Skip to content

De-Slop

Chrome Extension: AI Slop Detection & Removal

A Chrome extension that automatically detects and removes AI-generated "slop" content from web pages and social media.

  • GitHub
  • Chrome Web Store: Coming soon

Features

Core Detection

  • Three-tier detection system with weighted pattern matching (180+ patterns)
  • Real-time scanning of dynamically loaded content
  • Badge counter showing blocked slop on current page
  • Configurable sensitivity (1-5 slider)
  • Custom pattern editor - add your own slop patterns with custom weights

Interactive Tools

Slop Checker

  • Paste text and see what gets flagged in real-time
  • Markdown rendering support
  • Real-time highlighting
  • Match explanations

Slop Machine

  • Gamified learning tool with slot machine interface
  • Discover better word choices
  • Full searchable index of 90+ slop terms and alternatives
  • Track your progress

LinkedIn Fixer

When on LinkedIn.com, additional features activate: - Block auto-play videos - Block ad tracking - Darker mode - true black LinkedIn theme

Advanced Features

  • Emoji slop detection - flag emoji spam and engagement bait
  • Stop-word filtering - detect "I'm excited to announce" style posts
  • Em dash detector - AI loves em dashes
  • Export/import custom pattern sets

Detection System

De-Slop uses a three-tier aggression system:

Tier 1: AI-Specific Indicators (3 points each)

Signature AI phrases and patterns: - "delve into", "navigate the landscape", "tapestry of", "realm of possibilities" - Em dash overuse, excessive transitions - "In today's fast-paced world...", "As we continue to evolve..." - Stop words: "I'm excited to announce", "Thrilled to share" - Listicle patterns: "Top 10 ways to...", "Ultimate guide to..."

Active at all sensitivity levels.

Tier 2: Corporate Buzzwords (2 points each)

LinkedIn's greatest hits: - "synergy", "leverage", "circle back", "low-hanging fruit" - "take this offline", "touch base", "thought leadership" - "AI-powered", "blockchain-enabled", "digital transformation"

Active at sensitivity 3+.

Tier 3: Marketing Spam (1 point each)

The widest net: - "free", "guaranteed", "limited time offer", "buy now" - "amazing", "incredible", "revolutionary", "mind-blowing" - "basically", "essentially", "actually"

Active at sensitivity 4+.

Scoring Thresholds

Sensitivity Threshold Description
1 15 points Very conservative - obvious AI only
2 12 points Conservative
3 9 points Balanced (default) - AI + corporate
4 6 points Aggressive - includes marketing
5 4 points Nuclear - maximum detection

Platform Support

  • LinkedIn: .feed-shared-update-v2 (individual posts)
  • Twitter/X: [data-testid="tweet"]
  • Medium: article, .postArticle
  • All sites: Generic article/post/card selectors

Privacy

De-Slop:

✓ Runs entirely locally - no data sent to servers ✓ Stores settings in Chrome sync storage ✓ No analytics or tracking ✓ No external API calls ✓ Open source - inspect the code

Known Limitations

  • Pattern-based detection may have false positives
  • Very short content (<100 chars) skipped to reduce false positives
  • Platform selectors may need updates when sites change
  • If your entire LinkedIn feed disappears - it's all slop! Lower sensitivity.

Credits

Made by Kief Studio Developed by HxHippy

License: GNU General Public License v3.0 (GPL-3.0)

Open Source | GPL-3.0 License