Show HN: A live map of the news cycle, rebuilt hourly from embedded headlines

A live map of the English-language news cycle, rebuilt hourly from embedded headlines, ingests stories from Google News US and UK editions, embeds each with OpenAI's text-embedding-3-large, clusters them with hnswlib, lays them out in 2D with UMAP, groups them into topic regions with recursive DBSCAN, and labels them by an LLM. The map loads ~18MB upfront and runs client-side with zero network requests, currently displaying ~133,000 stories across 1,081 topics.

Hi HN. This is a live map of the English-language news cycle, with headlines are ingested continuously from Google News, US and UK editions. Each one is embedded with OpenAI's text-embedding-3-large, clustered into stories with hnswlib, laid out in 2D with UMAP so related topics sit near each other, grouped into topic regions with recursive DBSCAN, and labeled by an LLM. The map is rebuilt from scratch every hour. I deliberately skipped progressive loading. The whole map loads upfront, ~18MB of data, and after that everything runs client-side with zero network requests: pan, zoom, search, cluster panels. deck.gl handles all 133k points fine, even on mobile. Currently showing ~133,000 stories across 1,081 topics. Happy to answer any questions. Comments URL: https://news.ycombinator.com/item?id=49019336 https://news.ycombinator.com/item?id=49019336 Points: 3 Comments: 0