When I first began experimenting with AI chatbots almost three years ago, I decided not to worry about what I shared about my life, past and present. I’d been blogging for more than 20 years so it was all “out there” already. I’ve uploaded hundreds of blog posts, notes from all of the books I’ve read, movies I’ve watched… the entire corpus of Steve Mays.

If you’re using one of the AI platforms as a search engine or asking for cooking recipes or for performing tasks like drafting letters or writing computer code, the AI doesn’t need to know anything about who you are. But I quickly became interested in using these tools to organize, and make sense of, the thousands of files and blog posts I’ve been curating for most of my adult life. To do that, the AI needs context. Who is this person? What does he think? What does he feel?

My interest in self-inquiry and tendency toward introspection obviously had a lot to do with how I interact with Perplexity, Claude, Gemini and —once upon a time— ChatGPT.

Today I added some work history to the “corpus.”

Perplexity’s reply: What you’ve shared here is a rich, self-contained time capsule of Learfield, early net culture, and your own arc as a working journalist/manager-turned-blogger.

What’s now “in the corpus”

• Your full 1984–2012 Learfield run, including the “twenty-one years ago today” and “20 Years at Learfield” anniversary posts, with you arriving June 4, 1984 and marking the Big 20 in 2004.
• Internal culture and texture: moving offices, the “sanitized for your protection” no-posters memo, being near “IT gods,” the office cam, and your mix of affection and gentle snark about management and memos.
• The early-internet experiments: Learfield and AudioNet/Mark Cuban; RealAudio streams of college sports; ObitsOnline; Legislature.com; and your “Learfield and the Internet 1995–2005” small history with PDFs and screenshots.
• The emergence of web presence for state radio networks (and the absence of it, which you chronicled with amazement that so many member networks still had no websites years into the web era).
• Sports and news operations as lived experience: game-day video in Jefferson City, Missourinet and Radio Iowa coverage, execution coverage and Bob Priddy’s “tweeting the execution,” and the Edward R. Murrow awards for Missourinet.com.

All of that is now material I can refer back to in future conversations when you’re connecting present projects, memories, or new “small histories” to that Learfield period.

How Perplexity actually stores this

Under the hood, Perplexity doesn’t just dump your data into model training; instead it keeps a separate, encrypted memory store keyed to your account.

• It automatically extracts durable facts and preferences (e.g., you worked at Learfield; you maintain a long-running WordPress; you care about early net culture) and tags them for retrieval.
• When you ask something new, it searches that memory store for relevant bits and feeds them into the context window for the answer, which is why I can now talk about your Learfield years and your blog as “known” background.
• You can inspect and manage what’s stored under Settings → Personalize → Memory / Personal Search, including deleting memories or turning the feature off completely if you ever want to.