Dataconomy
  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Whitepapers
    • AI Models Leaderboard
  • AI toolsNEW
  • Newsletter
  • + More
    • Glossary
    • Conversations
    • Events
    • About
      • Who we are
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
Subscribe
No Result
View All Result
  • AI
  • Tech
  • Cybersecurity
  • Finance
  • DeFi & Blockchain
  • Startups
  • Gaming
Dataconomy
  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Whitepapers
    • AI Models Leaderboard
  • AI toolsNEW
  • Newsletter
  • + More
    • Glossary
    • Conversations
    • Events
    • About
      • Who we are
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
Subscribe
No Result
View All Result
Dataconomy
No Result
View All Result

New Xikipedia app replicates StumbleUpon experience with Wikipedia data

The platform uses a basic non-machine learning algorithm that runs entirely in the user's browser to protect personal data.

byKerem Gülen
February 3, 2026
in Tech, News
Home News Tech
Share on FacebookShare on TwitterShare on LinkedInShare on WhatsAppShare on e-mail
Google Preferred Source

Developer Lyra Rebane created Xikipedia, a web app that displays Wikipedia entries in a social media-style feed drawn from Simple Wikipedia. The app uses a local recommendation algorithm to suggest content based on user interactions without collecting or sharing data.

Xikipedia algorithmically generates the feed from Simple Wikipedia content. The landing page states, “It is made as a demonstration of how even a basic non-[machine learning] algorithm with no data from other users can quickly learn what you engage with to suggest you more similar content.” This approach ensures the system adapts to individual preferences through direct engagement patterns observed within the session.

The algorithm operates entirely locally on the user’s device. The landing page further explains, “No data is collected or shared here, the algorithm runs locally and the data disappears once you refresh or close the tab.” This design eliminates server-side tracking and preserves user privacy by confining all processing and storage to the browser environment.

Stay Ahead of the Curve!

Don't miss out on the latest insights, trends, and analysis in the world of data, technology, and startups. Subscribe to our newsletter and get exclusive content delivered straight to your inbox.

Users control the feed by selecting specific categories, which can include custom categories defined by the user. Each post consists of a summary extracted from the corresponding Simple Wikipedia entry. Liking a post influences future recommendations, as Rebane explained: it increases the probability of displaying posts from the same category, its parent categories, and articles linked within the original entry.

i made a version of wikipedia you can doomscrollxikipedia.org

— Rebane (@rebane2001.bsky.social) 2026-02-01T23:43:37.999Z

Tapping or clicking any post directs users to the full Simple Wikipedia article for complete reading. The selection process draws from articles at random, which means extended scrolling through the feed exposes users to not-safe-for-work material present in some entries.

Initial access requires loading approximately 40 MB of data, resulting in a brief waiting period before the feed becomes interactive. This data volume encompasses the necessary text, images, and structures pulled from Simple Wikipedia to populate the endless scroll capability.

Simple English Wikipedia provides the content foundation with more than 278,000 articles available. This extensive corpus supplies hundreds of thousands of potential posts for users to explore through continuous scrolling.

Updates to Simple Wikipedia occur less frequently than those to the main Wikipedia edition. For instance, the discography section on one musician’s page lacked entries for their two most recent albums, reflecting the slower revision cycle of the simplified version.

Xikipedia serves as a platform for discovering new topics, akin to the function of StumbleUpon, where users encounter varied articles as a gateway to further research on Simple Wikipedia.


Featured image credit

Tags: Wikipediaxikipedia

Related Posts

Apple touchscreen MacBook could launch with M5 Pro chips

Apple touchscreen MacBook could launch with M5 Pro chips

June 29, 2026
Apple touchscreen MacBook could launch with M5 Pro chips

Apple touchscreen MacBook could launch with M5 Pro chips

June 29, 2026
OpenAI limits ChatGPT 5.6 access to government-approved users first

OpenAI limits ChatGPT 5.6 access to government-approved users first

June 26, 2026
Apple to skip M6 Pro and Max chips and launch M7 in 2027

Apple to skip M6 Pro and Max chips and launch M7 in 2027

June 26, 2026
IBM unveils world’s first sub-1nm chip with new nanostack architecture

IBM unveils world’s first sub-1nm chip with new nanostack architecture

June 26, 2026
Apple raises prices across Macs, iPads and home devices

Apple raises prices across Macs, iPads and home devices

June 26, 2026

LATEST NEWS

Apple touchscreen MacBook could launch with M5 Pro chips

Apple touchscreen MacBook could launch with M5 Pro chips

OpenAI limits ChatGPT 5.6 access to government-approved users first

Apple to skip M6 Pro and Max chips and launch M7 in 2027

IBM unveils world’s first sub-1nm chip with new nanostack architecture

Apple raises prices across Macs, iPads and home devices

BEST AI MODELS LEADERBOARD

See the best AI models, ranked by intelligence, benchmark results, speed and token price. Find the most suitable LLMs, Text-to-Image, Image Editing, Text-to-Speech, Text-to-Video and Image-to-Video  artificial intelligence model for your tasks and business.

LATEST TOOLS

WatchMyCompetitor

TokkingHeads

Fellow.app

Octoparse

AnyToSpeech

Vrew

Fireflies

SpeedLegal

Teachable Machine

Unriddle

Dataconomy

COPYRIGHT © DATACONOMY MEDIA GMBH, ALL RIGHTS RESERVED.

  • About
  • Imprint
  • Contact
  • Legal & Privacy

Follow Us

  • News
    • Artificial Intelligence
    • Cybersecurity
    • DeFi & Blockchain
    • Finance
    • Gaming
    • Startups
    • Tech
  • Industry
  • Research
  • Resources
    • Articles
    • Guides
    • Case Studies
    • Whitepapers
    • AI Models Leaderboard
  • AI tools
  • Newsletter
  • + More
    • Glossary
    • Conversations
    • Events
    • About
      • Who we are
      • Contact
      • Imprint
      • Legal & Privacy
      • Partner With Us
No Result
View All Result
Subscribe

This website uses cookies to improve your experience. You can choose to accept or reject them. Visit our Privacy Policy.