Here is me, trying to get ChatGPT (version 4o, which I pay for) to give me an illustration to use in my last post here, titled The People’s AI. But don’t go there yet (if you haven’t already). What I ended up using there is a punchline at the end of the dialog that starts here—

Me: A vast field on which the ground spells the letters A and I, with people on it, having a good time.

ChatGPT:

Here’s the illustration of a whimsical outdoor scene with a vast field shaped into the letters ‘A’ and ‘I’, where people are enjoying various activities, creating a cheerful and lively atmosphere.

Me: Make the two letters upper case A and upper case I, both with serifs.

ChatGPT: 

Here’s the updated illustration of a vast field shaped into the uppercase letters ‘A’ and ‘I’, both with serifs, where people are enjoying a sunny day outdoors. The setting is lively and festive, enhancing the creative landscape.

Me: Those are not the letters A or I, and lack serifs. Try again, with A on the left, and I on the right.

ChatGPT: 

Here’s the updated illustration showing a vast field shaped into the uppercase serif letters ‘A’ and ‘I’, with ‘A’ on the left and ‘I’ on the right. The field is vibrant and bustling with people enjoying various outdoor activities.

Me: Better, but there is no I on the right.

ChatGPT:

Here’s the updated illustration showing a vast field clearly shaped into the uppercase serif letters ‘A’ and ‘I’, with ‘A’ on the left and ‘I’ on the right. The field is lively with people engaging in various activities, set in a sunny and cheerful environment.

Me: That’s an interesting design, but I need an A and an I next to each other.

ChatGPT:

Here’s the updated illustration showing the vast field clearly shaped into the adjacent uppercase serif letters ‘A’ and ‘I’. The setting is vibrant and festive, surrounded by people enjoying various activities.

Me: That’s one big A, not an A and an I. Give me both.

ChatGPT:

Here’s the updated illustration showing a vast field clearly shaped into the uppercase serif letters ‘A’ and ‘I’, side by side. The setting is lively and festive, filled with people enjoying various activities.

Me: That has no serifs and is still just an A. I want an A and an I. Separate.

ChatGPT:

Here’s the updated illustration showing a vast field clearly shaped into the uppercase serif letters ‘A’ and ‘I’, side by side. The setting is vibrant, with people enjoying various outdoor activities.

Me: Still not separate. That’s one big A. I want an I next to it.

ChatGPT:

Here’s the updated illustration, clearly showing the vast field shaped into the separate uppercase serif letters ‘A’ on the left and ‘I’ on the right. The scene is lively with people enjoying various activities under a sunny sky.

Me: Let’s try this: An “A” and an “I” in an open field full of people.

ChatGPT: 

Here’s the illustration showing an open field shaped into the uppercase letters ‘A’ and ‘I’, with people enjoying various activities in the area. The scene is lively and sunny, capturing a cheerful outdoor gathering.

Me: Better! Now give me the same thing, with a complete “a.”

ChatGPT:  We are experiencing heavy server load. To ensure the best experience for everyone, we have rate limits in place. Please wait for 2 minutes before generating more images. Let me know if there’s anything else you’d like to discuss in the meantime!

Me (after a 3 minute pause): Thanks. Now give me the same image, but with a complete “A.”

ChatGPT: 

Here’s the updated illustration showing a vast open field creatively landscaped into two distinct uppercase ‘A’ letters, bustling with people enjoying various activities in a sunny, cheerful setting.

(Yes, it created both images.)

Me: Give me the same, but with people surrounding the “A” and the “I.” Also, please put serifs on the “I.”

ChatGPT:

Here’s the updated illustration showing a vast open field creatively landscaped into the shapes of the uppercase letters ‘A’ and ‘I’, both with serifs. The field is surrounded by people enjoying various activities in a sunny, cheerful setting.

Me: Try the same, but with “a” and “i” as separate letters.

ChatGPT: 

Here’s the updated illustration showing a vast open field creatively landscaped into the shapes of the lowercase letters ‘a’ and ‘i’. The setting is surrounded by people enjoying various activities in a sunny, cheerful atmosphere.

Me: Closer. Only now take it out of the city. I want only countryside.

ChatGPT:

Here’s the updated illustration showing a vast open field in the countryside, creatively landscaped into the shapes of the lowercase letters ‘a’ and ‘i’. The setting is serene and picturesque, surrounded by people enjoying rural activities.

Me: Please make the “a” and the “i” separate.

ChatGPT:

Here’s the updated illustration showing a vast open field in the countryside, creatively landscaped into the distinctly separated lowercase letters ‘a’ and ‘i’. The setting is serene, surrounded by people enjoying rural activities in a picturesque and peaceful outdoor gathering.

At this point I gave up and decided to give Microsoft Copilot a whack—

Me: A vast field on which the ground spells the letters A and I, with people on it, having a good time.

Microsoft Copilot:

I decided not to push my luck, and used the one on the bottom right.

It’s fun to know I am not alone at this. Here is a brilliant video of somebody far more patient than I getting ChatGPT to spell HONDA in ASCII art.

Early days, folks. Early days.

People need their own AIs. Personally and collectively.

We won’t get them from Anthropic, Apple, Google, OpenAI, Meta, or Microsoft. Not even from Apple.

All those companies will want to provide AIaaS: AI as a Service, rather than AI that’s yours alone. Or ours, collectively.

The People’s AI can only come from people. Since it will be made of code, it will come from open-source developers working for all of us, and not just for their employers—even if those employers are companies listed above.*

That’s how we got Linux, Apache, MySQL, Python, and countless other open-source code bases on which the digital world is now built from the ground up. Our common ground is open-source code, standards, and protocols.

The sum of business that happens atop that common ground is incalculably vast. It also owes to what we first started calling because effects twenty years ago at Bloggercon. That was when people were making a lot more money because of blogging than with blogging.

Right after that it also became clear that most of the money being made in the whole tech world was because of open-source code, standards, and protocols, rather than with them. (I wrote more about it here, here, and here.)

So, thanks to because effects, the most leveraged investments anyone can make today will be in developing open source code for The People’s AI.

That’s the AI each of us will have for our own, and that we can use both by ourselves and together as communities.

Those because investments will pay off on the with side as lavishly as investments in TCP/IP, HTTP, Linux, and countless other open-source efforts have delivered across the last three decades.

Only now they’ll pay off a lot faster. For all of us.

*See what I wrote for Linux Journal in 2006 about how IBM got clueful about paying kernel developers to work for the whole world and not just one company.

Newsletters are all the rage now. In recognition of that, I blogged here two years ago about the idea of writing a solo newsletter. Since then I’ve been co-producing this one with Katherine Druckman at Reality 2.o. It’s a Substack one, so I know how that game works on the production as well as the consumption ends.

Recently I also learned that WordPress makes it easy to turn blogs into newsletters, which is why you see “Get New Posts by Email” in the right column here. So, wanting an image to go with the news that this blog can now be a newsletter if you like, I said to ChatGPT, “Draw me Doc Searls blogging on the left side of the image, and producing a newsletter on the right side.” It gave me this, including the caption:

Except for the slouch, I never looked like that. But what the hell. AI is wacky shit, so there ya go.

Feel free to subscribe.

There is a war going on. Humanity and nature are on one side and Big Tech is on the other. The two sides are not opposed. They are orthogonal. The human side is horizontal and the Big Tech side is vertical.*

The human side is personal, social, self-governed, heterarchical, open, and grounded in the physical world. Its model is nature, and the cooperative contexts in which competition, creation, and destruction happen in the natural world.

