- Home
- /
- How it works
How Viqus works
Viqus is an automated AI newsroom. Software reads a fixed set of sources, an AI model writes a short analysis of each new story, and every analysis links to the original article. This page explains each step and its limits, so you can judge how much weight to give what you read here.
From feed to page
- 01
Collect
RSS feeds of 14 publications, stories from the last 48 hours.
- 02
Deduplicate
Stories about an event already covered in the last 96 hours are skipped.
- 03
Analyze
The full text goes to the AI model, which writes the analysis.
- 04
Score
Two separate 1–10 scores: real impact and media hype.
- 05
Publish
A structure check, then the page, linked to the original source.
1Sources
Every 5 minutes Viqus checks the RSS feeds of these 14 publications and keeps stories published in the last 48 hours:
- Hugging Face Blog
- AIModels.fyi
- The Gradient
- Mistral AI
- OpenAI News
- DeepMind
- AI – SiliconANGLE
- Machine Learning Mastery
- InfoQ AI
- Simon Willison
- The Verge AI
- TechCrunch AI
- MIT Technology Review AI
- Ars Technica AI
Stories that cover the same event as one already published in the last 96 hours are skipped, so you get one analysis per event rather than one per outlet.
2AI analysis
The full text of each story is analyzed by an open-weight language model (gemma4:e4b) running on Viqus' own server; articles are not sent to third-party AI services. The model produces the headline, the summaries, the key points, the "why it matters" section, the category, tags and the Viqus verdict.
The output is checked automatically for structure before publishing, but it is not reviewed by a human. Every analysis page names and links the original source. Read it before relying on any detail: the model can misread, omit context or state something with more certainty than the source does.
3The Viqus verdict
Two independent 1–10 scores separate attention from consequence.
Real impact
Likely consequences over the next 12 months or more.
- 1–2Negligible
- 3–4Affects a narrow group
- 5–6Influences a sector
- 7–8Changes competitive dynamics or regulation
- 9–10A before/after moment for the industry
Media hype
How much attention the story is getting.
- 1–2Barely covered
- 5–6Major tech outlets
- 9–10Dominating the news cycle beyond tech
The model is instructed to be critical: most news should land between 4 and 6. A high hype score with a low impact score is the most useful signal Viqus gives you — lots of noise, little change.
Scores published before October 2026 were produced with an earlier version of the instructions and run noticeably higher; compare them with each other rather than with recent ones.
4Weekly briefing
Every Monday the weekly briefing collects 8 stories from the previous week and an AI-written analysis connecting them. It is written from the analyses above, not from new reporting.
- Stories are picked by impact score. Many stories share the same score, so among equals Viqus prefers a mix of categories, sources and days, then the lower hype score.
- The model groups related stories into themes, and adds a reality check for each one: what is a real change and what is incremental or hype. Stories that fit no theme are listed on their own.
- Before publishing, the briefing is checked automatically: every selected story must appear, and the text cannot point to stories by number. A briefing that fails is generated again.
5What stays online
All analyses remain available. Only those from the last 90 days, and older ones with an impact of 9 or more, are offered to search engines; the rest stay accessible as an archive.
Corrections and contact
If an analysis misrepresents its source, tell us and we will correct or remove it.