State of Technology is built around a simple frustration: most news products show articles, but readers are trying to understand events. One AI model launch, chip shortage, antitrust filing, or platform change can appear as a wall of repeated headlines. The useful unit is the underlying story and the sources confirming it.
The X News Inspiration
This project is partly inspired by the useful part of X's news experience: fast public conversation can make breaking stories legible before traditional homepages settle. The goal is not to recreate X's private ranking system. SoT has no access to it and does not claim to model it.
The narrower attempt is to capture a few visible behaviors in an open, inspectable way: group related coverage, expose source corroboration, detect momentum, explain why a story ranked, and keep the reader close to the original reporting.
Ranking Signals
Events first
The same announcement can produce dozens of near-identical articles. SoT groups those articles into one event so the reader sees what happened before seeing who covered it.
Corroboration matters
A story reported by one outlet is useful. A story independently covered by many outlets is a stronger signal. Source count is treated as a first-class ranking input.
Velocity matters
A story with fresh coverage arriving quickly is different from a slow follow-up cycle. SoT tracks recent article arrival patterns and marks fast-moving clusters.
Evidence should be visible
Story pages show why a cluster ranked, which source classes support it, and how coverage developed over time.
How It Works
SoT polls public RSS feeds and bounded sitemap sources, canonicalizes URLs, clusters similar headlines with lexical and embedding-based matching, scores the resulting story clusters, and serves a cached API. No request triggers live clustering, so the news pages stay fast while the scheduler keeps refreshing the edition.
Read the MethodologyQuick Answers
What SoT covers
The current edition is focused on AI technology: model releases, labs, agents, chips and compute, security, policy, science, and the companies shaping the AI stack.
What corroboration means
Corroboration is the number of distinct sources attached to a story cluster after exact duplicate URLs are collapsed. It is a signal of how broadly an event is being reported.
What velocity means
Velocity measures whether fresh articles are arriving faster than earlier coverage in the same rolling window. It is designed to surface breaking or accelerating stories.
What sources are used
SoT reads public RSS feeds and bounded public sitemaps from AI news outlets, broad technology desks, lab blogs, security sources, practitioner newsletters, and filtered Hacker News queries.
What the evidence panel shows
The evidence panel is deterministic: it is built from article metadata, source counts, source classes, ranking inputs, and publication order rather than model-written prose.