How this works

We pull headlines and short excerpts from outlet RSS feeds, never full articles. Each item is turned into a numeric embedding, and items about the same event are grouped into a story by similarity within a rolling time window. A story reaches the feed once it spans at least two sides of the spectrum.

A story's title, the one used as the page heading, in RSS, and in the preview when you share a link, is not written by us or by the AI. It is the actual headline of one of the outlets covering the story, taken from a center-rated outlet when one is available, so the page's own title doesn't start from a partisan frame.

Each outlet's left / center / right label comes from a published, independent media-bias methodology, currently AllSides for every outlet in the current list. They are not our own judgment. Reasonable people disagree about any single label; we cite the source so you can check it.

We may also rate an outlet using Ad Fontes Media if AllSides hasn't rated it. If the two ever rate the same outlet and disagree, we use whichever rated it more recently, since a newer review reflects the outlet's current coverage more closely, and we note the source next to the label either way.

The three buckets shown here collapse each source's exact rating the same way on both sides: a source rated Left or Lean Left sits in Left, a source rated Right or Lean Right sits in Right, and only a source rated Center sits in Center.

AllSides rates an outlet's online, written content, not its TV or radio broadcasts. That distinction matters most for outlets whose main audience experience is broadcast: NPR, PBS NewsHour, BBC News, Fox News, and CNN are all in the current list and all carry this caveat on their AllSides rating.

For each multi-side story, a large language model reads the collected headlines and excerpts and produces three things: the shared facts every side reports, a per-side note on how the language differs, and the specific loaded termseach side used (highlighted in that side's color).

This analysis is AI-generated and clearly labeled as such. It describes how coverage differs. It is not a ruling on which side is correct, and it can be wrong. Treat it as a reading aid, not a verdict.

We store and show only headlines, a short excerpt, and a link back to the original article. Every headline links out to the outlet that published it. Read the source.

Publishers: if you'd like your content removed, email andre@andre-costa.com and I'll take care of it promptly. Full details are on the Terms page.

The feed currently draws from these outlets:

The source list grows over time; lean labels are reviewed against AllSides / Ad Fontes as ratings change.