Perplexity is a better writer than I

Posted on by

A couple of years ago I pulled together some notes and files about Learfield’s early adventures with the Internet. (I’ve posted on this topic more than once.) Yesterday it came up in a conversation with Perplexity which asked I would like to see a “narrative chapter” of that history. I was pretty sure Perplexity would produce something more readable so I said “go ahead.” 

It boiled my fourteen page ramble down to three pages while creating a story that –to my mind– accurately captured the vibe of those frantic days. [Links above to PDFs]

I’ve resisted the temptation to let an AI write or rewrite these blog posts and will continue to do so. But I wonder if it’s much different than an author submitting a manuscript to an editor who cleans it up and generally improves it.

The more your AI knows about you…

Posted on by

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.” Continue reading →