The technical architecture
This section is currently available in English only.
The system is a pipeline of three independent services. Each does one thing well.
Three services, one result
What makes this hard
The dimensions sound clean on paper. In practice, the edge cases are everywhere:
- An obituary for a beloved community figure scores high on "social cohesion" but isn't constructive news. We had to learn to filter these out.
- A story about a successful clinical trial scores high on "evidence level" and "wellbeing impact," but if it's behind a paywall, we can't read enough to score it properly.
- An article about a breakthrough technology might score 9/10 on technical performance but 2/10 on benefit distribution, because only wealthy nations have access. The weighted average captures that tension.
- The same story can match multiple lenses. A community-led reforestation project is both "Recovery" and "Belonging." It appears once, in the narrowest lens it qualifies for (Recovery, then Discovery, Belonging, Solutions, Thriving).
Summarization
Articles come from sources worldwide. We use AI to create clear summaries, so readers quickly understand what each story is about. The summarization pipeline runs open-source models on local hardware: Gemma 4 12B for most new articles, given a list of the names and numbers in the article so it keeps them straight, and Gemma 3 27B for the rest. No cloud AI writes the summaries. The names in that list are found by wikineural-multilingual-ner (Babelscape, CC BY-NC-SA 4.0; Tedeschi et al., 2021), used unmodified.
Headlines are model-written too, not taken from the source. Both are labelled as AI-written on every article and in our feeds, as Article 50 of the EU AI Act requires of us.
Translation is currently switched off; the site runs English-first.
For details on how we keep summaries grounded and verifiable, see why you can trust this.
Open source
The scoring filters and their training pipeline are not public at the moment; the dimensions and weights for several lenses are described on the lenses page. The site itself is built with standard open-source tools (Astro, Tailwind, SQLite).
- Two earlier-generation filters published on Hugging Face (the five in use today are not public)
Images
Images on ovr.news come from four sources:
- Source images: The preview image (og:image) from the original article. We don't host these ourselves; your browser loads them directly from the source.
- Wikimedia Commons: Freely available images under the CC BY-SA 4.0 license. Attribution is always shown.
- Unsplash: Images under the Unsplash license. Attribution is shown out of respect.
- Curated library: A collection of CC-licensed images we maintain ourselves.
Last updated: November 2026