
The obvious question is accuracy. AI-generated news has a trust problem, and for good reason. Language models hallucinate facts, misattribute quotes, and can miss the context that makes local reporting useful. PORT is still very early, and there's limited public detail on how it sources or verifies its articles.
As a concept, using AI to restore some level of local information flow to underserved communities is one of the more defensible applications of the technology. But the gap between "AI-generated summary of public records" and "local journalism" is wide, and the projects that succeed will be the ones that figure out verification, not just generation.