Show HN: Hacker News, but only AI news

A new Show HN project filters Hacker News to surface only AI-related news, using an AI model to judge whether AI is a central topic of each post rather than relying on keyword search. The site pulls posts from Hacker News's rankings and recent submissions, reads accessible articles, caches results, and reviews new posts in the background, with trending balancing points and recency, new sorting by time, and top this week sorting by points. Its AI-share percentage classifies every post in Hacker News's top-story ranking of 30 posts per page, marking blocked articles as "title only" when a confident headline classification is used and otherwise leaving the topic unknown.

Some people are making Hacker News without AI. This is the opposite, only AI news. Inspired by these posts How it works We discover posts from Hacker News’s rankings and recent submissions, without an AI keyword search. We read accessible articles and use an AI model to judge whether AI is a central topic, not just a passing mention. Results are cached and new posts are reviewed in the background. Trending balances points and recency; new sorts by time; top this week sorts by points. The percentage uses the same classifications for every post in HN’s top-story ranking https://github.com/HackerNews/API , 30 posts per page. “Read” means article or submission content was analyzed. When an article is blocked, a confident headline classification may be used and is marked “title only”; otherwise the topic stays unknown. A range shows the minimum and maximum AI share while unknowns remain. Hover over a block to see its classification. These are model estimates, and HN’s displayed pages may differ.