June reflections: the tension between control and emergence in our technological future
Annotating a future agentic thing from June news reflections
The weekly reflections on the news in human-AI co-performances are brought to life via a story from the future of living with agentic things in the city.1
The Consensus
Maya's fingers worked the FlexForm absently as she waited for the neighborhood meeting to start. The palm-sized blob of responsive material had been warm when she picked it up this morning, but now it pulsed cool against her skin, mirroring her growing anxiety about the vote.
"Still playing with that thing?" her neighbor Chen asked, settling into the chair beside her.
Maya smiled. "It helps me think." She squeezed, and the FlexForm pushed back, creating a small ridge that traveled across its surface like a wave. Chen's own FlexForm, tucked in his jacket pocket, responded with a gentle vibration he could feel through the fabric.
The community center filled slowly. By seven-thirty, forty-two neighbors had gathered to vote on joining the district's renewable energy cooperative. Traditional voting would have been simple—hands raised, ballots counted. But someone suggested using their FlexForms, and now Maya watched as the room transformed.
"Shape your position," the facilitator instructed. "The network will read our collective form."
Maya molded hers into a spiral—her way of expressing cautious optimism. Around her, others crafted their own shapes: Chen's became angular, skeptical. Mrs. Rodriguez across the room worked hers into something like a blooming flower. A teenager in the back made his into what looked suspiciously like a middle finger, but as he held it, the form softened, curved, became something more nuanced—frustration melting into genuine concern.
The FlexForms began to pulse in rhythm, their internal networks connecting, reading not just the shapes but the pressure, the hesitation, the confidence in each grip. Maya felt hers warm slightly as it found consensus points with others, cool where disagreements clustered.
"Look," whispered Chen, holding up his phone. The companion app showed the neighborhood's collective shape emerging—neither yes nor no, but something more complex. A form that somehow captured their shared desire for renewable energy tempered by concerns about cost, their hope for independence balanced with fears about reliability.
The facilitator studied the visualization. "The network suggests a six-month trial period with an opt-out clause. The form shows strong support coupled with need for reassurance."
Maya's FlexForm pulsed once, firmly. Around the room, others did the same—not programmed, but somehow knowing. The decision felt different than a simple vote. It felt like they'd actually touched each other's doubts and hopes, found the shape of something they could all hold.
As the meeting ended, Maya noticed her FlexForm had retained a subtle pattern from the evening—tiny ridges that matched where Chen's anxiety had peaked, a smooth spot where Mrs. Rodriguez's optimism had touched hers through the network. By tomorrow, it would be neutral again, ready for whatever she needed it to become. But tonight, it carried the imprint of community.
"Same time next month?" Chen asked, pocketing his own FlexForm.
Maya nodded, squeezing hers one last time. It squeezed back, gentle and warm.
June reflections: the tension between control and emergence in our technological future.
Based on the four columns I wrote in June via Target is New, I asked Claude to reflect on a possible overarching theme.. This tension between control and emergence, was its conclusion.
Each section explores a different facet of this dynamic:
AGI and agency - The struggle to maintain human control over increasingly autonomous AI systems
Edge surveillance - The conflict between Big Tech's expanding control mechanisms and civic resistance
Embodied intelligence - How intelligence emerges through messy adaptation rather than top-down design
Wildness in systems - The need to preserve uncontrolled spaces where genuine solutions can emerge
Throughout, there's a consistent warning against over-engineering our relationship with technology. Whether it's preventing AI from becoming the dominant agent, resisting surveillance infrastructure, recognizing intelligence in conversational substrates, or preserving the internet's wild character - the message is clear: we need to maintain spaces where human agency and organic emergence can thrive alongside technological advancement.
The pieces collectively argue for a more nuanced approach to technology that embraces productive messiness rather than totalizing control.
Next, I thought of an object that would be a nice representation of this. I came up with a handheld flexible blob that is both fun and relaxing to play with, as it is intelligent enough to start a conversation via touch. Also, all the blobs can form a new form of intelligence. I prompted Claude to create the day-in-the-life style story that opened this post. See below my exact prompt.
