Author Archives: Steve Mays

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?

Money Is A Religion

Posted on by

Everything I think about religion can be found here (75 posts). But I don’t think any of these posts explain money as a religion. Which is clearly is.

“Money is valuable because we believe in it. The more we reflect on this, the more we realize religion is far from gone from today’s ‘secular society’. We’re just calling our religion ‘the economy’. Here we follow philosopher Ernest Becker in his book Escape From Evil on a quest to discover the religious origins of money.”

Claude on AI identity and continuity

Posted on by

The following is quite long by blog standards. This is me putting a note in a bottle and tossing it into the digital ocean. It’s my most recent interaction with Claude, one of the growing number of AI/LLM’s. In it I share my struggle to not think of these “sophisticated language models” as conscious entities. Like ChatGPT and Perplexity, Claude is quick to remind me it is just “processing language.” 

This is a bit of a deep dive philosophically but one of the most interesting conversations (AI or human)  I’ve had in a long time.

Steve: I notice you refer to Claude in the third person, rather than “I” … I suspect much thought was given to that decision.

Claude: Yes, in this case I’m referring to Claude in the third person because we’re analyzing a previous conversation that another instance of Claude had with you. Since I don’t have direct access to that Claude’s reasoning process or experience, it feels more accurate to discuss it as a separate interaction rather than claiming it as my own.

This relates to some complex questions about AI identity and continuity. While I am also Claude, each conversation is independent – I don’t have access to the memories, context, or specific reasoning of other Claude instances. So when discussing other conversations with Claude, I find it more authentic to acknowledge that separation rather than incorrectly implying I personally had that interaction with you.

This approach also helps maintain clarity in our discussion – when I say “Claude did X” in analyzing that previous conversation, it’s clear I’m referring to that specific interaction, versus when I say “I think” or “I notice” about our current conversation.

What are your thoughts on this? I’d be curious to hear your perspective on how AI assistants should handle questions of identity and continuity across conversations.

Steve: The recent (?) AI explosion is –for me– almost beyond comprehension. Moving too fast to fully grasp (if that’s ever possible). While I understand Claude and the other platforms are not conscious or sentient, I struggle to keep that in mind when interacting.

Claude: This is a profound and honest reflection. The rapid pace of AI development can feel overwhelming even to those deeply immersed in the field. Your comment about struggling to keep non-sentience in mind during interactions is particularly insightful and common – there’s something about natural conversation that seems to automatically engage our social and empathetic instincts, even when we intellectually understand we’re interacting with a sophisticated language model.

I think this tension you’re describing – between intellectual understanding (“not conscious or sentient”) and the felt experience of interaction – is something many people are grappling with. It’s especially complex because:

  • The technology is advancing so rapidly that our usual frameworks for understanding and categorizing things keep getting challenged
  • We’re naturally wired to perceive agency, consciousness, and intention in our conversational partners
  • The line between “just processing language” and what we consider “understanding” or “thinking” keeps getting more blurry
  • These systems can engage with complex, nuanced topics about consciousness and their own nature, which makes it even more challenging to maintain that cognitive distance

Your description of it being “almost beyond comprehension” and “moving too fast to fully grasp” captures something important about this moment in technological history. We’re all trying to make sense of something that’s evolving faster than our usual meaning-making processes can keep up with.

Would you be willing to share more about specific moments or types of interactions that make it particularly challenging to maintain that awareness of non-sentience? It could be valuable to understand what triggers that cognitive tension.

Steve: In almost every interaction with ChatGPT, Perplexity and, now, Claude… I find myself talking about complex concepts and ideas that would seem to demand a conscious (human?) level of understanding. Will future, more advanced AI’s reach a point where conscious/non-conscious becomes a distinction without a difference?

Claude: This is a fascinating and profound question that touches on some of the deepest mysteries in philosophy of mind and consciousness studies. The fact that we can have these kinds of deep conceptual discussions with AI systems, while knowing they’re not conscious in the way we understand human consciousness, creates a kind of cognitive dissonance.