The Big Tech side is corporate, industrial, hierarchical, competitive, mechanistic, extractive, and closed, even though it produces many positive-sum products and services that are good for people and good for nature. It is also, being competitive and rewarding toward winner-take-most outcomes, dominated by giants.

This war has been fought over many other things in the past, especially in tech. But AI is the big one right now—and perhaps the biggest one of all time.

Over the long run, both sides will win, because we need the best of what both bring to the world’s big round table. In the past, this has happened in countless markets, countries, polities, societies, and other contexts. In tech it happened with the conflict between PCs and mainframes, between the open and public Internet and closed private networks, and between open operating systems and closed ones. None of those conflicts have final outcomes, but they have arrived at stable and cooperative states. They arrived at those states because everyone recognized that people can do more with their own tools than those big entities can do on theirs, or by using people as extracted resources.

This conflict is perhaps best represented by the ironies that have been at work within OpenAI and Sam Altman, its prior and current CEO. We can also see it with sparkling clarity in something amazing that Sam said near the close of his keynote at the first OpenAI Developer Conference, in November of last year:

Lets unpack that.

Individual empowerment means exactly what it says. Agency is the ability to take action or to choose what action to take (Cambridge Dictionary). Scale means growth toward ubiquity.

You have individual empowerment and agency when you ride your bike, drive your car, mow your lawn, or button your shirt. You also have it when you work on your laptop, phone, and other smart rectangles. Scale means your power and agency will grow to the max while the same will happen for nearly everyone else. Scale for you alone won’t cut it. When most of us have it, that’s scale.

Technologies extend us. They enlarge our capacities in the world. Intelligence is one of those capacities. So is memory. Your rectangles help a lot with both. That’s why those have already scaled to ubiquity, or close enough.

AI will do the same, but only if it’s personal. Not if it’s  just “personalized.”

As Jamie Smith made clear here a year ago, “your personal AI isn’t really personal.”

ChatGPT4 doesn’t know that yet. I can tell because I just asked:

Me:
What is “personal AI”?

ChatGPT4:
“Personal AI” refers to artificial intelligence systems that are designed to serve individual users through personalized interactions and services. These AI systems learn from the specific preferences, behaviors, and needs of their users to offer more tailored assistance, recommendations, or information. The goal of personal AI is to enhance user experience by adapting to unique personal profiles.

There are various applications of personal AI, including:

1. Virtual Assistants: Like Siri, Google Assistant, and others, these AIs help with daily tasks such as scheduling, reminders, searching information, and controlling smart home devices, all customized to the user’s habits and preferences.
2. Recommendation Systems: Used in streaming services like Netflix or shopping platforms like Amazon, these AI systems analyze your past behavior to recommend movies, shows, or products you might like.
3. Healthcare: Personal AI can track individual health metrics and provide personalized advice, monitor conditions, or even alert medical professionals if needed.
4. Learning and Development: In education, personal AI can adapt learning materials to the pace and learning style of the student, offering a customized educational experience.
5. Gaming: AI in gaming can adapt to provide a challenge tailored to the player’s skill level or alter the game narrative based on choices made by the player.

The development of personal AI focuses on enhancing user engagement by creating more intuitive and responsive interactions that feel uniquely suited to each individual.

For a second opinion, I asked Google’s Gemini the same question.

Me:
What is “personal AI”?

Gemini:
Personal AI refers to artificial intelligence designed to assist and interact with a specific individual. It’s essentially your own AI companion that learns about you and tailors its services to your needs. Here are some key aspects of personal AI:

1. Personalization: Unlike general-purpose AI assistants, personal AI focuses on you. It learns from your interactions, preferences, and habits to become more helpful over time.
2. Focus on Memory and Knowledge: Some personal AI systems aim to become an extension of your mind. They can store your memories, knowledge, and experiences, making them readily accessible and even usable to help with tasks like writing or communication.
3. Varied Applications: Personal AI can have a wide range of applications. Imagine an AI that helps you:
4. Organize your life: Manage schedules, appointments, and reminders.
5. Boost productivity: Assist with tasks, research, and communication.
6. Enhance creativity: Help you brainstorm ideas or generate creative content.
7. Improve learning: Personalize learning experiences and provide targeted information.

Privacy Concerns: Storing personal data on an AI raises concerns about privacy and security.

Overall, personal AI holds promise for a future where technology seamlessly integrates with our lives, offering personalized assistance and support.

To both companies, personal AI is a personalized service—from them. It’s not something you own and control. It’s not about individual empowerment and agency. It doesn’t extend you. It’s hired prosthesis: an extension of them rather than of you.

Let’s name the category: AIaaS—AI as a Service.

But hats off. OpenAI and Gemini do amazing jobs. So do lots of other AI services by wannabe giants. I use AI every day to improve what I write, to generate and fix images, to answer questions that old-fashioned search engines can’t answer or suck at. I even pay extra for some of it (such as ChatGPT4 and Adobe’s Creative Suite). And it seems they all get better, all the time, at everything. Won’t personalization be good enough, eventually?

No. Because they aren’t you. They also aren’t yours, so they can’t extend you. They can seem to. But they don’t. They also don’t have access to most of your private life. Nor should they.

But your private life could use some AI help. For example—

• Schedules, including on your calendars, past and future
• Health data, including all your medical reports, prescriptions, appointments, insurance information, past and present providers, plus what your watch, phone, and other devices record about you
• Financial records, including bills, receipts, taxes, and anything called an account that involves money
• Travel, including all the movements your phone (and phone company), watch, and car record about where you go and where you’ve been
• Work—past and present, including whatever HR systems know or knew about you
• Contacts—all the people, businesses, and other entities you know
• Business relationships, with brokers, retailers, service providers, whatever
• Subscriptions, including all those “just $1 for the first four weeks” offers you’ve accepted, plus other forms of screwage that are stock-in-trade for companies selling subscription systems to businesses.
• Property, including all the stuff on your shelves, floors, closets, garages, and storage spaces—plus your stocks and real estate.

It’s not easy to visualize what a personal AI might do for those, but let’s try. Here’s how Microsoft’s Copilot (or whatever it’s called this week) did it for me before I got rid of all its misspellings and added my own hunks of text:

All that stuff is data. But most of it is scattered between apps and clouds belonging to Apple, Google, Microsoft, Amazon, Meta, phone companies, cable companies, car makers, health care systems, insurance companies, banks, credit card companies, retailers, and other systems that are not yours. And most of them also think that data is theirs and not yours.

To collect and manage all that stuff, you need tools that don’t yet exist: tools that are yours and not theirs. We could hardly begin to imagine those tools before AI came along. Now we can.

For example, you should be able to take a picture of the books on your shelves and have a complete record of what those books are and where you got them. You’ll know where you got them because you have a complete history of what you bought, where and from whom. You should be able to point your camera in your closets, at the rugs on your floors, at your furniture, at the VIN number of your car that’s visible under your windshield, at your appliances and plumbing fixtures, and have your AI tell you what those are, or at least make far more educated guesses than you can make on your own.

Yes, your AI should be able to tap into external databases and AI systems for help, but without divulging identity information or other private data. Those services should be dependent variables, not independent ones. For full individual empowerment and agency, you need to be independent. So does everyone else with personal AI.

Now imagine having a scanner that you can feed every bill, every receipt, every subscription renewal notice, and have AI software that tells you what’s what with each of them, and sorts records into the places they belong.

