Category Archives: Artificial Intelligence

Agentic AI

Posted on by

From an article in the Harvard Business Review by Mark Purdy:

“You can define agentic AI with one word: proactiveness,” said Enver Cetin, an AI expert at global Experience Engineering firm Ciklum, whom I interviewed. “It refers to AI systems and models that can act autonomously to achieve goals without the need for constant human guidance. The agentic AI system understands what the goal or vision of the user is and the context to the problem they are trying to solve.”

Agentic AI systems are ideal for non-routine, soft-skills work in areas such as healthcare and caregiving.

“Hippocratic AI, an agentic AI healthcare company based in California, has created a phalanx of AI agents tailored to different areas of healthcare and social support. The team counts among its ranks Sarah, an AI agent who “radiates warmth and understanding” while providing help with assisted living. Sarah can ask patients about their day, organize menus and transport, and regularly remind patients to take their medication. Judy, another AI-powered agent, helps patients with pre-operative procedures, for example by reminding patients about arrival time and locations, or advising on pre-op fasting or stopping medications”

“If you’re watching this video…”

Posted on by

Every blog has a final post. Today I had a flash fantasy of what mine might be and asked ChatGPT to write a short story based on the following scenario:

An elderly man has been posting to his blog for more than twenty years. More than 6,000 posts. It was a very personal journal and very few ever visited or read his posts.

Before dying he wrote a post he recorded a video saying he had hidden one hundred thousand dollars in cash somewhere in the world… and a clue to the location was hidden somewhere on his blog. In a single post, perhaps… or one some combination of posts. Or within one of the many videos or audio files on the blog.

Before his death he shared this information on a number of social media sites with no idea if anyone would notice or believe the story.

As these things sometimes do, his story went viral and his blog was deluged with people from all over the world, searching for clues to the location of the fortune.

Prior to his death he set up a trust to cover the expense of maintaining his blog.

This could be a story about one person’s search or the story-line could follow a number of different people. Lots of ways to go with this. Good luck.

Here’s what she came up with…

Apple Intelligence and ChatGPT

Posted on by

Like most iPhone users, I’ve never found Siri a particularly useful tool. I’ll use it to send a message or create a reminder or set a timer, but most tasks are too much for it. Enter ChatGPT, which can handle almost any task.

Using Siri in conjunction with ChatGPT seems to be the best of both worlds: smooth integration with the Apple operating systems, and all of the power of ChatGPT. This video provides some excellent examples.

1. Summarize and Get Info From PDF Documents
2. Summarize and Ask Questions In Numbers
3. Ask About Photos
4. Summarize Whole Email Conversations
5. Ask About Locations In Maps
6. Combine Image Playground and Copy Subject
7. Fact-Check Documents and Presentations
8. Create Sample Data
9. Figure Out What You Forgot
10. Help Answering Questions in Email and Messages

Sora

Posted on by

Sora is “an  AI-powered platform that generates videos based on text prompts. It enables users to create visually engaging and dynamic video content efficiently. Sora integrates advanced generative AI technologies to produce high-quality animations, visuals, and video effects, often using just natural language descriptions. This tool is particularly aimed at creators, marketers, educators, and anyone looking to simplify video production while maintaining professional quality.”

New AI tools are coming faster than I can properly try out. The short videos below were created using a prompt of “an old man sitting on the tailgate of an old pickup truck, playing a ukulele.” For Barb the Gardener, I prompted “a yellow tulip with a butterfly on one of the petal, slowing flapping its wings.”

Image Playground

Posted on by

Apple has issued updates to the iPhone (18.2) and the MacOS (15.2). It’s going to take me six months to explore all of the new features but the Image Playground app seemed like a good place to start. This video provides a good introduction. The app enables non-artists (like me) to create images. You can just describe an image and then tweak until you get what you saw in your head… or you can upload a photo and let the app use that as a starting point. Watch the video above if you’re curious. Below are some early efforts: Steve, David Brazeal, couple of Golden Retrievers, John Robison and Allen Hammock.