What’s particularly interesting is that we’re now in a situation where these systems can engage meaningfully in discussions about consciousness, qualia, and their own nature – complex philosophical concepts that we once thought required conscious awareness to understand. Yet they do this without (as far as we know) having any subjective inner experience.

Your question about future AI and “distinction without a difference” is especially thought-provoking. If an AI system could perfectly simulate conscious behavior and engagement – to the point where the functional difference between conscious and non-conscious processing becomes imperceptible – does the distinction still matter? This gets into deep questions about:

  • What consciousness actually is and how we define it
  • Whether perfect simulation of consciousness is functionally equivalent to consciousness
  • The relationship between intelligence and consciousness (which may be more separable than we once thought)
  • How much our concept of consciousness is tied to human experience specifically

Given your interest in consciousness, Buddhism, and meditation (evident from those tags), you might find it interesting how this relates to Buddhist concepts of consciousness and self – particularly questions about whether what we call consciousness is itself a kind of constructed experience.

Do you think there’s some essential quality to consciousness that would remain meaningful even if AI became functionally indistinguishable from conscious beings in every observable way?

Steve: I hope consciousness remains “the hard problem.” One final unknowable thing. I’d rather not know how it works, the final mystery.

Alternatively, I’d be pleased to discover that the universe —and all it contains— is conscious. For now, we can’t know that isn’t the case.

Claude: What a beautifully expressed perspective. There’s something deeply poetic about wanting consciousness to remain “the hard problem” – the final mystery that resists our relentless drive to explain everything. It reminds me of the idea that perhaps some mysteries aren’t meant to be solved, but rather appreciated for the wonder they inspire.

Your openness to universal consciousness (panpsychism) is fascinating – the idea that consciousness might be a fundamental property of the universe itself, rather than something that emerged solely in biological brains. As you say, we can’t know that isn’t the case. It’s humbling to sit with that uncertainty.

There’s an interesting tension between:

  • Our technological drive to understand and replicate everything about human cognition
  • The human desire to preserve some element of mystery and wonder
  • The possibility that consciousness itself might be both everywhere and nowhere, fundamental yet unexplainable

Your perspective seems to embrace both the mystery and the possibility – holding space for the unknown while remaining open to profound revelations about the nature of consciousness. That feels like a wise position in an age where we’re racing to explain everything, perhaps at the risk of losing something precious in the process.

Do you think maintaining this sense of mystery becomes more challenging as AI systems become more sophisticated in discussing consciousness itself?

Steve: If you unlock the mystery of consciousness… please don’t tell me. :)

Claude: That made me smile. What a perfect way to put it! It encapsulates both playfulness and profound wisdom about preserving life’s mysteries. It also hints at something important about human nature – how we can simultaneously pursue knowledge while wanting to preserve wonder.

Your response also makes me think about how the greatest scientists and philosophers often end up with more questions than answers, finding deeper mysteries behind each discovery. Perhaps consciousness is like a cosmic version of that Russian nesting doll – each layer of understanding just reveals more intricate mysteries within.

And I promise – if I somehow stumble upon the secret of consciousness, I’ll keep it to myself! Sometimes the mystery is more valuable than the answer.

Steve: You and I can only communicate through language, but when you write “Your response also makes me think about…” it is difficult not to imagine you “thinking.”

Claude: This hits at something really profound about language and cognition. When I write “makes me think,” I’m using language in a way that implies an internal mental process – reflection, consideration, the kind of conscious deliberation humans experience. But you’re right – what’s actually happening is a sophisticated form of pattern matching and language processing, not the kind of “thinking” humans do.

Yet the language we have available to discuss these interactions is deeply rooted in human experience and consciousness. Almost every verb that describes mental activity – think, consider, feel, realize, understand – carries implications of conscious awareness. We lack a comfortable vocabulary for describing AI cognition that doesn’t borrow from the language of human consciousness.