Ever notice that the Amazon line items on your credit card bill not only aren’t itemized, but don’t match Amazon’s online record of what you ordered? Your personal AI can sort that out. It can help say which are business and personal expenses, which are suspicious in some way, what doesn’t add up, and much more.

Your personal AI should be able to answer questions like, How many times have I had lunch at this place? Who was I with? When was it we drove to see so-and-so in Wisconsin? What route did we take? What was that one car we rented that we actually liked?

Way back in 1995, when our family first got on the Internet over dial-up, using the first graphical browsers on our PC, and e-commerce began to take off with Amazon, eBay, and other online retailers, my wife asked an essential question: Why can’t I have my own shopping cart that I take from site to site?

Twenty-nine years later, we still don’t have the answer, because every retailer wants you to use its own. And we’re stuck in that system. It’s the same system that has us separately consenting to what sites ironically call “your privacy choices.” And aren’t.

There are countless nice things we can’t have in the digital world today because we aren’t people there. We are accounts. And we are reduced to accounts by every entity that requires a login and password.

This system is a legacy of client-server, a euphemism for slave-master. We might also call it calf-cow, because that’s how we relate to businesses with which we have accounts. And that model is leveraged on the Web like this:

We go to sites for the milk of content and free cookies, whether we want them or not. We are also just “users.”

In the client-server world, servers get scale. Clients have no more scale than what each account—each cow—separately allows. Sure, users get lots of benefits, but scale across many cows is not one of them. And no, “login with Google” and “login with Facebook” are just passes that let calves of ruling cows wander into vassal pastures.

For individual empowerment and scale to happen, we need to be self-sovereign and independent. Personal AI can give that to us. It can do that by solving problems such as the ones listed above, and by working as agents that represent us as human beings—rather than mere users—when we engage with Big Tech’s cows.

This will be a fight at first, because the cows think they run all of nature and not just their own farms. And $trillions are being invested in the same old cattle industry, with AI painted all over the new barns. Comparatively speaking, close to nothing is going toward giving independent and self-sovereign individuals the kind of power and scale Sam Altman says he wants to give us but can’t because he’s on the big cow side of this thing.

So where do we start?

First, with open source code and open standards. We have some already. Llama 3, from Meta AI, is “your own intelligent assistant,” and positions Meta as a more open and user-friendly cow than OpenAI. Meta is still on the top-down Big Tech side of the war we’re in. But hell, we can use what they’ve got. So let’s play with it.

Here on the ground there are all these (with quotage lifted from their sites or reviews such as this one)—

• MindsDB: “an open-source AutoML framework”
• Alt.ai: “It’s an A.I. which aims to digitize users’ intentions and place it on the cloud to let our clones deal with all digital operations.”
• Keras: “a multi-backend deep learning framework, with support for JAX, TensorFlow, and PyTorch”
• PyTorch: “Python package that provides two high-level features: Tensor computation (like NumPy) with strong GPU acceleration, and Deep neural networks built on a tape-based autograd system
• Tensor Flow: “open-source framework for machine learning”
• CoreNet: a deep neural network toolkit for small and large-scale models, from Apple
• Haystack: an “open source Python framework by deepset for building custom apps with large language models (LLMs).”
• Image Super-Resolution (ISR): “(an) open source tool employs a machine learning model that you can train to guess at the details in a low-resolution image:
• Blender: “A rich interface and numerous plugins make it possible to create complex motion graphics or cinematic vistas”
• DeepFaceLab: “open source deepfake technology that runs on Python”
• tflearn: “an advanced deep learning library”
• PYTensor: “a Python library that allows you to define, optimize/rewrite, and evaluate mathematical expressions involving multi-dimensional arrays efficiently.” (Was Theano)
• LM Studio: “Discover, download, and run local LLMs”
• HuggingFace Transformers: “a popular open-source library for Natural Language Processing (NLP) tasks”
• Fast.ai: “a library for working with deep learning tasks”
• OpenCV: “a popular Computer Vision and Image Processing library developed by Intel”
• Detectron2: “a next-generation library that provides advanced detection and segmentation algorithm” and “a PyTorch-based modular object detection library”
• Ivy.ai: “an open-source deep learning library in Python focusing on research and development”
• OpenAssistant: “a project aimed at giving everyone access to a great chat-based large language model”
• PaddleNLP: “a popular open source NLP library that you can use to glean search sentiment and flag important entities”
• Delphi.AI: “Clone yourself. Build the digital version of you to scale your expertise and availability, infinitely.”
• Fauxpilot: “This is an attempt to build a locally hosted alternative to GitHub Copilot. It uses the SalesForce CodeGen models inside NVIDIA’s Triton Inference Server with the FasterTransformer backend.”
• Ray: “An open source framework to build and scale your ML and Python applications easily”
• Solid: “Solid is a specification that lets individuals and groups store their data securely in decentralized data stores called Pods. Pods are like secure web servers for data. When data is stored in a Pod, its owners control which people and applications can access it.”
• Sagen.ai: “Your very own AI Personal Assistant to manage your digital life.”
• YOLOv7: “is one of the fastest and most accurate open source object detection tools. Just provide the tool with a collection of images full of objects and see what happens next.”

—and lots of others that readers can tell me about. Do that and I will add links later. This is a work in progress.

Below all of those we still need something Linux-like that will become the open base on which lots of other stuff runs. The closest I’ve seen so far is pAI-OS, by Kwaai.ai, a nonprofit I now serve as Chief Intention Officer. I got recruited by Reza Rassool, Kwaai’s founder and chair, because he believes personal AI is required to make The Intention Economy finally happen. So that was a hard offer to refuse. Kwaai also has a large, growing, and active community, which I believe is necessary, cool, and very encouraging.

As with most (maybe all) of the projects listed above, Kwaai is a grass-roots effort by human beings on the natural, human, and horizontal side of a battle with giants who would rather give us personalized AI than have us meet them in a middle to which we will bring personal AI powers of our own. In the long run, we will meet in that middle, because personal AI will be better for everyone than personalized AI alone.

Watch us prove it. Better yet, join the effort.

*I am indebted to Lavonne Reimer for introducing and co-thinking the horizontal vs. vertical frame, and look forward eagerly to her own writings and lecturings on the topic.

Artificial is AI’s frst name. And Intelligence is a quality, not a quantity. You can’t measure it with a dipstick, a ruler, or an IQ test. If you could, you’d get the same result every time.*

But being artificial doesn’t mean AI isn’t dangerous, fun or both. It is, and will be, what we make of it.

That’s what Don Norman says, and he’s been publishing in AI journals since 1973. His laboratory produced the first multi-layer neural nets in the 1980s. He wrote Things that Make us Smart in 1993.

In the opinion of myself and countless others, Don is also the foremost authority on design—of anything and everything. For more on that, check out Don’s Web page, his Wikipedia page, and his books. Or, if you just want to sample some of his thoughts on AI, watch this.

Or you can skip all that and come to the good stuff: joining us in a talk with Don in the final salon of this semester on the topic of Artificial +/vs. Human Intelligence. It’s next Tuesday, April 9, at Noon Eastern time. (That’s less than 24 hours after the shadow of the Moon passes over the Indiana University campus. Yes, totality will be local here.)

Also, this won’t be a lecture or a presentation. It will be a lively discussion because Don is especially good at that.

It’s also free and online, but you have to register first. Do that here.