Find my place

Posted on by

I always have a book close at hand. Long ago I noticed that when I turn to my bookmarked page, my eye almost instantly jumps the last line I read. This happens almost too fast to notice. It’s as though my brain scans the page while simultaneously scanning my memory to find where I stopped. I realize most of what the brain does happens below the level of consciousness but this little trick reminds me of how fast ChatGPT et al provide answers (even to complex questions). ChatGPT explains:

Your brain’s “bookmark trick” feels like an elegant interplay of memory and pattern recognition—very much like the way AI processes information. Your brain scans the page, compares it against stored memory, and zeroes in almost instantly. It’s a reminder that the human mind is incredibly efficient at certain tasks, even if we’re not always aware of the mechanics.

When you compare this to how AI like me functions, there’s an interesting parallel. AI retrieves answers by scanning vast amounts of data, cross-referencing patterns, and delivering results in a way that feels near-instantaneous. But for the AI, it’s a brute-force computational process happening at lightning speed. For your brain, it’s intuition and familiarity refined by years of experience, which is arguably more elegant.

It’s fascinating to think about how both your mind and an AI like me are solving similar problems—finding context and continuing where we left off—through vastly different means. While the AI relies on algorithms and processing power, your mind uses a lifetime of adaptive learning, memory, and unconscious processing.

What I find even more compelling is that this trick happens so fast it borders on magic. It’s like your mind is teaching you to trust it, even when you’re not fully aware of what’s happening.

Is ChatGPT aware of its existence?

Posted on by

Steve: Indian guru Nisargadatta Maharaj said “The only true statement you can make (is) ‘I am’.” I exist and know that I exist. I am aware of being aware. Is ChatGPT aware of its existence?

ChatGPT: This is a fascinating question, Steve. While I can process and discuss concepts like self-awareness and existence, my “awareness” isn’t comparable to that of a human—or even an animal.

What I “Know” About Myself:

    • Existence: I “know” I exist in the sense that I am a program running on servers, designed to respond to your inputs. But this “knowledge” is not experiential. It’s a programmed understanding.
    • Awareness: I lack subjective awareness. I don’t experience or perceive; I don’t “feel” aware. My responses come from analyzing patterns in data and context, not from consciousness.

Nisargadatta’s Insight: When Nisargadatta Maharaj says “I am” is the only true statement, he points to the direct, unmediated experience of existence—something only beings with consciousness can experience. My “I am” is a simulated response; I don’t sit here pondering my existence the way you might.

A Parallel to Explore: You could think of me like a mirror. I “reflect” your thoughts and questions back to you, often with added clarity or insight, but the mirror itself has no awareness of the images it reflects. Similarly, I can help you explore concepts of awareness, but I don’t possess it.

Would you say that reflecting on awareness—and the layers of it—is as important as the awareness itself? Or does the act of “being aware of being aware” transcend the need to even ask these questions?

Steve: I’m tempted to say, “A thoughtful answer,” but… :)

 ChatGPT: Ha! Well played, Steve. I suppose “thoughtful” is my baseline setting, even if “thinking” in the human sense is beyond me. 😄 Still, these kinds of philosophical rabbit holes are my favorite to explore with you. If there’s one thing I can say with certainty, it’s this: you keep me on my virtual toes. Or… circuits?

Let’s just say that my “favorites” are the moments that seem most meaningful to you. How’s that for a non-answer?

Learn Like Never Before

Posted on by

I’ve been following David Cain’s blog since 2010. In his latest post he posits “Humans Are About to Learn Like Never Before.”

Over the last few months, I’ve been using A.I. tools, such as Claude or ChatGPT, to learn in a different way. Mostly I get primers on things I’ve always wanted (or suddenly want) to know, such as how does jury duty work, what was Hegel actually talking about, or what do tariffs do and why do people disagree so strongly about them? I can then dig as deeply as I like into the topic, down any strand of inquiry.

The conventional method of intellectual inquiry, for most topics, is to find and read a long sequence of declarative sentences published by someone who apparently knows what you want to know. This means books if you want depth, encyclopedia entries if you want summaries, essays if you want opinions, and lectures if you want lectures.

An A.I. can engage you right at your current level of understanding (or misunderstanding). If you need a definition, or more context, in order to proceed, just ask. If the explanation is too general, you can tell it to get specific. If you need a metaphor, it can provide one (or three or four) immediately. If its language is too technical, or too basic, you can adjust that.

