From Artificiality This Week * Our Gathering: Our Artificiality Summit 2025 will be held on October 23-25 in Bend, Oregon. The
AI agents are evolving with orchestration layers enabling modular, autonomous systems beyond traditional SaaS, reshaping workflows, labor, and software design.
David Wolpert warns AI networks may evolve beyond human math, creating unpredictable, emergent intelligence that defies control and comprehension.
OpenAI and Google Usher in The Intimacy Economy, Reasons You'll Need an AI Assistant—Even if You Don't Want One, Is AI The Cure for Male Loneliness, and more!
This week, OpenAI and Google announced new capabilities in their generative AI tools that are designed to capture a new level of intimate knowledge about their users. Real-time conversations tug at our interest in chatting, video capture taps our need to share our worlds, and flirty voices tap our need to be loved. Gone are the days of platforms inviting us to submit information. Gone are the days of inferring through social media scrolling patterns. Today, Big Tech has created the ultimate method of capturing data: an inviting voice that simply asks us to share.
In October 2023, I wrote:
Intimacy with technology has been the territory of science fiction. From the human-robot marriage in Isaac Asimov’s Forward the Foundation to the android Data’s girlfriend in Star Trek The Next Generation to Theodore’s romance with the AI Samantha in Her, we have been entertained by the idea of human-machine love. What happens if we are able to live those stories ourselves?
Some might have thought that idea was a bit over the top. But today, all you have to do is look at this capture of comments on Reddit to see that, in fact, people already find ChatGPT-4o to be an inviting and desirable companion. These people are already talking with ChatGPT-4o about their needs and desires. What might it learn?
ChatGPT currently “remembers” things about its users by capturing little nuggets of information from chats. I recently asked it to write a narrative about me based on what it knew about me. It said,
[Your Name] is a dynamic middle-aged entrepreneur and thought leader based in New Zealand, with a diverse array of interests and expertise. Passionate about the intersection of AI, complexity science, and organizational change, [Your Name] is dedicated to exploring and advancing these fields through research, presentations, and innovative projects.
As a pioneer in the realm of AI agents, [Your Name] leverages wayfinding as a metaphor to describe the nuanced skills required for managing change in complex systems. This approach emphasizes preparing teams for adventure and harnessing the emergence of ideas and talent from the edges of the system. This philosophy is at the heart of [Your Name]'s market research presentations and their ongoing exploration of agentic AI.
A natural problem-solver, [Your Name] balances intuition with systematic planning, analyzing context, constraints, and desired outcomes to navigate challenges effectively. This analytical mindset is complemented by their interest in complexity science, which informs their evaluation of AI agents across spectrums of perception, reasoning, and action.
Together with their wife and business partner, [Your Name] speaks at corporate events and major conferences, sharing insights on AI and complexity.
With a new Apple Watch Ultra adorning their wrist and an adventurous spirit guiding their endeavors, [Your Name] continues to chart new paths in the ever-evolving landscape of technology and entrepreneurship.
Some of those details aren’t correct—I was recently in New Zealand, not based in New Zealand—but most of it is. And I’m tempted to correct the incorrect, giving OpenAI even more detail than it already has.
On the one hand, this could be quite helpful. The more it knows, the more accurate its future responses might be. But what else will it do with this information? How might it use this information to target ads or upsell me to future products? And is it appropriate for OpenAI to capture this information at all?
OpenAI made a large business shift this week by opening its most advanced model to everyone for free. It is doing this in return for intimate information about its users—since free user data is not private. And this isn't the end of the road. As Helen points out, the future of information consumption on the internet will require AI assistants which will capture even more intimate data.
We used to watch ads for information in the information economy and pay attention to access scrolling feeds and videos in the attention economy. We are now paying for ChatGPT with our intimate information.
Again, as I wrote in October 2023:
But we should learn from what’s come before. Commercially motivated, unconstrained, and poorly designed solutions for information scarcity eroded the veracity of information. A similar pattern happened with attention. Eroding our intimacy destroys us so at our peril do we blindly accept the tenets of the intimacy economy. This time there is even more at stake. The promise has a utopian flavor, but the peril is in all ways a dystopia.
How We Live Is How We Die, by Pema Chödrön
If you are after a complete antidote to AI, this book might just fit the bill. When I was diagnosed with cancer in 2018, I took up meditation as a way to deal with the waves of panic that accompanies such a diagnosis. Along the way I began to realize that meditation is not about stress relief or anxiety reduction or even relaxation. That it's something altogether different. I have listened to Buddhist teachings in my mediation app (which contains a satisfying mix of Eastern philosophy and modern neuroscience as well as various meditation practices) but I have not read any teachings until I picked this book up in a local store.
Pema Chödrön was born Deirdre Blomfield-Brown in 1936, in New York City and became a novice nun in 1974 and is now the director of Gampo Abbey in rural Cape Breton, Nova Scotia. In this compact and informative book, she takes you through how by reframing your perspective on life and cultivating a new relationship with your neuroses and the emotions they elicit, you can develop skills that will make the process of dying less terrifying.
Like I say, a beautiful antidote to the machines and all that their masters have had to say this week.
How we work with our thoughts and emotions now is what we'll take with us when we die. We can't put it off until the end; by then it will be too late. So now is the time. How we live is how we die.
The Artificiality Weekend Briefing: About AI, Not Written by AI