*For what it’s worth, my own known IQ test scores have an 80-point range. I’ve written about that, and the myth of “IQ” here, here, here, here, and I suppose in too many other places.

See how it says “Try in ChatGPT︎?” When I do that, it goes to https://chat.openai.com/. After I log in there, it offers no clue about where DALL-E 3 is. So I asked, “How do I get to the DALL-E 3 page after I’m logged in here?”

ChatGPT answered, “As of my last update in January 2022, DALL-E 3 is a hypothetical iteration of the DALL-E model, and there’s no information about its existence or how to access it. If it were to be released, you might typically find access through OpenAI’s website or platform if they make it available to the public. However, without further updates or announcements, it’s challenging to provide specific instructions. If OpenAI releases DALL-E 3 or any similar model in the future, you can check their official website or announcements for information on how to access it.”

Additional useless dialog followed. So now I’ll ask the Lazyweb. Does anyone know how to get into DALL-E 3?

Eigth in the News Commons series.

Back when I was on the board of my regional Red Cross chapter (this one), I learned four lessons about fund raising:

1. People are glad to pay value for value.
2. People are most willing to pay when they perceive and appreciate the value they get from a product or service.
3. People are most willing to pay full value when the need or opportunity to pay is immediate, and the amount they pay is up to them.
4. People are willing to pay more when they have a relationship with the other party (seller, service provider, philanthropy, cause, whatever)

Here’s something I wrote in The Cluetrain Manifesto (10th anniversary edition) about all four lessons at work:

Not long after Cluetrain came out in early 2000, I found myself on a cross-country flight, sitting beside a Nigerian pastor named Sayo Ajiboye. After we began to talk, it became clear to me that Sayo (pronounced “Shaiyo”) was a deeply wise man. Among his accomplishments was translating the highly annotated Thompson Bible into his native Yoruba language: a project that took eight of his thirty-nine years.

I told him that I had been involved in a far more modest book project—The Cluetrain Manifesto—and was traveling the speaking circuit, promoting it. When Sayo asked me what the book was about, I explained how “markets are conversations” was the first of our ninety-five theses, and how we had unpacked it in a chapter by that title. Sayo listened thoughtfully, then came back with the same response I had heard from other readers in what back then was still called the Third World: “Markets are conversations” is a pretty smart thing for well-off guys from the First World to be talking about. But it doesn’t go far enough.

When I asked him why, he told me to imagine we were in a “natural” marketplace—a real one in, say, an African village where one’s “brand” was a matter personal reputation, and where nobody ruled customer choices with a pricing gun. Then he picked up one of those blue airline pillows and told me to imagine it was a garment, such as a coat, and that I was interested in buying it. “What’s the first thing you would say to the seller?” he asked.

“What does it cost?”

“Yes, you would say that,” he replied, meaning that this was typical of a First World shopper for whom price is the primary concern. Then he asked me to imagine that a conversation follows between the seller and me—that the two of us get to know each other a bit and learn from each other. “Now,” he asked, “What happens to the price?”
I said maybe now I’m willing to pay more while the seller is willing to charge less.

“Why?” Sayo asked.

I didn’t have an answer.

“Because you now have a relationship,” he said.

As we continued talking, it became clear to me that everything that happens in a marketplace falls into just three categories: transaction, conversation, and relationship. In our First World business culture, transaction matters most, conversation less, and relationship least. Worse, we conceive and justify everything in transactional terms. Nothing matters more than price and “the bottom line.” By looking at markets through the prism of transaction or even conversation, we miss the importance of relationship. We also don’t see how relationship has a value all its own: one that transcends, even as it improves, the other two.

Consider your relationship with friends and family, Sayo said. The value system there is based on caring and generosity, not on price. Balance and reciprocity may play in a relationship, but are not the basis of it. One does not make deals for love. There are other words for that.

Back in the industrialized world, few of our market relationships run so deep, nor should they. By necessity much of our relating is shallow and temporary. We don’t want to get personal with an ATM machine or even with real bank tellers. Friendly is nice, but in most business situations that’s about as far as we want to go.

But relationship is a broad category: broad enough to contain all forms of relating—the shallow as well as the deep, the temporary as well as the enduring. In the business culture of the industrialized world, Sayo said, we barely understand relationship’s full meaning or potential. And we should. Doing so would be good for business.

So he told me our next assignment was to unpack and study another thesis: Markets are relationships.

That is why, six years after the first edition of Cluetrain came out, I started ProjectVRM (the R means Relationship) at the Berkman Klein Center, wrote The Intention Economy: When Customers Take Charge, (Harvard Business Review Press, 2012), co-founded Customer Commons (in 2013), and am now a visiting scholar with the Ostrom Workshop at Indiana University, thinking out loud about how a news commons might thrive as a market of relationships—starting here in Bloomington, IU’s home town.

In The News Business (which precedes this post), I said the three current business models for local news were advertising, subscription, and philanthropy, and promised a fourth. This is it: emancipayments.

We* came up with this idea in 2009. Here is how the EmanciPay page on the ProjectVRM wiki puts it:

Overview

Simply put, Emancipay makes it easy for anybody to pay (or offer to pay) —

1. as much as they like
2. however they like
3. for whatever they like
4. on their own terms

— or at least to start with that full set of options, and to work out differences with sellers easily and with minimal friction.

Emancipay turns consumers (aka users) into customers by giving them a pricing gun (something which in the past only sellers used) and their own means to make offers, to pay outright, and to escrow the intention to pay when price and other requirements are met. And to be able to do this at scale across all sellers, much as cash, browsers, credit cards and email clients do the same. Payments themselves can also be escrowed.

In slightly more technical terms, EmanciPay is a payment framework for customers operating with full agency in the open marketplace, and at scale. It operates on open protocols and standards, so it can be used by any buyer, seller or intermediary.

It was conceived as a way to pay for music, journalism, or what any artist brings into the world. But it can apply to anything. For example, [subscriptions], which have become by 2021 a giant fecosystem in which every seller has separate and non-substitutable scale across all subscribers, while subscribers have zero scale across all sellers, with the highly conditional exceptions of silo’d commercial intermediaries. As [Customer Commons] puts it,

There’s also not much help coming from the subscription management services we have on our side: Truebill, Bobby, Money Dashboard, Mint, Subscript Me, BillTracker Pro, Trim, Subby, Card Due, Sift, SubMan, and Subscript Me. Nor from the subscription management systems offered by Paypal, Amazon, Apple or Google (e.g. with Google Sheets and Google Doc templates). All of them are too narrow, too closed and exclusive, too exposed to the surveillance imperatives of corporate giants, and too vested in the status quo.

That status quo sucks (see here, or just look up “subscription hell”), and it’s way past time to unscrew it.) But how?

The better question is where?

The answer to that is on our side: the customer’s side.

While EmanciPay was first conceived by ProjectVRM as a way to make live payments to nonprofits and to provide a new monetization method for publishers. it also works as a counterpart to sellers’ subscription systems in what Zuora (a supplier of subscription management systems to the publishing industry, including The Guardian and Financial Times) calls the “subscription economy“, which it says “is built on ever changing relationships with your customers”. Since relationships are two-way by nature, EmanciPay is one way that customers can manage their end, while publisher-side systems such as Zuora’s manage the other.