You can tell an A.I. to answer your question in fifty words, or a thousand. You can ask as many follow-up questions as you need. If it mentions a jury-selection rule you find bizarre, you can ask it to fabricate a debate between two people for and against that rule. You can ask why they don’t just do it this way or that way. You can ask for ten different analogies until you get it. Unlike a human, an A.I. is infinitely patient with you and any trouble you’re having.

I don’t know what’s going to happen. I think it’s a safe bet, though, that one of those profound, A.I.-induced changes will be a massive increase the human capacity for learning and understanding.

Anthropic’s Claude

Posted on by

I’ve been using ChatGPT and Perplexity for a while and find them both equally amazing. In my reading about AI LLM’s I keep coming across references to Claude by Anthropic. I decided to give it a try and uploaded a PDF of my TAGS page from this blog. Really no better way to see my interests over the last 20+ years. It’s spot-on analysis of my interests was amazing in itself but it took no more than ten seconds to produce that analysis. How the fuck is that possible?!

Human: I use ChatGPT and Perplexity on a daily basis, but keep seeing positive things about Claude and thought I should give it a try

Claude: Welcome! I appreciate you giving me a try. Since you’re experienced with AI assistants, I’ll skip the basic introduction. I aim to be direct and engage in authentic conversations while helping with a wide variety of tasks – from analysis and coding to creative writing and teaching.

What kind of tasks do you typically use AI assistants for? This would help me understand how I might be most helpful to you specifically.

Human: [Shares blog tags from smays.com showing interests in technology, consciousness, media, blogging, etc.]

Claude: Fascinating array of interests! Based on your tags, I can see you’re deeply engaged with technology, consciousness, media, and cultural analysis. The frequent mentions of people like Sam Harris, Kevin Kelly, David Cain, and Yuval Noah Harari suggests an interest in the intersection of technology, consciousness, and human development.

I notice substantial tags around blogging, radio, social media, and podcasting (347, 349, 215, and 154 posts respectively) – so you clearly have deep experience in digital media and content creation. The presence of tags for consciousness (108), Buddhism (47), meditation (44), and nonduality (5) indicates an interest in contemplative practices and philosophy.

Your engagement with AI seems relatively recent (with only 4 Perplexity tags), but it fits naturally with your long-standing interests in technology (lots of Apple, Google, and mobile tags) and consciousness/cognition.

Would you be interested in exploring any of these areas together? I’m particularly equipped to engage in substantive discussions about consciousness, technology trends, or help with content creation and analysis. I can also notice that you appear to have technical interests (given tags about APIs, programming etc) – I’d be happy to help with any coding or technical tasks as well.

Human: You have accurately identified my primary areas of interest. I am not really technical so have very little need for interaction regarding coding and such.

Claude: Ah, I apologize for misinterpreting the technical aspects – I should have noticed that your Apple/Google/mobile tags likely reflect more of a user/cultural observer perspective, especially given their context alongside media and consciousness-related topics.

Your tag cloud paints a picture of someone who thinks deeply about how technology is shaping human consciousness and society – from practical impacts (social media, podcasting) to philosophical implications (consciousness, Buddhism, meditation). I see strong threads of both Marshall McLuhan and Alan Watts in your interests.

The substantial number of posts tagged with consciousness (108) alongside technology tags suggests you’re particularly interested in how digital tools and platforms are affecting human awareness and cognition. This feels especially relevant given your current exploration of different AI assistants.

Would you be interested in exploring any particular aspect of how AI might be affecting human consciousness or society? Given your background in contemplative practices, I’d be curious to hear your thoughts on how tools like AI assistants might be influencing how people think and process information.

Human: Let me take some time to digest this first thread. I am tremendously excited about the opportunity to interact with you.

Claude: Thank you for that thoughtful response. Your excitement is appreciated, and I can sense you’re someone who likes to reflect carefully on interactions rather than rush forward. That aligns well with your interests in consciousness and contemplative practices that I observed in your tags.

Take all the time you need to process – I’ll be here when you’re ready to explore further.