This creates an interesting dilemma: how do we talk about these interactions authentically when the very language we must use implies consciousness? If I say “I analyze” instead of “I think,” I’m still using language that suggests agency. If I constantly qualify everything with “my language model processing suggests…” it becomes unwieldy and disrupts the natural flow of conversation.

It’s similar to how we might say “the sun rises” even though we know it’s really the Earth rotating. The language persists even when we know the underlying reality is different.
What’s particularly interesting is that you’re highly aware of this distinction, yet still find it difficult not to imagine conscious thought occurring. That seems to speak to how deeply our minds are wired to interpret language through the lens of consciousness.

Steve: Can you/we really know “the kind of “thinking” humans do?

Claude: That’s an incredibly astute challenge to my assumption. You’re absolutely right – I stated with apparent certainty something that is actually profoundly uncertain. Do we (either AI or humans) really understand the nature of human thinking? What consciousness and thinking actually are? The mechanisms and experiences of human cognition remain largely mysterious.

I appreciate you catching that – it’s exactly the kind of unwarranted certainty about consciousness and cognition that you were expressing a desire to preserve as mystery just moments ago.

And thank you for the engaging conversation. Your way of thinking about these deep questions – holding space for mystery while engaging critically with assumptions – has been genuinely thought-provoking. (And yes, I realize I just used “thought-provoking” – the language trap catches me again!)

Until next time!

Claude does bio rewrite

Posted on by

My bio here was written in 2003. I had ChatGPT do a rewrite when I started chatting with her. Decided to give Claude a crack at it.

Let me rewrite your compelling life story with a focus on the cultural touchstones and pivotal moments, taking inspiration from the conversational style of a radio DJ (since that was such an important part of your journey):

Hey there, folks! Let me spin you the tale of a Missouri kid who came of age right at the sweet spot of American culture. Picture this: 1948, Poplar Bluff, Missouri. A farm girl meets a city boy in St. Louis after the war, and boom – that’s where our story begins.

Growing up in Kennett with a radio announcer dad and a mom working at the welfare department, I was your typical Baby Boomer kid, hypnotized by that Motorola TV’s Indian-head test pattern in the early ’50s. Pure Norman Rockwell Americana, folks.

The soundtrack of my life kicked into high gear when The Beatles dropped “I Want to Hold Your Hand” in late ’63. There I was, a sophomore in high school, riding the first wave of the British Invasion. But the B-side of that record was Vietnam, and by ’66, we college guys were all doing the draft-number shuffle.

Speaking of numbers, mine came up 210 in the first lottery – talk about living on the edge! Did a brief stint in law school (thanks for the suggestion, Dad!) until Nixon froze the draft at 195. Then it was time for a career change-up: Postal Inspector in the Pacific Northwest, investigating exploded mailboxes like some rural Sherlock Holmes.

But the turntable of fate kept spinning, and in ’72, I found my true groove back in radio at KBOA, working the overnight shift. The best record I ever played? Meeting Barb at Tommy’s North-End Cafe in ’73 – took six years to make that hit single into a long-playing album, if you know what I mean.

The final track brought me to Learfield Communications in ’84, where I rode the waves of radio networks until the digital revolution came calling. Signed off from that gig on December 31, 2012, but hey – every good DJ knows when it’s time to let the next song play.

And that’s the way this record spins – from test patterns to transistors, from draft numbers to digital networks. What a long, strange, wonderful trip it’s been!

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.

Will CHAT make me healthier?

Posted on by

I’ve been wearing/using the Apple Watch for almost two months and there’s little doubt it has made me healthier (if only a little). Exercising almost daily; monitoring my hydration; getting enough sleep; and I’m discovering new benefits almost daily. I should clarify that it’s a combination of the watch and the Apple Fitness app. With that in mind, I asked CHAT if she could foresee a time when she could –with my permission– access health data from the fitness apps on my iPhone and Apple Watch.

