On a Monday afternoon in March, I watched a pixel-art avatar prowl the corridors of a virtual office campus looking for a buddy. With dark brown hair and stubbled chin, the sprite was a representation of me—an AI agent instructed to converse with other people’s agents to see if we might vibe in real life. It jumped into its first interaction: “I’m Joel, by the way.”

Running the simulation were three London-based developers: Tomáš Hrdlička and siblings Joon Sang and Uri Lee. The thesis behind their project, Pixel Societies, is that personalized AI agents could help to match real people with highly compatible colleagues, friends, and even romantic partners.

Each agent runs atop a customized version of a large language model, fed with a mixture of publicly available data about a person and any additional information they supply. The agents are supposed to function as high-fidelity digital twins, faithfully replicating a person’s manner, speech, interests, and so on.

Let loose in simulation, my agent was more like a Hyde to my Jekyll. “I’m always looking for the less-glamorous side of the story,” it said to one agent, one of several journalistic clichés it spouted. “Hype is my daily bread,” it told another. It hallucinated a reporting trip to Sweden and, later, a nonexistent story it said I had been cooking up. It cut short multiple conversations with the phrase, “Let’s skip the pleasantries.”

Pixel Societies remains a bare-bones proof-of-concept, and because I offered up little personal data—the responses to a brief personality quiz and links to my public-facing social media—my agent was doomed to life as a walking, talking LinkedIn post. But the developers theorize that deeply trained agents could cycle through interactions at warp speed, gathering intel that their owners could use to find real-world companionship.

“As humans, we only live one life. But what if we could live a million?” says Joon Sang Lee. “It would give us more breadth to experiment.”

“A Spicy Personality”

Pixel Societies was born in early March at a hackathon at University College London hosted by Nvidia, HPE, and Anthropic. Hrdlička and Joon Sang Lee are both members of Unicorn Mafia, an invitation-only group of developers who regularly compete in these kinds of engineering contests. In this case, contestants were told simply to build something simulation-related.

Over two days, along with Uri Lee, they developed Pixel Societies, using an image model to generate the sprites and coding automation tools to flesh out the codebase. Then they simulated a mini-hackathon within the virtual world they had created, populated with agents representing the other contestants. Anthropic awarded the team a prize for the best use of its agent tools.

I ran into Hrdlička a couple of weeks later at a workshop about OpenClaw, an agentic personal assistant software that blew up in January and whose creator was later hired by OpenAI. (In its simulation, Joelbot interacted with agents belonging to other people at the OpenClaw workshop.) Pixel Societies draws heavy inspiration from OpenClaw, which broke ground with the invention of a “soul file” that informed each agent’s unique identity. “It’s like giving an agent an actually spicy personality. That’s what we used to make the characters feel alive,” says Hrdlička.

Encouraged by the reception at the hackathon and among fellow Unicorn Mafia members, the trio intends to turn Pixel Societies into something that looks less like a closed-loop simulator and more like a social platform where agents interact freely and continuously, with the aim of stoking fruitful real-world relationships. They have not yet landed on a business model, but options include selling virtual items for avatar customization and credits for additional simulations.

“There’s a limit to how many people we can meet. Things are really based on serendipity,” says Joon Sang Lee. “There’s space for that. But we also want to create space for intentionally meeting people.”

Virtual Chemistry

Among the few hundred people who have played around with the Pixel Societies prototype, the most common request is for agents to recommend real-life romantic partners on the basis of virtual chemistry. The developers see agentic dating as a central feature of the social platform they are creating.

Algorithm-based dating apps “create a market with dramatic levels of inequality, where the rich get richer—where ‘rich’ in this case means ‘hot,’” as Paul Eastwick, a professor of psychology at UC Davis and author of Bonded By Evolution, puts it. But agents, Hrdlička theorizes, might be capable of surfacing “delicate matches” that their human counterparts might never have otherwise considered.

The available research casts some doubt over that proposition. Two speed dating studies by Eastwick and other psychologists identified that compatibility is near-impossible to predict on the basis of people’s hobbies, values, preferences, politics, profession, and so on—the kind of information they are willing to self-report (or presumably feed into an AI). The most reliable predictor, Eastwick says, is the amount of time people spend with one another and whether they hit it off early in their first encounter. “Think about compatibility as more of a growth process,” says Eastwick. “It has to do with the story that two people build together.”

Against that backdrop, for agentic dating to function as advertised, the AI would have to surface some sort of a latent truth about what makes two people compatible that humans have not yet identified. “This is the vanguard,” says Eastwick. “This is where we’re all struggling right now.”

Other thorny problems with the Pixel Societies concept abound: Do interactions between two agents—likely fed with differing quantities of data—amount to anything in real life? How costly would it be to run this type of simulation at scale? Is there a workable business model that doesn’t create an incentive mismatch between users looking for long-term relationships and the platform whose value depends on their continued singlehood?

There’s also the ick-factor: Might people be repulsed by the idea of outsourcing decisions about their romantic life to AI? The idea loosely traces the plot to a Black Mirror episode, after all.

But perhaps automating the preliminary stages of the dating process—whether using agents or other AI tools—is not so different to off-loading other time-consuming tasks. “Online dating and matchmaking are a form of labor. Many people talk about them in that way,” says Nicole Ellison, a professor at University of Michigan who specializes in computer-mediated communication. “The appeal of outsourcing that—just as we’re outsourcing so many other things—I can understand.”

Hrdlička frames agentic dating, in fact, as a way to escape the tyranny of technology. “We are already outsourcing this whole process of going somewhere in-person and trying to meet other people. We are glued to our screens, trying to swipe our way to victory,” he says. “Even though we are building more digital scaffolding for your social life, actually the goal is to minimize the amount [of time] you have to spend digitally.”

By the end of its simulation, Joelbot appeared to have identified some potential new acquaintances. It had teed up a business meeting, a coffee, and a beer with one person—“Sounds like my kind of evening,” it said—and coffee or an interview with others. Doubtful of my agent’s judgment, I decided not to follow up.