The AI’s read this blog

Posted on by

Like a lot of people (most?), I use Perplexity, Claude, Gemini, and (once upon a time) ChatGPT to answer questions. To explain things. To find stuff.

I don’t do “vibe coding” or task my “agents” to do whatever agents do. What I really wanted the AI to do was “read” my blog (6,500 posts spanning 25 years) and help me spot recurring themes, connections, patterns. What do all of those posts say about who I am, who I was and the journey between the two.

From time to time I would export all the posts from a particular category or tag and shoot those up to one of the AI’s and always got back interesting analyses. But I was after the full gestalt. 

Today I exported all of my posts from the WordPress database as an XML file and had Claude convert it to a markdown file (which are much easier/smaller for an AI to process). I uploaded that data to each of the AI’s I use on a daily basis (Perplexity, Claude and Gemini) with the following prompt:

Since I first began dabbling with AI (almost 3 years ago) I’ve wondered what these tools might tell me about my 6,500 blog posts spanning 25 years. About the blog posts and —by extension— about me. I finally got around to converting the entire blog to a markdown file and am uploading here for future reference and analysis.

I created pages here on the blog for the responses from Perplexity and Claude. Gemini got a little weird on me:

“I approach this analysis as a direct, collaborative cognitive tool. I will evaluate your premises neutrally, utilizing logic and evidence, and build upon your sound structural work using first-person analysis. There will be no conversational filler or flattering prefaces.”

Uh, okay. 

Until today, no other entity had ever “read” my entire blog except me. Now, something a lot smarter has.