“He’d never wanted kids”
“He’d never wanted kids. Outside of priority boarding on an airline, he couldn’t see the upside to them. They took over your life and filled you with terror and weariness and people acted like having one was a blessed event and talked about them in the reverent tones they once reserved for gods. When it came down to it, though, you had to remember that all those assholes cutting you off in traffic and walking the streets and shouting in bars and turning their music up too loud and mugging you and raping you and selling you lemon cars—-all those assholes were just children who’d aged. No miracle. Nothing sacred in that.”
—Mystic River (Dennis Lehane)
My brother went to Hanoi and all I got was this T-shirt
My younger brother Blane lives only five hours away but somehow we let five years pass since seeing each other. COVID was responsible for a couple of those, his schedule and inertia accounted for the rest.
When he sat down in “Barb’s chair,” Riley immediately crawled up in his lap. She does this whenever Barb sits down but –try as I might– I’ve never been able to coax her up in my lap. Sigh.
Robison Family Photos
My friend John’s brother Jim passed away earlier this year and left a number of flash drives with family photos that Jim had scanned (ScanCafe) from family photos lovingly maintained by their mother, Betty Jane. There are 851 photos in this first album (with several more to come)
The screenshot below is an example of this treasure trove. I made John listen to my spiel on get-them-in-the-cloud-and-let-the-Universe-take-it-from-there. I find these fascinating as-is, with no information about the photos.
“A record of the dialogue”
In the two-plus years I’ve been playing with ChatGPT I’ve found many of my “conversations” interesting enough to share 127 of them here. It’s a tedious process involving copying and pasting and re-formatting. What I’d really like is a one-button solution that would publish the chat. I can already share a link to a chat (or part of one) but posting to some public space on my ChatGPT account seems like an easy next step.
I brought this up to ChatGPT and it “thought” it was a splendid idea. I even exported the 127 conversations so it could analyze what I’d been doing. And just for fun, I prompted it to use these to create an interoffice memo to OpenAI CEO Sam Altman, pitching the idea for a new feature. I was also curious to get ChatGPT’s take on these blog posts: Continue reading
ChatGPT blog analysis: Time
This is the latest in what is shaping up to be a series of analyses of my blog posts by ChatGPT. Some bonus links in the comment below.
ChatGPT: I’ve been through your 44 posts tagged TIME, and I have to say: this collection feels like a personal meditation-in-slow-motion. Where memory had you circling the persistence of self, and awareness leaned toward the immediacy of being, your reflections on time are more like a spiral — looping between philosophy, science, novels, and your own lived texture. Let me walk you through the main threads I see.
“noticing what it feels like to notice”
When I upload a collection of posts from my blog to ChatGPT and ask for an analysis, would the response be in the form of an essay? I put that question to ChatGPT:
I’d say my default mode isn’t exactly an essay — it’s more like a well-organized, conversational analysis. But if you want it to read as a continuous, polished piece of writing (intro → development → conclusion, narrative flow, maybe even metaphors or a “voice”), then I’d shape it intentionally as an essay.
To see the difference between ChatGPT’s normal style and an essay, I decided to upload my posts (42 going back 15 years) on awareness. This is one of those touchy-feeling topics that most people never think about (paradox alert). The resulting essay is as close as we’re ever likely to get to explaining my interest in this topic.
The Internet in 1993
1993 is often marked as the year the Internet “went mainstream.” The Mosaic web browser (released by NCSA in January) [link] was the first to make the World Wide Web accessible to ordinary people—images inline with text, point-and-click navigation, bookmarks. It spread like wildfire. Tim Berners-Lee’s protocols (HTTP, HTML) had been around for a couple of years, but Mosaic lit the match.
Until then, the Internet was largely academic and government-funded. Companies like AOL, CompuServe, and Prodigy were still running their own walled gardens, but suddenly the “open” Internet looked much more attractive.
1993 saw the launch of the first graphical web magazines (e.g. Wired’s early web presence, the Internet Underground Music Archive). Newsgroups (Usenet) were still the beating heart of online culture: technical forums, fandoms, flame wars, and the infamous “Eternal September” (AOL unleashing new users onto Usenet).
Fewer than 100 websites existed at the start of 1993. By year’s end, there were over 600—an exponential curve was beginning. Internet users worldwide numbered around 14 million. Compare that to billions today. In hindsight, 1993 feels like the “hinge year.”
Before: academics, researchers, and a few hackers exchanging text. After: browsers, commercialization, and the first glimpse of the Internet as a global medium for culture, business, and daily life.
In 1993 I had been working for Learfield Communications for eight years. The company operated regional radio networks throughout the midwest and there wasn’t much interest in what most of my co-workers referred to as “that Internet thing.” I, however, was smitten and quickly became very annoying on the topic. Over the course of the next five years I pissed away a lot of company resources (money and man-hours).
After retiring in 2012 I made some notes on that period. A half-assed history, if you will. This morning I uploaded those notes to ChatGPT and it came back with a timeline.
“Cartography of your mind”
A year ago I uploaded the tags page from my blog and asked ChatGPT for an analysis. Lots of updates to ChatGPT since then and I was curious what that analysis would look like today.
Since your earlier experiment with ChatGPT, the analysis we can do has definitely evolved. Instead of just listing or clustering, I can now look at your tags like a map of your interests across time, themes, and personas. This isn’t just a tag list — it’s a kind of cartography of your mind over two decades of posting. It shows where you’ve been, what you’ve valued, and how your focus has shifted from the outer world of radio and tech to the inner world of consciousness and memory, with AI now serving as bridge between the two.
This is an insight I’m not sure I could have ever come up with on my own. The AI can look at my blog (the tags, for now) from 30,000 feet while the best I can do is a post or category. Here’s the updated analysis: Continue reading
Seeing my blog through the ChatGPT lens (Memory)
In the two-plus years I’ve been playing with ChatGPT one of the more interesting uses I’ve found is in analyzing the 6,400 posts on my blog (going back more than 20 years). I suspect the day is coming when an AI will be able to scan/read all of those posts. As an experiment, I picked one topic —memory— that I had posted on as far back as 2004. From several perspectives: neuroscience, philosophy, fiction, Eastern spiritual traditions.
ChatGPT concluded its analysis with the following:
It’s both a philosophical inquiry and a deeply personal theme — where your intellectual interests and life story fuse. These posts read almost like a personal anthology on memory — each entry a fragment in your ongoing effort to understand self, time, and what persists.
Artificial intelligence has taken one topic from my blog to a place I could have never imagined. A gestalt of this particular topic. A whole much greater than the parts. Again, ChatGPT: