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.

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.

Most AI news is about what the giants (OpenAI/Microsoft, Meta, Google/Apple, Amazon, Adobe, Nvidia) are doing (seven $trillion, anyone?), or what AI is doing for business (all of Forbes’ AI 50). Against all that, personal AI appears to be about where personal computing was in 1974: no longer an oxymoron but discussed more than delivered.

For evidence, look up “personal AI.” All the results will be about business (see here and here) or “assistants” that are just suction cups on the tentacles of giants (Siri, Google Assistant, Alexa, Bixby), or wannabes that do the same kind of thing (Lindy, Hound, DataBot).

There may be others, but three exceptions I know are Kin, Personal AI and Pi.

Personal AI is finding its most promoted early uses on the side of business more than the side of customers. Zapier, for example, explains that Personal AI “can be used as a productivity or business tool.”

Kin and Pi are personal assistants that help you with your life by surveilling your activities for your own benefit. I’ve signed up for both, but have only experienced Pit,” or “just vent,” when I ask it to help me with the stuff outlined in (and under) the AI-generated image above, it wants to hook me up with a bunch of siloed platforms that cost money, or to do geeky things (PostgreSQL, MongoDB, Python on my own computer. Provisional conclusion: Pi means well, but the tools aren’t there yet. [Later… Looks like it’s going to morph into some kind of B2B thing, or be abandoned outright, now that Inflection AI’s CEO, Mustafa Suleyman is gone to Microsoft. Hmm… will Microsoft do what we’d like in this space?]

Open source approaches are out there: OpenDAN, Khoj, Kwaai , and Llama are four, and I know at least one will be at VRM Day and IIW.

So, since personal AI may finally be what pushes VRM into becoming a Real Thing, we’ll make it the focus of our next VRM Day.

As always, VRM Day will precede IIW in the same location: the Boole Room of the Computer History Museum in Mountain View, just off Highway 101 in the heart of Silicon Valley. It’ll be on Monday, 15 April, and start at 9am. There’s a Starbucks across the street and ample parking because the museum is officially closed on Mondays, but the door is open. We lunch outdoors (it’s always clear) at the sports bar on the other corner.

Registration is open now at this Eventbrite link:

https://vrmday2024a.eventbrite.com

You can also just show up, but registering gives us a rough headcount, which is helpful for bringing in the right number of chairs and stuff like that.

See you there!