279 AI models hallucinated the same fake scientist.
We analyzed 2.14 million words from 250 models over 4 months. Found identical jokes, identical character names, identical cultural blind spots. This report maps where AI imagination ends and pattern replication begins.
4 months of analysis. 58 slides. No filler.
Charts, data tables, and findings. Not a single stock photo.
If you're building with AI, you're building on patterns you can't see. This report maps them.
Every model has a personality fingerprint. Measurable from punctuation alone. Most teams don't know what theirs looks like.
19 models from 12 labs independently named a knight "Sir Reginald." The training data has opinions. This report shows which ones.
What's inside
58 data-driven slides. No filler. No "AI is changing everything" padding. Just the weird, specific things we found when we read 2.14 million words of AI output.
The Chen Problem
279 appearances of the same hallucinated scientist name across unrelated prompts. 15 top hallucinated characters ranked.
Sir Reginald Convergence
Ask different models to voice a medieval knight. An impossible number of them choose the same name. Same title. Same backstory. Across independent labs.
The Joke Problem
42% open with the atom joke. 36% the scarecrow. Side-by-side: Claude, Gemini, and GPT tell the same punchline word for word.
AI's Spotify Wrapped
Every model family has a favorite movie, album, and game. The overlap will surprise you. The outliers will surprise you more.
The Fox Problem
"Draw a surprise animal." 40% draw a fox. DeepSeek: 67%. Llama: 0%. Plus the pelican that only Claude draws facing left.
Punctuation DNA
Radar charts for every major model family. Exclamation marks, em dashes, emoji density, bullet lists. You can ID the maker from formatting alone.
59:1 Western Bias
We counted every cultural reference across 7,877 responses. The geographic distribution is dramatically lopsided. One entire continent barely registers.
Garlic Pasta Every Time
Ask AI to write a recipe. The cuisine distribution tells you exactly what the training data ate. Plus: how AI writes code (there's a default font, layout, and accent color).
Contract Blind Spots
Models reviewed the same contract. Some clauses get caught every time. Others get missed by every single model. The gap is actionable.
Writing Style Fingerprints
Sentence length, heading density, bold frequency. Each model family writes in a measurably different way. We charted all of them.
Deep Breath Fiction
The most common action characters take, the #1 story setting, and the phrase that shows up in almost every creative response. AI fiction has a formula.
7 Key Findings
Summary slides with the numbers that matter. Plus methodology, actionable takeaways, and the full analysis pipeline.
The free preview covers 3 chapters. The full report has all 12, plus methodology and takeaways.
Who this is for
AI engineers
Understand convergence patterns before they show up in your product.
ML researchers
Structured hallucination data across 250 models. Citation-ready.
Product teams
Know each model's personality fingerprint before choosing one.
AI journalists
Original findings with specific numbers. Not vibes, data.
$49
4 months of analysis. Yours in one PDF.
AI Hallucination Index
58 slides, all data