The Algorithm

Every ~15 minutes the wire pulls its sources. Exact duplicates — the same article arriving from different feeds — collapse first: links are stripped of tracking noise and reduced to one canonical address, so a story can only enter once.

Then coverage of the same story is threaded together. Each new report is compared against every thread born in the last 72 hours using word-overlap similarity, with headline words counted 2× — the headline is the story’s identity. Score at least 0.3 against a thread and the report joins it; otherwise it starts a new one.

Inside a thread, the original is simply the earliest published report — even one that arrives late. Follow-ups nest under it. That’s the de-noising promise: the source first, the echoes beneath.

score = log2(1 + reports) × √sources × e^(−hours since last report / 24) × breaking boost

breaking boost = min(1 + 0.6 × log2(1 + sources per hour since first report), 3)

Coverage — how much reporting a story has drawn, log-dampened so forty reports isn’t worth forty times one. Independence — how many different outlets are on it. Sixteen outlets covering one event is news; sixteen posts from one outlet is a live-blog. This is the heart of the ranking. Freshness — scores decay on a 24 hour curve from the last new report; fresh coverage resets the clock, silence sinks the story. Velocity — how fast a story is gathering independent sources. Three sources in thirty minutes is breaking; three sources in a day is not. Fast-gathering stories get a boost (weight 0.6, capped at 3×, with threads younger than 15 minutes scored as that age) that fades naturally as a thread ages — so brand-new news can reach the top ranks while it is still news.

Threads with activity in the last 48 hours are ranked; the top 100 make the page and the top 10 get the full treatment — original on top, up to 4 follow-ups nested under it, at most one per outlet so a thread shows breadth, not one outlet’s volume. Scores recompute after every pull, roughly every 15 minutes. Above the ranks, the Breaking strip shows up to 6 of the newest threads born within the last 1 hour that aren’t already ranked up top — regardless of score, so a story that broke minutes ago is visible before the ranking has anything to measure.

No engagement weighting. No click optimization. No personalization — yet. What you see is coverage, independence, and time.

Signed out, the ✕ and 👍 live only in your browser: they change what you see and feed nothing else. Nothing is tracked.

Signed in, three things are stored against your account, each timestamped: headlines you click through on the story lists (the breaking strip is untracked), stories you 👍, and stories you ✕. That is the whole reading-data list; the account itself adds the operational minimum every sign-in system carries — your email, session records, and short-lived sign-in-link timestamps. It exists so your history and controls follow you across devices, and it is yours to see on your history page (the free tier views the window below; Pro views all time). Free accounts view the last 30 days; everything is kept regardless, so upgrading unlocks your past instantly rather than starting over. Removing an interaction removes it server-side too — with one v1 honesty note: a second signed-in device that still holds the old state can re-sync it back until full tombstone sync ships.

The honest part about aggregate data: what the whole readership clicks and skips is a real future ranking signal (everyone engaging = a boost; everyone skipping = a demote), and if we ever feed it into ranking, the formula on this page will say so explicitly — the same way every other number here is public. Today it feeds nothing.