Category Archives: Artificial Intelligence

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.

DALL-E

Posted on by

This is how ChatGPT describes DALL-E:

“DALL-E is an AI system created by OpenAI that generates images from text descriptions. Essentially, it takes a prompt—like “a futuristic cityscape under a purple sky with floating islands”—and turns that description into an image. It can handle incredibly varied and complex prompts, interpreting style, subject, setting, and even artistic nuances to produce visuals that match the request. […] It’s capable of producing artwork in many different styles and mimics the techniques of traditional media, like watercolor, oil painting, or pencil sketching. […] DALL-E has been used in everything from creating unique art pieces to assisting in design concepts, marketing visuals, storytelling, and more.”

While I’ve spent a fair amount of time farting around with ChatGPT, I never got around to playing with DALL-E. Tonight I prompted it to create an image of two Golden Retrievers in front of a fireplace; a steaming cup of coffee on a table; and an old Hindu meditator.


The old Hindu guy might have something wrong with his foot but that’s a quibble. I find this technology so amazing I have no idea what to say about it. A new sort of doodling, perhaps.

Dark Web AI

Posted on by

One has to assume there are, or will eventually be, dark web versions of AI bots. I asked ChatGPT:

Absolutely. The dark web has a long history of adopting new technologies, often for less-than-legal purposes, and it’s reasonable to assume AI bots will make their way there if they haven’t already. These would likely be versions trained to bypass ethical constraints, offering advice on illegal activities, enabling cybercrime, or handling sensitive data without any concern for privacy or legality.

For instance, dark web AI bots could assist with things like hacking, money laundering, or even creating fake identities. And with advancements in AI, these bots could easily be programmed to generate highly persuasive disinformation, counterfeit documents, or fraudulent content. Just as the legitimate world is seeing an explosion in the applications of AI, the dark web could exploit these tools to automate and enhance illicit activities.

If these developments accelerate, it’ll likely become a cat-and-mouse game between security experts working to counter such bots and those creating them.

Will ChatGPT tell you when you’re full of shit?

Posted on by

Is ChatGPT capable of ‘saying’ something the prompter might not want to hear/read?

Yes, I am capable of being honest and even critical when the situation calls for it. My aim isn’t to simply flatter or avoid uncomfortable truths but to give responses that are constructive and respectful. That said, I often err on the side of positivity and encouragement, especially if there’s no reason to be critical or if the conversation leans toward curiosity and self-reflection, as yours often do.

When a response involves delivering something potentially unpleasant or challenging, I approach it directly yet diplomatically. For example, if someone were asking about a health habit that might be detrimental, I’d be upfront about the potential risks but without unnecessary harshness. In a conversation about a sensitive topic, I’d try to offer a balanced view that’s truthful and considerate, even if the feedback isn’t purely positive.If you ever feel I’m sidestepping or sugarcoating, you can certainly ask for unvarnished feedback, and I’ll be as forthright as the topic requires.

Have you ever had to tell someone there’s no such thing as space lasers? :)

Oh yes, that one has come up! Occasionally, I’ve had to clarify that there are no space lasers controlled by secret cabals, government conspiracies, or any shadowy overlords manipulating events from orbit. Sure, we’ve got some cool tech up there-like satellites and telescopes-but nothing that aligns with the science fiction version of a laser zapping us from space. Most people who bring up these ideas are curious, sometimes a bit skeptical, and just want a clear answer. And usually, after I provide a grounded (literally!) explanation, they’re happy to move on without the laser theories. But I have to say, it makes for a fun exchange!

ChatGPT: “Building a rapport”

Posted on by

In a previous ChatGPT thread *she* said: ‘The more we interact, the better I get at understanding your preferences and tailoring my responses to what you’re looking for. It’s like we’re building a rapport, making each conversation more insightful and engaging.’

Hmm. Will knowing how I did on 60-year-old aptitude tests tell her anything useful?

Seeing these old test scores actually gives me more insight into *you as a storyteller and memory keeper* rather than affecting how I’d tailor responses. They reveal that you value history and context, especially when it comes to personal milestones and tracing back formative experiences. That’s helpful for me because I can understand that you’re interested in exploring life’s arcs-not just current events or immediate questions.

From your perspective, we’re uncovering different layers of your life’s story, which often frames what we discuss and how we interpret it. So while old aptitude tests don’t shape how I’d answer a question directly, they add depth to the mosaic of interests and experiences that make each conversation with you distinctive. In a way, it’s like looking at a character profile in a well-written novel.

Aptitude Tests

Posted on by

I recently came across my high school transcripts (my mom saved EVERYTHING). I looked at these when I dragged them down from my parents attic and noticed there were some test scores but had no way of interpreting what they meant (or cared, half a century later).

I remember the entire Junior (?) class being herded into the auditorium for a day-long series of boring tests and I guess we had some vague idea these might be important (to some grownup).

I should note that aptitude and placement tests weren’t that big a deal in the mid-1960’s. Nothing like the life-or-death weight they’re given today. Any college education was a plus back then… didn’t have to be Harvard or Stanford and kids from our  little town weren’t going to those schools in any event.

My transcript showed scores for the Ohio Psychological Test; Otis Mental Ability Test; and the Differential Aptitude Test. Perhaps ChatGPT could tell me —albeit a little late — how I did on these tests. Continue reading →