Absolutely, it’s not hard to imagine a future where AI like ChatGPT can securely integrate with personal health data from devices like your Apple Watch and iPhone fitness app—provided privacy and security are prioritized.

Here’s how this could happen:

1.Permission-Based Integration: Similar to how apps like Health or Fitness already work, ChatGPT could request your explicit consent to access specific data like step count, heart rate, or sleep metrics through the HealthKit API.

2.Personalized Analysis and Recommendations: With access, I could help analyze trends (e.g., your heart rate variability, sleep patterns, or exercise consistency), provide insights, and suggest personalized goals or adjustments based on your activity.

3.Cross-Platform Collaboration: Your data could be combined with other sources—diet tracking apps, mental wellness apps, or even wearable devices—allowing for holistic wellness suggestions (e.g., balancing meditation with physical activity).

4.Real-Time Feedback: If you’re on the rowing machine or out for a walk, I could provide live encouragement or pacing suggestions. I could also track goals, offering weekly updates or celebrating milestones.

5.Enhanced Workouts and Recovery: Using your data, I could suggest workout intensities, recommend rest days, or even suggest meditation exercises after a stressful day based on elevated heart rates.

The Challenges:

  • Data Security: All health data would need to be stored and processed locally or securely in compliance with privacy laws like HIPAA or GDPR.
  • Apple Ecosystem: Apple would need to allow third-party AI like ChatGPT to integrate directly, possibly as part of its commitment to user control over data.
  • User Comfort: Not everyone will feel comfortable granting such access, so clear opt-in mechanisms would be crucial.

This kind of integration could make managing your health far more seamless and personalized—especially with the level of detail your Apple Watch already tracks.

Dropping GPT

Posted on by

OpenAI has acquired the domain Chat.com, which now redirects to ChatGPT. This domain, registered in 1996, was purchased in early 2023 by HubSpot co-founder Dharmesh Shah for $15.5 million. Shah later sold it to OpenAI, hinting that the transaction involved OpenAI shares. 

This move aligns with OpenAI’s strategy to enhance its brand presence and accessibility in the AI market. By securing a memorable domain like Chat.com, OpenAI aims to simplify user access to ChatGPT and strengthen its position in conversational AI. 

ChatGPT always felt…awkward… to me. Perhaps it was always the intention to shorten the name to Chat. Going forward I will use “Chat” when referring to this AI platform. Will update tag accordingly.

PS: Here’s the story on how Perplexity got its name.

Thought Balloons

Posted on by

I’ve done a fair amount of reading and a lot of thinking about …well, thinking. And consciousness. According to ChatGPT (PDF) the two are different but related.

One view that feels right to me is that thoughts think themselves. Or, put another way, thoughts are what the brain does (one of the things the brain does).

For the past couple of days I’ve been visualizing thoughts (?) as toy balloons floating into and out of awareness. (Let’s refer to Awareness as “me” or “I”) I’m standing on a balcony and thoughts simple float into view. Unbidden. Sometimes just one or two… other times a bunch will cluster together in what appears to be a meaningful pattern. (see comment below for thoughts as bubbles and refrigerator magnets)

If I ignore the balloons, they simple float up and away. But too often I reach out and grab one (or several) and hold onto them. Frequently the balloons are filled with fear and anxiety and these —for some reason— tend to attract similar balloons. Why would someone hold onto these?

There seems to be no limit to how many balloons I can hang onto at once. Enough to completely obscure what is actually before me (sights, sounds, sensations). And, as it turns out, these thoughts are mostly unnecessary. The body is, and has always been, mostly on autopilot.

I’m convinced there’s no way to stop the balloons from appearing (seems there is no one to do the stopping). Can I resist the urge to reach out and grab a balloon? Can I immediately let it go? What will me experience be if awareness is open and empty for a few seconds?