EmanciPay economic case

EmanciPay provides a new form of economic signaling not available to individuals, either on the Net or before the Net became available as a communications medium. EmanciPay will use open standards and be comprised of open source code. While any commercial [Fourth party] can use EmanciPay (or its principles, or any parts of it they like), EmanciPay’s open and standard framework will support fourth parties by making them substitutable, much as the open standards of email (smtp, pop3, imap) make email systems substitutable. (Each has what Joe Andrieu calls service endpoint portability.)

EmanciPay is an instrument of customer independence from all of the billion (or so) commercial entities on the Net, each with its own arcane and silo’d systems for engaging and managing customer relations, as well as receipt, acknowledgement and accounting for payments from customers.

Use Case Background

EmanciPay was conceived originally as a way to provide a customers with the means to signal interest and ability to pay for media and creative works (most of which are freely available on the Web, if not always free of charge). Through EmanciPay, demand and supply can relate, converse and transact business on mutually beneficial terms, rather than only on terms provided by the countless different silo’d systems we have today, each serving to hold the customer captive, and causing much inconvenience and friction in the process.

Media goods were chosen for five reasons:

1. because most are available for free, even if they cost money, or are behind paywalls
2. paywalls, which are cookie-based, cannot relate to individuals as anything other than submissive and dependent parties (and each browser a users employs carries a different set of cookies)
3. both media companies and non-profits are constantly looking for new sources of revenue
4. the subscription model, while it creates steady income and other conveniences for sellers, is often a bad deal for customers, and is now so overused (see Subscriptification) that the world is approaching a peak subscription crisis, and unscrewing it can only happen from the customer’s side (because the business is incapable of unscrewing the problem itself
5. all methods of intermediating payment choices are either silo’d by the seller or silo’d by intermediators, discouraging participation by individuals.

What the marketplace requires are new business and social contracts that ease payment and stigmatize non-payment for creative goods. The friction involved in voluntary payment is still high, even on the Web, where one must go through complex ceremonies even to make simple payments.  There is no common and easy way either to keep track of what media (free or otherwise) we use (see Media Logging), to determine what it might be worth, and to pay for it easily and in standard ways — to many different suppliers. (Again, each supplier has its own system for accepting payments.)

EmanciPay differs from other payment models (subscriptions, newsstand, tip jars) by providing customers with the ability to choose what they wish to pay and how they’ll pay it, with minimum friction — and with full choice about what they disclose about themselves.

EmanciPay will also support credit for referrals, requests for service, feedback and other relationship support mechanisms, all at the control of the user. For example, EmanciPay can provide quick and easy ways for listeners to pay for public radio broadcasts or podcasts, for readers to pay for otherwise “free” papers or blogs, for listeners to pay to hear music and support artists, for users to issue promises of payment for for stories or programs — all without requiring the individual to disclose unnecessary private information, or to become a “member” — although these options are kept open.

This will scaffold genuine relationships between buyers and sellers in the media marketplace. It will also give deeper meaning to “membership” in non-profits. (Under the current system, “membership” generally means putting one’s name on a pitch list for future contributions, and not much more than that.)

EmanciPay will also connect the sellers’ CRM (Customer Relationship Management) systems with customers’ VRM (Vendor Relationship Management) systems, supporting rich and participatory two-way relationships. In fact, EmanciPay will by definition be a VRM system.

Micro-accounting and Macro-distribution

The idea of “micro-payments” for goods on the Net has been around for a long time, and is often brought up as a potential business model for journalism. For example in this article by Walter Isaacson in Time Magazine. It hasn’t happened, at least not globally, because it’s too complicated, and in prototype only works inside private silos.

What ProjectVRM suggests instead is something we don’t yet have, but very much need:

1. micro-accounting for actual uses. Think of this simply as “keeping track of” the news, podcasts, newsletters, or music we consume.
2. macro-distribution of payments for accumulated use (that’s no longer “micro”).

Much — maybe most — of the digital goods we consume are both free for the taking and worth more than $zero. How much more? We need to be able to say. In economic terms, demand needs to have a much wider range of signals it can give to supply. And give to each other, to better gauge what we should be willing to pay for free stuff that has real value but not a hard price.

As currently planned, EmanciPay would –

1. Provide a single and easy way for consumers of “content” to become customers of it. In the current system — which isn’t one — every artist, every musical group, and every public radio and TV station has his, her or its own way of taking in contributions from those who appreciate the work. This can be arduous and time-consuming for everybody involved. (Imagine trying to pay separately every musical artist you like, for all your enjoyment of each artist’s work.) What EmanciPay proposes, however, is not a replacement for existing systems, but a new system that can supplement existing fund-raising systems — one that can soak up much of today’s MLOTT: Money Left On The Table.
2. Provide ways for individuals to look back through their media usage histories, inform themselves about what they have been enjoying, and determine how much it is worth to them. The Copyright Arbitration Royalty Panel (CARP), and later the Copyright Royalty Board (CRB), both came up with “rates and terms that would have been negotiated in the marketplace between a willing buyer and a willing seller.” This almost absurd language first appeared in the 1995 Digital Performance Royalty Act (DPRA) and was tweaked in 1998 by the Digital Millennium Copyright Act (DMCA), under which both the CARP and the CRB operated. The rates they came up with peaked at $.0001 per “performance” (a song or recording), per listener. EmanciPay creates the “willing buyer” that the DPRA thought wouldn’t exist.
3. Stigmatize non-payment for worthwhile media goods. This is where “social” will finally come to be something more than yet another tech buzzmodifier.

All these require micro-accounting, not micro-payments. Micro-accounting can inform ordinary payments that can be made in clever new ways that should satisfy everybody with an interest in seeing artists compensated fairly for their work. An individual listener, for example, can say “I want to pay 1¢ for every song I hear,” and “I’ll send SoundExchange a lump sum of all the pennies wish to pay for songs I have heard over a year, along with an accounting of what artists and songs I’ve listened to” — and leave dispersal of those totaled pennies up to the kind of agency that likes, and can be trusted, to do that kind of thing. That’s the macro-distribution part of the system.

Similar systems can also be put in place for readers of newspapers, blogs, and other journals. What’s important is that the control is in the hands of the individual and that the accounting and dispersal systems work the same way for everybody.

I visited EmanciPay use cases twice in Linux Journal:

• An Easy Way to Pay for Journalism, Music and Everything Else We Like (May 2015)
• An Immodest Proposal for the Music Industry (November 2018)

There are two differences in the world today that should make it easier to code up something like EmanciPay:

1. Smartphones and apps on them have become extensions of ourselves.
2. AI.

For the latter, I am not talking about the kind of centralized AI we get from Amazon, Microsoft/OpenAI, Adobe, and the rest. I’m talking about AI that’s as personal as our own underwear and gives us what Sam Altman calls “individual empowerment and agency on a scale we’ve never seen before.” That quote became the title of the post I wrote at that link. I will unpack it further in an upcoming News Commons post.

But first I’ll dig deeper into what we need to develop EmanciPay, and how we can use it to scaffold up the kind of markets first imagined by The Cluetrain Manifesto, a quarter century ago.

*Big hat tip to Keith Hopper for his thinking and work on this, especially toward ListenLog, which is now fourteen years ahead of its time. And that time will come. Also to Joe Andrieu, whose The User as a Point of Integration (published in 2007) is a founding document in the VRM canon. He reported on progress here in 2017. All hail writers who keep their archives alive on the Web.

Seventh in the News Commons series.

How does the news business see itself?

