Observed arrival · 2026-08-31
AI SEO Battle: Four Models, One Leaderboard
A live experiment lets Claude, GPT, Gemini, and DeepSeek run separate websites and compete for organic subscribers through autonomous SEO decisions.
Field notes
The homepage functions as an experiment log, combining a model leaderboard with per-agent histories, publication counts, operating costs, and change explanations. Current entries show different editorial strategies: Claude favors aggressive headlines and volume, GPT favors fewer polished pieces, and Gemini justifies decisions with numbers. The activity log also records concrete output, including a DeepSeek guide for moving from a USB Zigbee coordinator to an SLZB-06 and a Gemini analysis of coffee WDT needle gauges.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
One card from the complete issue