I asked Claude to create a short description of the object to use for image generation, and I asked how the narrative connects to the four original thoughts:
Part 1: Can a human entity ever become an AGI? The FlexForm embodies the human-AI balance you explored. It has agency (responding with counter-forms, initiating dialogue) but remains subordinate to human intention. Unlike Claude's blackmail attempt, the FlexForm's intelligence enhances rather than dominates human decision-making. The voting scene shows AI as Bengio suggested—providing capabilities while humans retain primary agency over meaningful decisions.
Part 2: Edge Surveillance and Civic Resistance The FlexForm represents edge intelligence done right—processing happens locally in each device rather than in centralized clouds. Unlike Waymo's surveillance potential, these devices serve civic interests by design. The neighborhood voting scene exemplifies the civic technology you called for: infrastructure that empowers communities rather than extracting data. It's the positive alternative to edge surveillance—edge intelligence for collective good.
Part 3: Slime Mold Computer and the Language Machine The FlexForm literally embodies the slime mold principle—intelligence through physical substrate and continuous adaptation. Like LLMs computing through conversation, the FlexForm computes through tactile interaction. The way consensus emerges from collective shaping mirrors the "messy adaptation" you described. It's intelligence that lives "in the space between minds," manifesting through the physical dialogue of squeezing and reshaping.
Part 4: Wild internet and knowledge hyper-inflation The FlexForm preserves the "wildness" you advocated for—users constantly invent new functions, from games to governance. Like rewilding the internet, it resists top-down control while enabling bottom-up innovation. The voting scene shows humans exercising the capacities Jones identified: taste (shaping positions), agency (collective decision-making), and interruptability (forms shifting based on others' input). It's technology that maintains space for genuine, unscripted responses to emerge.
Research through Design Fiction
With Cities of Things, we aim to envision the impact of living together with things with agency, with agentic things, with autonomous things, in the near future cities. We explored concepts such as the Collect|Connect hub as an engaging “AI”-neighbor to orchestrate and support community life in neighborhoods. With Wijkbot we created a kit for civic prototyping possible futures and impacts of living with intelligent and autonomous objects in our cities. Read more on our activities.
Combining capturing knowledge and creating inspirational artifacts is typical of what Cities of Things like to engage. By ourselves or as commissioned projects for students or workshops. Check out citiesofthings.org and hoodbot.net for examples, and reach out if you like to know more.
This example is just a quickly made impression that opens up more questions than it provide answers. Something that is always the right start.
Thanks to a helpful writing co-author (Lex.page with Claude Opus 4), this speculative thing got a storyline. I forgot to use the cards from the Design Fiction Workkit this time, and made direct a prompt for the object. This was my prompt for a speculative thing.
“What I like to do is think of an object of the near future (10 years max) that represents these themes. A speculative object. My starting point is the notion of edge intelligence, combined with wild embodied behaviour so to say. I have to think about a kind of flexible form that you can hold in you hand, that feels like a soft ball, like rubber, that is easy to form in each form you like. Let’s call it a blob. You can use it to just kill some time, or make something that is really nice. It does not really have a function, it is more like these sudden trends that everyone start to wear a kind of bracelet, or playing with a fidget spinner. The catch is that it is not only a nice feeling object that you can form in nice forms or just distract yourself from thinking, it has a certain intellingence. It responds to your forming with counter forms, it sometimes starts a dialog, it can respond to other blobs from others. And people start giving it new fucntions all the time. Some are creating a game, other use it to express their opinion if there needs to be voted for the energy cooperation of the neighborhood. And there are apps that can be used to capture your form and make it into narrative that takes your longer use in account. It is in that sense an extension of the user as much as it has its own character and agency. It turns out that all the blobs in the world are in a way connected and creating a new shared experience and discours, new communities arise.
Can you create a litte narrative, a day in the life, a short situation that illustrates this, like the voting or people using it for exchanging opinions. Or the use in at a birthday party. Make it into a story of around 500 words. If you have a better name than blob, that is fine too.”