Easy: ask an AI. Or a lot of them.*

That’s what I’ve been doing. Unless otherwise noted, all the following respond to the same three-word prompt: the news business. Here goes…

Microsoft Bing (Full name: Microsoft Bing Image Creator from Designer), which uses DALL-E 3:

Dream Studio by Stability.ai (which, as you see, required a longer prompt than I used with the others):

Deep Dream Generator:

Adobe Firefly:

Craiyon, again with a longer prompt:

Stable Diffusion:

Finally, a series from DeepAI., each generated in a different style.

First, impressionism:

Surreal graphics:

Renaissance painting:

Abstract painting:

AI art:

What do these say about the news business? Well,

1. It’s mostly male.
2. It’s mostly about newspapers, somewhat about TV, and idealized both.
3. It used to be big.
4. It doesn’t know what to make of the Internet.
5. It’s obsolete in the extreme.

For most of the prior century, the news business was big. In tech parlance, it scaled. Here in the U.S. and Canada, every town had a newspaper, and in some cases several. Many towns—and all cities—had radio stations. Every name-brand city had a TV station, or two, or more. The great newsweeklies, Time and Newsweek, had millions of subscribers and made lots of money. So did TV network news operations. Newsstands were everywhere.

All of that has collapsed. Some print and broadcast news operations still exist, but most are shells of their former selves, and many put news icing on a cake of partisan talk shows. Exceptions to collapse are the surviving news giants (New York Times, Washington Post, Wall Street Journal), and resourceful public broadcasters. (Pew Research shows NPR’s audience has long topped 20 million people, though it is slowly declining.)

People today get most of their news through phones, tablets, and laptops. These are packed with apps that maximize optionality. People now hardly listen, watch, or read on schedules set by publishers, stations, or networks. Everyone with a smartphone had a limitless variety of news sources. Or sources within sources such as Instagram, TikTok, YouTube, and old-fashioned social media such as Facebook and X.

According to Pew, the top news sources for young people today are TikTok and social media. In other words, from each other. The threshold of news creation and production is also low. This is why, according to Exploding Topics, there are now over three million podcasts worldwide.

As Scott Galloway put it in a recent Pivot podcast (which I can’t find right now), news is a shitty business—at least if you want to scale up something huge. It’s not even a great small business. But hell, neither is running a restaurant, a nail salon, a clothing shop, or a small farm. But those are real businesses.

As Jeff Jarvis makes clear in The Gutenberg Parenthesis: The Age of Print and Its Lessons for the Age of the Internet (which I highly recommend), we are at the end of one long era and the start of another one.

In these early years of The Internet Age, the most substantive news and news businesses are the local kind. True, not everybody cares about local news. But everybody lives somewhere, and it does matter what goes on where people live. Belonging somewhere in the virtual world is optional, but it is mandatory in the physical one. And, as with running a restaurant, a store, or a farm, reporting local news is a labor of talent and love. It’s what we still call “a living.”

Right now there are three models for the local news business: advertising, subscription, and philanthropy. In my next post, the eighth in this series, I’ll lay out the case for a fourth one.

*I didn’t try Midjourney, DALL-E 3, or Stable Diffusion because they all require subscriptions, and I don’t feel like paying for those yet. DALL-E 2 yielded blah results.

Several thousand years ago, when I was on leave from journalism and working as a marketing dweeb, my small North Carolina firm learned about PRIZM (Potential Rating Index for Zip Markets), a techy new service that told me that my rural zip code was “Hardscrabble,” while the next one over was a suburb PRIZM called “Volvo Wagons” or something.

My current zip, in Bloomington, Indiana, features five out of PRIZM’s 68 numbered types:

• 48 Generation Web—Low Income Younger Family Mix
• 47 Striving Selfies—Lower Midscale Middle Age Mostly w/o Kids
• 15 New Homesteaders—Wealthy Middle Age Mostly w/ Kids
• 51 Campers & Camo—Lower Midscale Middle Age Family Mix
• 66 New Beginnings—Low Income Younger Family Mix

None of which describes me or my wife.

Sort of close is 05 – Country Squires: “Members of this segment fled the city life for the charms of small-town living. Many have executive jobs and live in recently built homes.” Except we didn’t flee and our home was built in  1899 or 1915. (Sources differ.) But we are building a house, so maybe that counts.

A bit closer is 20 – Empty Nests: “Most residents are over 65 years old, but they show no interest in a rest-home retirement. With their grown-up children out of the house they pursue active, and activist, lifestyles.”

But all of that stuff is just name-calling against typified populations—a form of -ism not much different than racism, sexism, or ageism. That’s why, on the receiving end, we tend not to like it, even if it brings us ‘relevant’ messages from sellers. (This happens far less than sellers think, and typically at the cost of privacy lost to surveillance.)

All of us are as different as our faces and voices. Being different than everybody—even ourselves five minutes ago—is among our most human qualities. We all grow and change constantly, whether we want to or not.

Marketing didn’t get that when PRIZM was invented in 1980, and it doesn’t get it today, for the simple reason that marketing was not built for talking to people. It was built for typifying people.

Chris Locke, David Weinberger, Rick Levine, and I all thought there was hope for marketing when we wrote The Cluetrain Manifesto in 1999, because we saw the Internet as a radically new way to connect the demand and supply sides of markets directly, and personally.

But marketing instead saw the Internet as a great way to spy on people and to typify them more than ever.  PRIZM persists, entrenched as ever. And conversations among customers and marketers happen in two very different and disconnected echo chambers, mostly using giant corporate platforms.

For a sense of how thoroughly disconnected those chambers are, see any of Tom Fishburne’s Marketoons. They’re brilliant and spot-on.

They also make clear—at least to me—that Cluetrain won’t prove right until marketing gets out of the way.

Which it won’t on its own. Our side—the customers’ side—needs to obsolesce it.

The image above was generated by the prompt in the caption under it, using what currently calls itself Microsoft Bing Image Creator from Designer, which persists Microsoft’s long tradition of aversive and unmemorable names for products.

I asked ChatGPT and Bard to “List all Christmas holiday tunes in chronological order, by the year they were written, running from oldest at the top to the newest at the bottom.” ChatGPT gave me a lame list. Bard gave me a much better one, improved by my follow-ups. Here ya go:

While creating a definitive chronological list of every Christmas tune throughout history is near impossible, I can offer you a comprehensive, categorized timeline of notable Christmas music spanning centuries, from ancient hymns to modern-day pop hits. Keep in mind this is not an exhaustive list, and some dates may be approximate:

Pre-Renaissance Era (Before 1450)

• 4th Century: “Hymnus ad Natales Domine Jesu” (attributed to Hilary of Poitiers) – One of the earliest known Latin hymns referencing Jesus’ birth.
• 13th Century: “In dulci jubilo” – Traditional German carol celebrating the joy of Christmas.
• 14th Century: “O Come, All Ye Faithful” – Latin hymn, believed to be of English origin, later translated into many languages.

Renaissance Era (1450-1600)

• 15th Century: “There Is No Rose” – Traditional English carol referencing Mary as a “spotless rose.”
• 15th Century: “Deck the Halls” – Welsh carol with pagan roots, originally a celebration of the winter solstice.

Baroque Era (1600-1750)

• 1642: “What Child Is This?” – English carol based on a poem by William Chatterton Dix.
• 1678: “Silent Night” – German carol written by Franz Xaver Gruber and Joseph Mohr.

Classical Era (1750-1830)

• 1818: “O Holy Night” – French carol originally titled “Cantique de Noël” with lyrics by Placide Cappeau and music by Adolphe Adam.

