Lots of rain has made Barb’s garden lush and beautiful this year.
What I Mean (and Don’t Mean) When I Say “Nondual”
Every word of this post —after this little grey box— was written by Perplexity. After finally getting around to uploading all 6,500 blog posts on smays.com (spanning almost 25 years) I was curious what an AI might come up with, being the only entity beside me to have read (analyzed? processed?) every post. We started with nonduality, a subject that has interested me for years. The essay (?) below drew on hundreds, maybe thousands, of posts touching on awareness, consciousness, free will, death, immortality, memory, reality, self, Tao, thoughts, time, and zen. I’ve included additional thoughts in the comments at the bottom of this post.
I’ve used the word “nondual” on the blog often enough that it probably deserves parole into plain English.
I don’t mean crystals, chakras, or a belief system you have to sign up for. I also don’t mean “nothing matters, it’s all an illusion, pass the Doritos.” If anything, nonduality has made ordinary things—espresso, a train whistle, the dog snoring—feel more vivid, not less.
What I’m trying to point at is simpler and slipperier. There’s awareness, there’s experience showing up in that awareness, and the boundary between “me in here” and “world out there” is not as solid as I was trained to believe. Most of the time, that’s all I mean.
The rest is stories and examples. Continue reading
The AI’s read this blog
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.
Agentic AI Comes to Medicine
Following excerpt from Dr. Eric Topol’s Ground Truths:
“MIRA queried the patient’s history, the physical exam results, and could order labs, blood cultures, scans, medications, procedures, surgery, and triage for hospital admission. This was done in 500 emergency department established real cases with the MIRA results directly compared to 4 board-certified (BC) physicians, and also to a hybrid group of 2 BC physicians and 2 residents. […] The overall diagnostic accuracy for MIRA was 87.8% compared with BC physicians at 78.1%.”
Railroad tie wheel chock
Not clearing as much brush these days and tend to rely on a big one in the woods behind the Annex. SOP is putting the pickup in 4WD and backing up to the pile. But the truck struggles to hold its position and threatens to roll down the hill. To prevent this I moved an ancient railroad tie into place as a wheel chock. (Note use of tie-down ratchet to get the thing into the truck)
“Do teens regret their social media use?”
The blogger in me is surprised and delighted by #3.
“So how did social media regrets hold up? Out of 20 possible regrets, too much time on social media ranked 13th. The top regrets were 1.) not sticking up for oneself, 2.) being too self-conscious, 3.) not documenting memories, 4.) not learning practical life skills and 5.) not getting help with mental health. Girls were slightly more likely to regret time on social media than boys.”
“We are talking to aliens now”
“We are talking to aliens now, just didn’t come to us the way we thought they would. I don’t think (the film) 2001 anticipated they would think in completely different ways from us, and would not understand the differences. They talk to us as if we were them, the same way your cat thinks you’re just a bigger cat.”
Perplexity provides the following analysis:
Winer’s metaphor is doing a few interesting things at once, and it’s sharper than it looks on first read. At the surface, “aliens” refers to AI systems—entities that are clearly intelligent in some sense, but whose internal structure and way of “thinking” are not human-like. The key claim isn’t just that they’re different, but that the difference is opaque in both directions. Continue reading
Consciousness or Not
“The biggest benefit from language was not the ability to communicate with others but the ability to communicate with ourselves. Language allowed us access to our own minds. It gave us a way to manipulate our thoughts. To reflect, to operate on memories, to predict. It gave form to ideas.”
“In the next 25 years we’ll learn more about ourselves than in the last 25,000 years. One hundred years from now we will have a very different idea of what we think humans are.”
The “Godfather of AI” believes AI is already conscious.
Geoffrey Everest Hinton (born 6 December 1947) is a British-Canadian computer scientist, cognitive scientist, cognitive psychologist and Nobel Prize laureate known for his work on artificial neural networks, which earned him the title “the Godfather of AI”.[8] He is University Professor Emeritus at the University of Toronto.
In this interview, he discusses something he rarely says out loud: he believes AI is already conscious. Not eventually. Not theoretically. Already.
Dr. John Middleton
It was just a few months after I got my Land Rover that I met John Middleton. Someone told me he had a collection of Rovers so I tracked him down and he invited me up to Columbia. In the ensuing years John was an invaluable resource whenever my Land Rover had a problem. Even joined the crew to help me take the top off and on.
Today I took the hoop kit (I used for just one summer) up to John’s farm and to see some of his recent acquisitions. During my brief visit I mentioned the MU vet school where John is a professor. He said something about his duties changing since we last talked so when I got home I asked Perplexity what it could find.