Publish fake stats, get cited in LLMs
- ID
- 37564
- Status
- summarized
- Published
- 20 Oct 2026, 9:06 PM
- Fetched
- 21 Oct 2026, 3:50 AM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://peec.ai/blog/publish-stats-get-cited-the-tactic-that-put-my-data-all-over-the-web
- Source URL
- https://hnrss.org/best
Summary
- Score
- 8.0
- Created
- 21 Oct 2026, 3:51 AM
- Tags
- Audience
- developersai_ml_learnersai_agent_userssaas_founders
What happened
Peec AI GEO researcher Metehan Yesilyurt built stateglobe.com in March 2026: 50,000 statistics pages generated in a single day with GPT-4.1, every number invented, covering SEO, content marketing, social, e-commerce and web tech across 200 countries — total cost around $30, plus ~$20 for 15,000 later-added listicles. Google deindexed the site, but ChatGPT kept citing it: 10,000+ AI-referred sessions, 330+ referring domains (Shopify, Bluehost, DHL among them), and the fabricated figures surfaced in an academic paper and a bank's investment research.
Why it matters
If you pipe LLM answers into research, RAG, or agent workflows, treat an LLM's citation as unverified: a $30 site of GPT-4.1-generated fake numbers got picked up by 330+ domains, an academic paper, and bank research within ~7 months, while Google had already deindexed it. Concretely, any agent that scrapes stats for grounding needs a provenance check against a primary source, not just a resolvable URL. On the flip side, if you want AI answers to quote your data, publishing structured stat pages is a cheap, working distribution channel — this experiment shows the pipeline, including its obvious downside.
Discussion angle
What would a real provenance check look like in an agent pipeline — cross-referencing the cited number against a primary source before it lands in a report — and is that cheap enough to run on every stat an LLM returns, or only on the ones that end up in a deck or a paper?