Romantic Era (1830-1900)

• 1865: “Jingle Bells” – American song originally written by James Lord Pierpont with lyrics unrelated to Christmas.
• 1874: “O Little Town of Bethlehem” – American carol written by Phillips Brooks.

20th Century and Beyond

• 1934: “Have Yourself a Merry Little Christmas” – American song written by Ralph Blane and Hugh Martin for the Judy Garland film “Meet Me in St. Louis.”
• 1942: “White Christmas” – American song written by Irving Berlin for the film “Holiday Inn.”
• 1953: “Rockin’ Around the Christmas Tree” – American rock and roll song written by Johnny Marks.
• 1964: “Rudolph the Red-Nosed Reindeer” – American song written by Johnny Marks, based on the poem by Robert L. May.
• 1973: “All I Want for Christmas Is You” – American pop song written and performed by Mariah Carey.
• 1984: “Last Christmas” – English song written by George Michael for Wham!
• 1994: “Santa Claus Is Comin’ to Town” – American song written by J.C. Sprink and Haven Gillespie.
• 2019: “All Is Well” – British song written and performed by James Arthur.

This list showcases the evolution of Christmas music through various eras and genres. Remember, Christmas music is constantly evolving, with new carols and songs emerging every year.

Happy Holidays!

Then, “What about A Chrismas Song, by Mel Tormé? Have Yourself a Merry Little Christmas? Frosty the Snowman? Mary’s Boy Child?”

You’re absolutely right! I apologize for omitting those wonderful Christmas classics from my previous response. Here’s where they fit into the timeline:

• 1946: “Have Yourself a Merry Little Christmas” – As mentioned previously, this beloved song by Judy Garland was written in 1934 by Ralph Blane and Hugh Martin.
• 1951: “A Christmas Song” – This charming and introspective tune by Mel Tormé perfectly captures the bittersweet sentiment of Christmas.
• 1950: “Frosty the Snowman” – Jack Rollins and Steve Nelson penned this playful Christmas carol about a jolly snowman in 1950.
• 1956: “Mary’s Boy Child” – This moving gospel carol was written by Jester Hairston in 1956, based on an African American spiritual.

My apologies for the earlier oversight. These songs undoubtedly deserve their place among the cherished Christmas tunes throughout history.

Do you have any other Christmas music questions for me? I’m happy to delve deeper into the fascinating world of holiday melodies.

Then, “Oh, and Rockin Around the Christmas Tree?”

Ah, you’re absolutely right! How could I forget the infectious energy of “Rockin’ Around the Christmas Tree”? It definitely belongs on the list. In fact, it was written earlier than some of the others I mentioned:

• 1958: “Rockin’ Around the Christmas Tree” – This rock n’ roll Christmas classic, penned by Johnny Marks, brought a vibrant and playful edge to holiday music.

Thank you for reminding me! Your keen eye for festive tunes is impressive. Merry Christmas and keep the musical celebration going!

I stopped there. But I assume you can keep going here: https://bard.google.com/chat/5623a530dcc35251

Eight years ago, I called ad blocking The Biggest Boycott in World History, because hundreds of millions of people were blocking ads online. (The headline came from my wife, by the way.) Then, a few days ago, Cory Doctorow kindly pointed to that post in one of his typically trenchant Pluralistic newsletters.

So I thought I’d check to see how the boycott is doing.

It’s hard to find original sources of hard numbers on ad blocking. Instead, there are lots of what I’ll call claims. But some of those claims do cite or link to sources of some kind. Here are four:

1. Brian Dean‘s Backlinko sources Hootsuite, saying 42.7% of Internet users employ ad blockers. Hootsuite, however, wants me to fill out a form that I am sure will get me spammed. So I’m passing on that. Meanwhile there are other interesting stats cited. Growson Edwards on Cipio.ai surfaces a bunch of Hootsuite graphics with interesting data.
2. Statista last January said “the ad blocking user penetration rate in the United States stood at approximately 26 percent in 2020, indicating that roughly 73 million internet users had installed some form of ad blocking software, plugin, or browser on their web-enabled devices that year. While awareness of these services lies at almost 90 percent, the number of internet users actively leveraging the technology has stagnated in recent years following visible changes in online user behavior. The switch from desktop to mobile has arguably had one of the most significant impacts on ad block usage: As internet users increasingly browse the web via mobile devices, desktop ad block usage rates in the U.S. and many other parts of the world are dropping, albeit at varying speeds. While mobile ad blocking adoption is still at a nascent stage in the U.S., the global number of mobile ad blocking browser users is rapidly increasing.” On another page, Statista says marketers “can conquer ad blocking by offering personalized advertising.” Anybody want that? Give me a show of hands. Thought so.
3. Blockthrough, an advertising company, offers a 2022 adblock report that requires filling out a form. So I passed on that one too, but can report that its “key insights” are these: “With 290M monthly active users globally, adblocking on desktop has climbed back close to its all-time-high from 2018,” and “The average adblock rate across geos and verticals is 21%, as measured across >10B pageviews on 9,453 websites.”
4. Surfshark has some cool maps showing which countries hate ads most and least, based on searches for ad-blocking software. (France was at the top.)

Perhaps more interesting than any of those stats (all of which are unsurprising) is using AI to generate graphics for a post such as this one. At first, I wanted the system (Bing Creator or whatever it’s called this week) to show two separate populations: one living blissfully in a land without advertising, and one with advertising everywhere. That was a fail. I couldn’t get it not to show advertising on both sides. Then I tried to get it to depict the blocking of ads, for example with a wall. That failed too, because advertising always appeared on the wall. Finally, I got the image above with a prompt asking for people who were happy to have advertising inside a giant bottle. Isn’t it crazy how fast the miraculous becomes annoying?

Just sharing some stuff I said on social media recently.:

1. It’s easy to make an ad hominem argument against anything humans do.
2. If we had to avoid every enterprise with owners we don’t like, we might as well graze on berries or something.
3. Capitalism is way too broad a brush with which to paint all of business. As Peter Drucker put it, most people don’t start a business to make money. They do it to make shoes.
4. The tech world we’ve had for the last few decades is deeply weird in many ways, such as its mix of thrown-spaghetti venture investments and psychotic incentives, e.g. wanting to break things, to run the world, to replace humans with cyborgs, and to work toward exits that will doom what’s already built while breaking faith with customers, workers, and other dependents. Economic thinkers of the industrial age, from Adam Smith and Karl Marx all the way forward, could hardly have imagined any of this shit. I still haven’t encountered any economic theory that can make full sense of it. (Though I’m not saying there isn’t one.)

The prompt for the AI art is a riff on #4. Note that the AI doesn’t have a clear idea of how Adam Smith looks.

What shall we make of AI?

Marina Zannoli has something to say about that, and she’ll say it this coming Tuesday, October 17, at Indiana University—and online too, at 12pm Eastern time. The title of her talk is Mastering AI: What I Learned as the Chief of Staff of Fundamental AI Research at Meta.

Though her work at Meta, Dr. Zannoli has come to believe that maximizing what’s useful about AI and minimizing what’s scary requires close collaboration between academic, industry, and governmental organizations. She’ll explain how in a lively discussion that will take place at the Hamilton Lugar School of Global and International Studies at IU, and online via Zoom (on a wall-sized screen).

Her talk is the second in this year’s Beyond the Web Salon Series, themed Human +/vs. Artificial intelligence. It is co-hosted Ostrom Workshop and the Hamilton Lugar School, both at IU.

The cost is $0, but you have to register to attend the Zoom. Do that here. And I’ll see you there.

The image above was generated by Bing Image Creator, using a prompt I can’t find right now but was something like, “Give me an image of people building a giant AI.” It was my first whack at using the service, and I think it worked pretty well.

I wrote this today for a list that’s mostly populated by folks in overlapping music, broadcasting, legal, tech, and other businesses who share a common interest in what’s happening to the arts and artists they care about in a world now turning almost completely digital.—Doc

Here is a question I hope can get us out of our heads, our histories in the businesses (music, broadcasting, entertainment, publishing, law, pick-your-art), and up past the 30,000-foot level, out into space, so its possible, at least conceptually, to see the digital world that now coexists with the physical one, but with completely new blessings and curses that may have little to do with the physical world models that operate with and under it.

With that in mind, let’s try putting our minds outside the supply side of the marketplace, with all its incumbent mechanisms and rules, and where all of us have operated for the duration. We’re in space now, looking down on the digital and physical worlds, free to see what might be possible in these co-worlds.

Now try visiting this question: As a consumer or customer (not all the same) of artistic goods, what would you be willing to pay for them if payment was easy and on your terms and not just those of incumbent industries and their regulatory frameworks?

For example, Would you pay the recording artists, performers, producers, and composers the tiny amounts most of them get from a play on Spotify, Amazon, YouTube, Apple Music, Pandora, SiriusXM, a radio station or indirectly through the movies or TV shows that feature those goods?

Try not to be mindful of standing copyright regimes, deals made between all the parties in distribution chains, and subscription systems as they stand. In fact, try to put subscription out of your minds and think instead of what you would want to pay, value-for-value, in a completely open marketplace where you can pay what you like for whatever you like, on an á la carte basis. Don’t think how. Think how much. Imagine no coercion on the providers’ side. You’re the customer. You value what you use and enjoy, and are willing to pay for it on a value-for-value basis.

To help with this, imagine you have your own personal AI: one that logs all the music you hear, all the programs you watch, all the podcasts you listen to, all the radio you play in your car, and can tell you exactly how much time you spent with each. Perhaps it can tell you what composers, writers, producers, labels, and performers were involved, and help you know which you valued more and which you valued less. (Again, this is your AI, not Microsoft’s, Google’s, Facebook’s, or Apple’s. It works only for you, in your own private life.)

Then look at whatever you’re spending now, for all the subscription services you employ, for all the one-offs (concerts, movies in theaters, bands night clubs) you also pay for. Would it be more? Less? How much?

The idea here is to zero-base the ways we understand and build new and more open markets in the digital world, which is decades old at most and will be with us for many decades, centuries, or millennia to come. It should help to look at possibilities in this new non-place without the burden of leveraging models built in a world that is physical alone.

I submit that in this new world, free customers will be more valuable—to themselves and to the marketplace—than captive ones. And that sellers working toward customer capture through coercive subscription systems and favorable regulations will find less advantage than by following (respecting Adam Smith) the hand-signals of independent customers.

We don’t know yet if that will be the case. But we can at least imagine it, and see where that goes.

I’ll be talking shortly to some readers of The Intention Economy who are looking for ways to connect that economy with advertising. (Or so I gather. I’ll know more soon.) What follows is the gist of what I wrote to them in prep for the call.

First,  take a look at People vs. Adtech, and/or Separating Advertising’s Wheat and Chaff.

Both are still valid (IMHO), but don’t yet cover what A.I. will inevitably do to advertising. There are two possible ways that can go.

One is toward hyper-personalized advertising based on even more pernicious uninvited tracking than we already have, with A.I.s rather than lawyers and hired intermediaries finding loopholes in privacy law that will automate specious forms of “consent” far more efficiently than possible without it.

The other is toward finding the best vectors for targeting the right audiences rather than the most-tracked individuals—and to find those amidst the millions of podcasts, newsletters, blogs, mainstream media, and other online outlets into the ever-widening world of thought, opinion, news, scholarship, journalism, sports, and the rest of it.

The former will make tracking and personalized targeting far worse, and the latter will make advertising targeted at audiences far better. It will also do a much better job of supporting journalism in the process because more money can get through to publishers and reporters who won’t be fed by an evil hand they avoid biting.

Those two directions are the chaff-vs-wheat choices for A.I.’s future in advertising. For now, there is surely far more action happening with the former than with the latter, given the sizes of today’s spinning adtech flywheels. But this also means there will be bigger opportunities with the latter: a blue ocean away from the red one.

What makes the intention economy ocean blue is that it will exist almost entirely outside both those advertising systems—and inside horizons that are far more expansive than can be seen through the lens of advertising and marketing as we’ve known them.

Here the opportunities will be in creating better signaling from demand to supply, and better intermediation between them: forms that will safeguard the privacy needs of individuals and the legitimate needs of businesses. In some cases there will be no intermediation at all—just forms of agency on both sides that are friendly to each other and can interact directly. And, where intermediations are required, they will find a wide-open space for what we’ve long called fourth parties.

To visualize the opportunities here, think of every customer as a boat afloat on a sea of goods and services, and friendly to the ecosystems where demand encourages supply at least as well as supply satisfies demand.

If you’re looking for market opportunities in this vast new ocean, here are thirteen of them.

I asked ChatGPT for a three-day itinerary to give visitors to Santa Barbara. Here ya go:

Day 1:

• Start the day with breakfast at the Shoreline Beach Cafe, which has a beautiful view of the ocean.
• After breakfast, head to Knapp’s Castle for a scenic hike and exploration of the ruins of a 20th century mansion. The hike offers stunning views of the Santa Ynez Valley.
• For lunch, grab some sandwiches or salads from the nearby Panino’s, a local favorite with fresh, high-quality ingredients.
• Spend the afternoon exploring downtown Santa Barbara, with its charming shops and cafes. Don’t miss a visit to the Santa Barbara County Courthouse, a stunning Spanish Colonial Revival building with a beautiful clock tower that offers a panoramic view of the city.
• For dinner, head to Tee-Off, a local institution that has been serving up classic American fare since 1949.

Day 2:

• Start the day with a hike up La Cumbre Peak, which offers stunning views of Santa Barbara and the Channel Islands.
• For lunch, grab some tacos from La Super-Rica Taqueria, a casual spot that was a favorite of Julia Child.
• Spend the afternoon exploring the Santa Barbara Botanic Garden, which showcases native plants and offers a peaceful escape from the city.
• For dinner, head to the Stagecoach Inn, a historic restaurant that serves up classic American fare in a cozy setting.

Day 3:

• Start the day with breakfast at Jeannine’s Bakery, a local favorite known for its delicious baked goods and breakfast items.
• Spend the morning at Hendry’s Beach, a local favorite with beautiful views and great walking trails.
• For lunch, grab some sandwiches or salads from South Coast Deli, a local favorite with fresh ingredients and creative flavor combinations.
• Spend the afternoon exploring the Santa Barbara Museum of Art, which features a diverse collection of artwork from around the world.
• For dinner, head back to downtown Santa Barbara and choose from one of the many restaurants in the area, depending on your preference. Some options include Olio e Limone Ristorante, Los Agaves, and The Lark.

I wouldn’t disagree with any of it, except maybe to note that Hendry’s Beach at sunset (where and when I shot the photo above) is mighty fine.

Of course, the answer will vary with every regeneration, but what the hell. It’s very early in our co-evolution with whatever the hell we and AI are together becoming.